@article{
 title = {Conserved and distinct roles of H3K27me3 demethylases regulating flowering time in Brassica rapa},
 type = {article},
 year = {2022},
 websites = {https://onlinelibrary.wiley.com/doi/10.1111/pce.14258},
 month = {2},
 day = {9},
 id = {565481b2-4d7a-3d07-aab4-98df770716e3},
 created = {2022-02-10T09:18:35.092Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2022-02-10T09:19:29.081Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Poza‐Viejo, Laura and Payá‐Milans, Miriam and San Martín‐Uriz, Patxi and Castro‐Labrador, Laura and Lara‐Astiaso, David and Wilkinson, Mark D. and Piñeiro, Manuel and Jarillo, José A. and Crevillén, Pedro},
 doi = {10.1111/pce.14258},
 journal = {Plant, Cell & Environment}
}

@article{
 title = {Semantic modelling of common data elements for rare disease registries, and a prototype workflow for their deployment over registry data},
 type = {article},
 year = {2022},
 pages = {9},
 volume = {13},
 month = {12},
 day = {15},
 id = {afd69365-ee27-3d25-9bbd-526e8ba77a18},
 created = {2022-05-31T10:14:52.129Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2022-07-14T08:46:29.167Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 bibtype = {article},
 author = {Kaliyaperumal, Rajaram and Wilkinson, Mark D. and Moreno, Pablo Alarcón and Benis, Nirupama and Cornet, Ronald and dos Santos Vieira, Bruna and Dumontier, Michel and Bernabé, César Henrique and Jacobsen, Annika and Le Cornec, Clémence M. A. and Godoy, Mario Prieto and Queralt-Rosinach, Núria and Schultze Kool, Leo J. and Swertz, Morris A. and van Damme, Philip and van der Velde, K. Joeri and Lalout, Nawel and Zhang, Shuxin and Roos, Marco},
 doi = {10.1186/s13326-022-00264-6},
 journal = {Journal of Biomedical Semantics},
 number = {1}
}

@article{
 title = {The Indole-3-Acetamide-Induced Arabidopsis Transcription Factor MYB74 Decreases Plant Growth and Contributes to the Control of Osmotic Stress Responses},
 type = {article},
 year = {2022},
 volume = {13},
 websites = {https://www.frontiersin.org/article/10.3389/fpls.2022.928386},
 id = {fe696c92-6a29-362a-bf00-a99eb14cc5e9},
 created = {2022-07-14T08:42:23.035Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2022-07-14T08:42:23.337Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {10.3389/fpls.2022.928386},
 source_type = {article},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {The accumulation of the auxin precursor indole-3-acetamide (IAM) in the ami1 mutant has recently been reported to reduce plant growth and to trigger abiotic stress responses in Arabidopsis thaliana. The observed response includes the induction of abscisic acid (ABA) biosynthesis through the promotion of NCED3 expression. The mechanism by which plant growth is limited, however, remained largely unclear. Here, we investigated the transcriptional responses evoked by the exogenous application of IAM using comprehensive RNA-sequencing (RNA-seq) and reverse genetics approaches. The RNA-seq results highlighted the induction of a small number of genes, including the R2R3 MYB transcription factor genes MYB74 and MYB102. The two MYB factors are known to respond to various stress cues and to ABA. Consistent with a role as negative plant growth regulator, conditional MYB74 overexpressor lines showed a considerable growth reduction. RNA-seq analysis of MYB74 mutants indicated an association of MYB74 with responses to osmotic stress, water deprivation, and seed development, which further linked MYB74 with the observed ami1 osmotic stress and seed phenotype. Collectively, our findings point toward a role for MYB74 in plant growth control and in responses to abiotic stress stimuli.},
 bibtype = {article},
 author = {Ortiz-García, Paloma and Pérez-Alonso, Marta-Marina and González Ortega-Villaizán, Adrián and Sánchez-Parra, Beatriz and Ludwig-Müller, Jutta and Wilkinson, Mark D and Pollmann, Stephan},
 doi = {10.3389/fpls.2022.928386},
 journal = {Frontiers in Plant Science}
}

The accumulation of the auxin precursor indole-3-acetamide (IAM) in the ami1 mutant has recently been reported to reduce plant growth and to trigger abiotic stress responses in Arabidopsis thaliana. The observed response includes the induction of abscisic acid (ABA) biosynthesis through the promotion of NCED3 expression. The mechanism by which plant growth is limited, however, remained largely unclear. Here, we investigated the transcriptional responses evoked by the exogenous application of IAM using comprehensive RNA-sequencing (RNA-seq) and reverse genetics approaches. The RNA-seq results highlighted the induction of a small number of genes, including the R2R3 MYB transcription factor genes MYB74 and MYB102. The two MYB factors are known to respond to various stress cues and to ABA. Consistent with a role as negative plant growth regulator, conditional MYB74 overexpressor lines showed a considerable growth reduction. RNA-seq analysis of MYB74 mutants indicated an association of MYB74 with responses to osmotic stress, water deprivation, and seed development, which further linked MYB74 with the observed ami1 osmotic stress and seed phenotype. Collectively, our findings point toward a role for MYB74 in plant growth control and in responses to abiotic stress stimuli.

@article{
 title = {FAIR Data Point: A FAIR-oriented approach for metadata publication},
 type = {article},
 year = {2022},
 pages = {1-21},
 websites = {https://direct.mit.edu/dint/article/doi/10.1162/dint_a_00160/112599/FAIR-Data-Point-A-FAIR-oriented-approach-for},
 month = {8},
 day = {10},
 id = {a3a37cbd-061d-35c2-9dc2-50afae31f8d4},
 created = {2022-08-26T07:26:00.913Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2022-08-26T07:26:00.913Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {Metadata, data about other digital objects, play an important role in FAIR with a direct relation to all FAIR principles. In this paper we present and discuss the FAIR Data Point (FDP), a software architecture aiming to define a common approach to publish semantically-rich and machine-actionable metadata according to the FAIR principles. We present the core components and features of the FDP, its approach to metadata provision, the criteria to evaluate whether an application adheres to the FDP specifications and the service to register, index and allow users to search for metadata content of available FDPs.},
 bibtype = {article},
 author = {da Silva Santos, Luiz Olavo Bonino and Burger, Kees and Kaliyaperumal, Rajaram and Wilkinson, Mark D.},
 doi = {10.1162/dint_a_00160},
 journal = {Data Intelligence}
}

Metadata, data about other digital objects, play an important role in FAIR with a direct relation to all FAIR principles. In this paper we present and discuss the FAIR Data Point (FDP), a software architecture aiming to define a common approach to publish semantically-rich and machine-actionable metadata according to the FAIR principles. We present the core components and features of the FDP, its approach to metadata provision, the criteria to evaluate whether an application adheres to the FDP specifications and the service to register, index and allow users to search for metadata content of available FDPs.

@article{
 title = {The FAIR Data Point: Interfaces and Tooling},
 type = {article},
 year = {2022},
 pages = {1-18},
 month = {9},
 day = {28},
 id = {e43e1e38-66dc-368c-807d-54ea5cc2e1c7},
 created = {2022-10-10T09:53:21.433Z},
 file_attached = {true},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2023-01-31T08:25:41.282Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {While the FAIR Principles do not specify a technical solution for ‘FAIRness’, it was clear from the outset of the FAIR initiative that it would be useful to have commodity software and tooling that would simplify the creation of FAIR-compliant resources. The FAIR Data Point is a metadata repository that follows the DCAT(2) schema, and utilizes the Linked Data Platform to manage the hierarchical metadata layers as LDP Containers. There has been a recent flurry of development activity around the FAIR Data Point that has significantly improved its power and ease-of-use. Here we describe five specific tools—an installer, a loader, two Web-based interfaces, and an indexer—aimed at maximizing the uptake and utility of the FAIR Data Point},
 bibtype = {article},
 author = {Benhamed, Ousamma Mohammed and Burger, Kees and Kaliyaperumal, Rajaram and da Silva Santos, Luiz Olavo Bonino and Suchánek, Marek and Slifka, Jan and Wilkinson, Mark D},
 doi = {10.1162/dint_a_00161},
 journal = {Data Intelligence}
}

While the FAIR Principles do not specify a technical solution for ‘FAIRness’, it was clear from the outset of the FAIR initiative that it would be useful to have commodity software and tooling that would simplify the creation of FAIR-compliant resources. The FAIR Data Point is a metadata repository that follows the DCAT(2) schema, and utilizes the Linked Data Platform to manage the hierarchical metadata layers as LDP Containers. There has been a recent flurry of development activity around the FAIR Data Point that has significantly improved its power and ease-of-use. Here we describe five specific tools—an installer, a loader, two Web-based interfaces, and an indexer—aimed at maximizing the uptake and utility of the FAIR Data Point

@article{
 title = {Towards FAIRification of sensitive and fragmented rare disease patient data: challenges and solutions in European reference network registries},
 type = {article},
 year = {2022},
 pages = {436},
 volume = {17},
 websites = {https://ojrd.biomedcentral.com/articles/10.1186/s13023-022-02558-5},
 month = {12},
 day = {14},
 id = {5d85b7ca-3d95-3ca1-8bbd-b6b71c785674},
 created = {2023-01-30T12:21:40.056Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2023-01-30T12:21:40.056Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 bibtype = {article},
 author = {dos Santos Vieira, Bruna and Bernabé, César H. and Zhang, Shuxin and Abaza, Haitham and Benis, Nirupama and Cámara, Alberto and Cornet, Ronald and Le Cornec, Clémence M. A. and ’t Hoen, Peter A. C. and Schaefer, Franz and van der Velde, K. Joeri and Swertz, Morris A. and Wilkinson, Mark D. and Jacobsen, Annika and Roos, Marco},
 doi = {10.1186/s13023-022-02558-5},
 journal = {Orphanet Journal of Rare Diseases},
 number = {1}
}

@article{
 title = {Predicting microbiomes through a deep latent space},
 type = {article},
 year = {2021},
 pages = {1444-1451},
 volume = {37},
 websites = {https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btaa971/5988714,https://academic.oup.com/bioinformatics/article/37/10/1444/5988714},
 month = {6},
 day = {16},
 id = {c467687d-616f-393d-9251-48d732e29b5b},
 created = {2020-12-01T10:10:41.382Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2021-08-25T15:31:54.873Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Garcia-Jimenez2020},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {García-Jiménez, Beatriz and Muñoz, Jorge and Cabello, Sara and Medina, Joaquín and Wilkinson, Mark D},
 editor = {Jonathan, Wren},
 doi = {10.1093/bioinformatics/btaa971},
 journal = {Bioinformatics},
 number = {10}
}

@article{
 title = {Endogenous indole-3-acetamide levels contribute to the crosstalk between auxin and abscisic acid, and trigger plant stress responses in Arabidopsis},
 type = {article},
 year = {2021},
 pages = {459-475},
 volume = {72},
 websites = {https://academic.oup.com/jxb/article/72/2/459/5928899},
 month = {2},
 day = {2},
 id = {12f5f83b-e084-3fad-8bb3-7c620ba2446b},
 created = {2021-03-03T10:05:14.406Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2021-03-03T10:05:15.340Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Perez-Alonso2020},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {The evolutionary success of plants relies to a large extent on their extraordinary ability to adapt to changes in their environment. These adaptations require that plants balance their growth with their stress responses. Plant hormones are crucial mediators orchestrating the underlying adaptive processes. However, whether and how the growth-related hormone auxin and the stress-related hormones jasmonic acid, salicylic acid, and abscisic acid (ABA) are coordinated remains largely elusive. Here, we analyse the physiological role of AMIDASE 1 (AMI1) in Arabidopsis plant growth and its possible connection to plant adaptations to abiotic stresses. AMI1 contributes to cellular auxin homeostasis by catalysing the conversion of indole-acetamide into the major plant auxin indole-3-acetic acid. Functional impairment of AMI1 increases the plant’s stress status rendering mutant plants more susceptible to abiotic stresses. Transcriptomic analysis of ami1 mutants disclosed the reprogramming of a considerable number of stress-related genes, including jasmonic acid and ABA biosynthesis genes. The ami1 mutants exhibit only moderately repressed growth but an enhanced ABA accumulation, which suggests a role for AMI1 in the crosstalk between auxin and ABA. Altogether, our results suggest that AMI1 is involved in coordinating the trade-off between plant growth and stress responses, balancing auxin and ABA homeostasis.},
 bibtype = {article},
 author = {Pérez-Alonso, Marta-Marina and Ortiz-García, Paloma and Moya-Cuevas, José and Lehmann, Thomas and Sánchez-Parra, Beatriz and Björk, Robert G and Karim, Sazzad and Amirjani, Mohammad R and Aronsson, Henrik and Wilkinson, Mark D and Pollmann, Stephan},
 editor = {Napier, Richard},
 doi = {10.1093/jxb/eraa485},
 journal = {Journal of Experimental Botany},
 number = {2}
}

The evolutionary success of plants relies to a large extent on their extraordinary ability to adapt to changes in their environment. These adaptations require that plants balance their growth with their stress responses. Plant hormones are crucial mediators orchestrating the underlying adaptive processes. However, whether and how the growth-related hormone auxin and the stress-related hormones jasmonic acid, salicylic acid, and abscisic acid (ABA) are coordinated remains largely elusive. Here, we analyse the physiological role of AMIDASE 1 (AMI1) in Arabidopsis plant growth and its possible connection to plant adaptations to abiotic stresses. AMI1 contributes to cellular auxin homeostasis by catalysing the conversion of indole-acetamide into the major plant auxin indole-3-acetic acid. Functional impairment of AMI1 increases the plant’s stress status rendering mutant plants more susceptible to abiotic stresses. Transcriptomic analysis of ami1 mutants disclosed the reprogramming of a considerable number of stress-related genes, including jasmonic acid and ABA biosynthesis genes. The ami1 mutants exhibit only moderately repressed growth but an enhanced ABA accumulation, which suggests a role for AMI1 in the crosstalk between auxin and ABA. Altogether, our results suggest that AMI1 is involved in coordinating the trade-off between plant growth and stress responses, balancing auxin and ABA homeostasis.

@inproceedings{
 title = {Reuse of Design Pattern Measurements for Health Data},
 type = {inproceedings},
 year = {2021},
 websites = {http://ceur-ws.org/Vol-2969/},
 city = {Bolzano, Italy, September 11-18},
 id = {26b6f146-ca73-3c24-8bd1-3859abd348a7},
 created = {2021-10-24T07:49:32.126Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2021-11-30T07:59:57.162Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Queralt-Rosinach2021},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Queralt-Rosinach, Núria and Wilkinson, Mark D and Kaliyaperumal, Rajaram and Bernabé, César and Long, Qinqin and Dumontier, Michel and Schofield, Paul and Roos, Marco},
 editor = {Sanfilippo, Emilio M. and Kutz, Oliver and Troquard, Nicolas and Hahmann., Torsten and Masolo, Claudio and Hoehndorf, Robert and Vita, Randi},
 booktitle = {12th International Conference on Formal Ontology in Information Systems (FOIS 2021) Demonstrations}
}

@article{
 title = {FAIR Principles for Research Software (FAIR4RS Principles)},
 type = {article},
 year = {2021},
 websites = {https://zenodo.org/record/6623556#.YqCJTJNBwlw},
 publisher = {Research Data Alliance},
 id = {572a15aa-a4b8-3e5f-8171-068a787c88b7},
 created = {2022-07-14T08:46:28.917Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2022-07-14T08:46:28.917Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {https://doi.org/10.15497/rda00068},
 source_type = {article},
 private_publication = {false},
 bibtype = {article},
 author = {Chue Hong, Neil P and Katz, Daniel S and Barker, Michelle and Lamprecht, Anna-Lena and Martinez, Carlos and Psomopoulos, Fotis E and Harrow, Jen and Castro, Leyla Jael and Gruenpeter, Morane and Martinez, Paula Andrea and Honeyman, Tom},
 doi = {10.15497/RDA00068}
}

@misc{
 title = {RO-Crate Metadata Specification 1.1.1},
 type = {misc},
 year = {2021},
 websites = {https://doi.org/10.5281/zenodo.4541002},
 month = {2},
 id = {caf6d176-6091-393d-9f32-091416d5ce64},
 created = {2022-07-14T08:46:28.936Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2022-07-14T08:46:28.936Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {peter_sefton_2021_4541002},
 source_type = {manual},
 notes = {Recommendation published by researchobject.org - <br/>see https://w3id.org/ro/crate/1.1 for web version.},
 private_publication = {false},
 bibtype = {misc},
 author = {Sefton, Peter and Carragáin, Eoghan Ó and Soiland-Reyes, Stian and Corcho, Oscar and Garijo, Daniel and Palma, Raul and Coppens, Frederik and Goble, Carole and Fernández, José María and Chard, Kyle and Gomez-Perez, Jose Manuel and Crusoe, Michael R and Eguinoa, Ignacio and Juty, Nick and Holmes, Kristi and Clark, Jason A and Capella-Gutierrez, Salvador and Gray, Alasdair J G and Owen, Stuart and Williams, Alan R and Tartari, Giacomo and Bacall, Finn and Thelen, Thomas and Ménager, Hervé and Rodríguez-Navas, Laura and Walk, Paul and brandon whitehead, undefined and Wilkinson, Mark and Groth, Paul and Bremer, Erich and Castro, L J Garcia and Sebby, Karl and Kanitz, Alexander and Trisovic, Ana and Kennedy, Gavin and Graves, Mark and Koehorst, Jasper and Leo, Simone and Portier, Marc},
 doi = {10.5281/zenodo.4541002}
}

@misc{
 title = {A Fresh Look at FAIR for Research Software},
 type = {misc},
 year = {2021},
 keywords = {FOS: Computer and information sciences,Software Engineering (cs.SE)},
 websites = {https://arxiv.org/abs/2101.10883},
 publisher = {arXiv},
 id = {9256d0ac-8f75-3e57-97e9-4c91d6cf7319},
 created = {2022-07-14T09:01:21.081Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2022-07-14T09:01:21.081Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {https://doi.org/10.48550/arxiv.2101.10883},
 source_type = {misc},
 private_publication = {false},
 bibtype = {misc},
 author = {Katz, Daniel S and Gruenpeter, Morane and Honeyman, Tom and Hwang, Lorraine and Wilkinson, Mark D and Sochat, Vanessa and Anzt, Hartwig and Goble, Carole and 1, for FAIR4RS Subgroup},
 doi = {10.48550/ARXIV.2101.10883}
}

@article{
 title = {BioHackathon 2015: Semantics of data for life sciences and reproducible research},
 type = {article},
 year = {2020},
 pages = {136},
 volume = {9},
 websites = {https://f1000research.com/articles/9-136/v1},
 month = {2},
 day = {24},
 id = {68a7fa20-e2c3-331d-a8d2-b7c17bb746f1},
 created = {2020-02-25T08:55:52.881Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2020-07-10T11:55:06.907Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Vos2020},
 private_publication = {false},
 abstract = {We report on the activities of the 2015 edition of the BioHackathon, an annual event that brings together researchers and developers from around the world to develop tools and technologies that promote the reusability of biological data. We discuss issues surrounding the representation, publication, integration, mining and reuse of biological data and metadata across a wide range of biomedical data types of relevance for the life sciences, including chemistry, genotypes and phenotypes, orthology and phylogeny, proteomics, genomics, glycomics, and metabolomics. We describe our progress to address ongoing challenges to the reusability and reproducibility of research results, and identify outstanding issues that continue to impede the progress of bioinformatics research. We share our perspective on the state of the art, continued challenges, and goals for future research and development for the life sciences Semantic Web.},
 bibtype = {article},
 author = {Vos, Rutger A. and Katayama, Toshiaki and Mishima, Hiroyuki and Kawano, Shin and Kawashima, Shuichi and Kim, Jin-Dong and Moriya, Yuki and Tokimatsu, Toshiaki and Yamaguchi, Atsuko and Yamamoto, Yasunori and Wu, Hongyan and Amstutz, Peter and Antezana, Erick and Aoki, Nobuyuki P. and Arakawa, Kazuharu and Bolleman, Jerven T. and Bolton, Evan and Bonnal, Raoul J. P. and Bono, Hidemasa and Burger, Kees and Chiba, Hirokazu and Cohen, Kevin B. and Deutsch, Eric W. and Fernández-Breis, Jesualdo T. and Fu, Gang and Fujisawa, Takatomo and Fukushima, Atsushi and García, Alexander and Goto, Naohisa and Groza, Tudor and Hercus, Colin and Hoehndorf, Robert and Itaya, Kotone and Juty, Nick and Kawashima, Takeshi and Kim, Jee-Hyub and Kinjo, Akira R. and Kotera, Masaaki and Kozaki, Kouji and Kumagai, Sadahiro and Kushida, Tatsuya and Lütteke, Thomas and Matsubara, Masaaki and Miyamoto, Joe and Mohsen, Attayeb and Mori, Hiroshi and Naito, Yuki and Nakazato, Takeru and Nguyen-Xuan, Jeremy and Nishida, Kozo and Nishida, Naoki and Nishide, Hiroyo and Ogishima, Soichi and Ohta, Tazro and Okuda, Shujiro and Paten, Benedict and Perret, Jean-Luc and Prathipati, Philip and Prins, Pjotr and Queralt-Rosinach, Núria and Shinmachi, Daisuke and Suzuki, Shinya and Tabata, Tsuyosi and Takatsuki, Terue and Taylor, Kieron and Thompson, Mark and Uchiyama, Ikuo and Vieira, Bruno and Wei, Chih-Hsuan and Wilkinson, Mark and Yamada, Issaku and Yamanaka, Ryota and Yoshitake, Kazutoshi and Yoshizawa, Akiyasu C. and Dumontier, Michel and Kosaki, Kenjiro and Takagi, Toshihisa},
 doi = {10.12688/f1000research.18236.1},
 journal = {F1000Research}
}

We report on the activities of the 2015 edition of the BioHackathon, an annual event that brings together researchers and developers from around the world to develop tools and technologies that promote the reusability of biological data. We discuss issues surrounding the representation, publication, integration, mining and reuse of biological data and metadata across a wide range of biomedical data types of relevance for the life sciences, including chemistry, genotypes and phenotypes, orthology and phylogeny, proteomics, genomics, glycomics, and metabolomics. We describe our progress to address ongoing challenges to the reusability and reproducibility of research results, and identify outstanding issues that continue to impede the progress of bioinformatics research. We share our perspective on the state of the art, continued challenges, and goals for future research and development for the life sciences Semantic Web.

@article{
 title = {Data-driven classification of the certainty of scholarly assertions},
 type = {article},
 year = {2020},
 pages = {e8871},
 volume = {8},
 websites = {https://peerj.com/articles/8871},
 month = {4},
 day = {21},
 id = {0b32f8c2-f0a8-3480-bb74-cde89e8d0992},
 created = {2020-05-12T12:13:44.995Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2020-07-10T11:55:06.849Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Prieto2020},
 private_publication = {false},
 abstract = {The grammatical structures scholars use to express their assertions are intended to convey various degrees of certainty or speculation. Prior studies have suggested a variety of categorization systems for scholarly certainty; however, these have not been objectively tested for their validity, particularly with respect to representing the interpretation by the reader, rather than the intention of the author. In this study, we use a series of questionnaires to determine how researchers classify various scholarly assertions, using three distinct certainty classification systems. We find that there are three distinct categories of certainty along a spectrum from high to low. We show that these categories can be detected in an automated manner, using a machine learning model, with a cross-validation accuracy of 89.2% relative to an author-annotated corpus, and 82.2% accuracy against a publicly-annotated corpus. This finding provides an opportunity for contextual metadata related to certainty to be captured as a part of text-mining pipelines, which currently miss these subtle linguistic cues. We provide an exemplar machine-accessible representation—a Nanopublication—where certainty category is embedded as metadata in a formal, ontology-based manner within text-mined scholarly assertions.},
 bibtype = {article},
 author = {Prieto, Mario and Deus, Helena and de Waard, Anita and Schultes, Erik and García-Jiménez, Beatriz and Wilkinson, Mark D.},
 doi = {10.7717/peerj.8871},
 journal = {PeerJ}
}

The grammatical structures scholars use to express their assertions are intended to convey various degrees of certainty or speculation. Prior studies have suggested a variety of categorization systems for scholarly certainty; however, these have not been objectively tested for their validity, particularly with respect to representing the interpretation by the reader, rather than the intention of the author. In this study, we use a series of questionnaires to determine how researchers classify various scholarly assertions, using three distinct certainty classification systems. We find that there are three distinct categories of certainty along a spectrum from high to low. We show that these categories can be detected in an automated manner, using a machine learning model, with a cross-validation accuracy of 89.2% relative to an author-annotated corpus, and 82.2% accuracy against a publicly-annotated corpus. This finding provides an opportunity for contextual metadata related to certainty to be captured as a part of text-mining pipelines, which currently miss these subtle linguistic cues. We provide an exemplar machine-accessible representation—a Nanopublication—where certainty category is embedded as metadata in a formal, ontology-based manner within text-mined scholarly assertions.

@article{
 title = {FAIR Principles: Interpretations and Implementation Considerations},
 type = {article},
 year = {2020},
 pages = {10-29},
 volume = {2},
 websites = {https://www.mitpressjournals.org/doi/abs/10.1162/dint_r_00024},
 month = {1},
 id = {bfeb8cec-d455-3ef0-acf5-1b2e0ad24181},
 created = {2020-07-20T08:38:47.818Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2020-12-01T10:10:42.667Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Jacobsen2020},
 private_publication = {false},
 abstract = {The FAIR principles have been widely cited, endorsed and adopted by a broad range of stakeholders since their publication in 2016. By intention, the 15 FAIR guiding principles do not dictate specific technological implementations, but provide guidance for improving Findability, Accessibility, Interoperability and Reusability of digital resources. This has likely contributed to the broad adoption of the FAIR principles, because individual stakeholder communities can implement their own FAIR solutions. However, it has also resulted in inconsistent interpretations that carry the risk of leading to incompatible implementations. Thus, while the FAIR principles are formulated on a high level and may be interpreted and implemented in different ways, for true interoperability we need to support convergence in implementation choices that are widely accessible and (re)-usable. We introduce the concept of FAIR implementation considerations to assist accelerated global participation and convergence towards accessible, robust, widespread and consistent FAIR implementations. Any self-identified stakeholder community may either choose to reuse solutions from existing implementations, or when they spot a gap, accept the challenge to create the needed solution, which, ideally, can be used again by other communities in the future. Here, we provide interpretations and implementation considerations (choices and challenges) for each FAIR principle.},
 bibtype = {article},
 author = {Jacobsen, Annika and de Miranda Azevedo, Ricardo and Juty, Nick and Batista, Dominique and Coles, Simon and Cornet, Ronald and Courtot, Mélanie and Crosas, Mercè and Dumontier, Michel and Evelo, Chris T. and Goble, Carole and Guizzardi, Giancarlo and Hansen, Karsten Kryger and Hasnain, Ali and Hettne, Kristina and Heringa, Jaap and Hooft, Rob W.W. and Imming, Melanie and Jeffery, Keith G. and Kaliyaperumal, Rajaram and Kersloot, Martijn G. and Kirkpatrick, Christine R. and Kuhn, Tobias and Labastida, Ignasi and Magagna, Barbara and McQuilton, Peter and Meyers, Natalie and Montesanti, Annalisa and van Reisen, Mirjam and Rocca-Serra, Philippe and Pergl, Robert and Sansone, Susanna-Assunta and da Silva Santos, Luiz Olavo Bonino and Schneider, Juliane and Strawn, George and Thompson, Mark and Waagmeester, Andra and Weigel, Tobias and Wilkinson, Mark D. and Willighagen, Egon L. and Wittenburg, Peter and Roos, Marco and Mons, Barend and Schultes, Erik},
 doi = {10.1162/dint_r_00024},
 journal = {Data Intelligence},
 number = {1-2}
}

The FAIR principles have been widely cited, endorsed and adopted by a broad range of stakeholders since their publication in 2016. By intention, the 15 FAIR guiding principles do not dictate specific technological implementations, but provide guidance for improving Findability, Accessibility, Interoperability and Reusability of digital resources. This has likely contributed to the broad adoption of the FAIR principles, because individual stakeholder communities can implement their own FAIR solutions. However, it has also resulted in inconsistent interpretations that carry the risk of leading to incompatible implementations. Thus, while the FAIR principles are formulated on a high level and may be interpreted and implemented in different ways, for true interoperability we need to support convergence in implementation choices that are widely accessible and (re)-usable. We introduce the concept of FAIR implementation considerations to assist accelerated global participation and convergence towards accessible, robust, widespread and consistent FAIR implementations. Any self-identified stakeholder community may either choose to reuse solutions from existing implementations, or when they spot a gap, accept the challenge to create the needed solution, which, ideally, can be used again by other communities in the future. Here, we provide interpretations and implementation considerations (choices and challenges) for each FAIR principle.

@article{
 title = {Dynamic simulations of microbial communities under perturbations: opportunities for microbiome engineering},
 type = {article},
 year = {2020},
 websites = {https://www.researchsquare.com/article/rs-14990/v1},
 id = {850be0cc-e34c-37d9-be56-0322bfdc90f0},
 created = {2020-11-25T09:30:01.860Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2022-01-06T10:25:47.398Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Garcia-Jimenez2020a},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {García-Jiménez, Beatriz and Carrasco, Jorge and Medina, Joaquín and Wilkinson, Mark D},
 doi = {10.21203/rs.2.24431/v1},
 journal = {Research Square Preprints}
}

@article{
 title = {Perturbations of the AMI1 IAM-amidohydrolase expression trigger plant stress responses in Arabidopsis thaliana},
 type = {article},
 year = {2020},
 websites = {https://doi.org/10.1101%2F2020.08.31.275206},
 month = {8},
 publisher = {Cold Spring Harbor Laboratory},
 id = {69a6b313-1dcf-31d9-bb92-5b2d07ad83bc},
 created = {2022-07-14T08:46:28.921Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2022-07-14T08:46:28.921Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {P_rez_Alonso_2020},
 source_type = {article},
 private_publication = {false},
 bibtype = {article},
 author = {Pérez-Alonso, Marta Marina and Ortiz-Gárcia, Paloma and Moya-Cuevas, José and Lehmann, Thomas and Sanchez-Parra, Beatriz and Björk, Robert G and Karim, Sazzad and Amirjani, Mohammad R and Aronsson, Henrik and Wilkinson, Mark D and Pollmann, Stephan},
 doi = {10.1101/2020.08.31.275206}
}

@article{
 title = {Robust and automatic definition of microbiome states},
 type = {article},
 year = {2019},
 pages = {e6657},
 volume = {7},
 websites = {https://peerj.com/articles/6657},
 month = {3},
 day = {26},
 id = {1b9224c1-99b1-3935-96f6-2b7cb5e00505},
 created = {2019-04-24T09:53:40.994Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2020-07-10T11:55:07.004Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Garcia-Jimenez2019},
 private_publication = {false},
 abstract = {Analysis of microbiome dynamics would allow elucidation of patterns within microbial community evolution under a variety of biologically or economically important circumstances; however, this is currently hampered in part by the lack of rigorous, formal, yet generally-applicable approaches to discerning distinct configurations of complex microbial populations. Clustering approaches to define microbiome “community state-types” at a population-scale are widely used, though not yet standardized. Similarly, distinct variations within a state-type are well documented, but there is no rigorous approach to discriminating these more subtle variations in community structure. Finally, intra-individual variations with even fewer differences will likely be found in, for example, longitudinal data, and will correlate with important features such as sickness versus health. We propose an automated, generic, objective, domain-independent, and internally-validating procedure to define statistically distinct microbiome states within datasets containing any degree of phylotypic diversity. Robustness of state identification is objectively established by a combination of diverse techniques for stable cluster verification. To demonstrate the efficacy of our approach in detecting discreet states even in datasets containing highly similar bacterial communities, and to demonstrate the broad applicability of our method, we reuse eight distinct longitudinal microbiome datasets from a variety of ecological niches and species. We also demonstrate our algorithm’s flexibility by providing it distinct taxa subsets as clustering input, demonstrating that it operates on filtered or unfiltered data, and at a range of different taxonomic levels. The final output is a set of robustly defined states which can then be used as general biomarkers for a wide variety of downstream purposes such as association with disease, monitoring response to intervention, or identifying optimally performant populations.},
 bibtype = {article},
 author = {García-Jiménez, Beatriz and Wilkinson, Mark D.},
 doi = {10.7717/peerj.6657},
 journal = {PeerJ}
}

Analysis of microbiome dynamics would allow elucidation of patterns within microbial community evolution under a variety of biologically or economically important circumstances; however, this is currently hampered in part by the lack of rigorous, formal, yet generally-applicable approaches to discerning distinct configurations of complex microbial populations. Clustering approaches to define microbiome “community state-types” at a population-scale are widely used, though not yet standardized. Similarly, distinct variations within a state-type are well documented, but there is no rigorous approach to discriminating these more subtle variations in community structure. Finally, intra-individual variations with even fewer differences will likely be found in, for example, longitudinal data, and will correlate with important features such as sickness versus health. We propose an automated, generic, objective, domain-independent, and internally-validating procedure to define statistically distinct microbiome states within datasets containing any degree of phylotypic diversity. Robustness of state identification is objectively established by a combination of diverse techniques for stable cluster verification. To demonstrate the efficacy of our approach in detecting discreet states even in datasets containing highly similar bacterial communities, and to demonstrate the broad applicability of our method, we reuse eight distinct longitudinal microbiome datasets from a variety of ecological niches and species. We also demonstrate our algorithm’s flexibility by providing it distinct taxa subsets as clustering input, demonstrating that it operates on filtered or unfiltered data, and at a range of different taxonomic levels. The final output is a set of robustly defined states which can then be used as general biomarkers for a wide variety of downstream purposes such as association with disease, monitoring response to intervention, or identifying optimally performant populations.

@article{
 title = {Data-driven classification of the certainty of scholarly assertions},
 type = {article},
 year = {2019},
 keywords = {FAIR Data,certainty,machine learning,scholarly communication,text mining},
 pages = {e27829v1},
 volume = {7},
 websites = {https://doi.org/10.7287/peerj.preprints.27829v1},
 month = {6},
 id = {07a29268-eafb-3f6f-9d3e-e7e1fec54ea2},
 created = {2019-09-06T09:36:15.315Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2019-09-06T09:36:15.315Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {10.7287/peerj.preprints.27829v1},
 source_type = {article},
 private_publication = {false},
 abstract = {
The grammatical structures scholars use to express their assertions are intended to convey various degrees of certainty or speculation. Prior studies have suggested a variety of categorization systems for scholarly certainty. However, these have not been objectively tested for their validity, particularly with respect to representing the interpretation by the reader, rather than the intention of the author. In this study, we use a series of questionnaires to determine how researchers classify various scholarly assertions, using three distinct certainty classification systems. We find that there are three categories of certainty perceived by readers: one level of high certainty, and two levels of lower certainty that are somewhat less distinct, but nevertheless show a significant degree of inter-annotator agreement. We show that these categories can be detected in an automated manner, using a machine learning model, with a cross-validation accuracy of 89.2% relative to an author-annotated corpus, and 82.2% accuracy against a publicly-annotated corpus. This finding provides an opportunity for contextual metadata related to certainty to be captured as a part of text-mining pipelines, which currently miss these subtle linguistic cues. We provide an exemplar machine-accessible representation - a Nanopublication - where certainty category is embedded as metadata in a formal, ontology-based manner within text-mined scholarly assertions.
},
 bibtype = {article},
 author = {Prieto, Mario and Deus, Helena and De Waard, Anita and Schultes, Erik and García-Jiménez, Beatriz and Wilkinson, Mark D},
 doi = {10.7287/peerj.preprints.27829v1},
 journal = {PeerJ Preprints}
}

The grammatical structures scholars use to express their assertions are intended to convey various degrees of certainty or speculation. Prior studies have suggested a variety of categorization systems for scholarly certainty. However, these have not been objectively tested for their validity, particularly with respect to representing the interpretation by the reader, rather than the intention of the author. In this study, we use a series of questionnaires to determine how researchers classify various scholarly assertions, using three distinct certainty classification systems. We find that there are three categories of certainty perceived by readers: one level of high certainty, and two levels of lower certainty that are somewhat less distinct, but nevertheless show a significant degree of inter-annotator agreement. We show that these categories can be detected in an automated manner, using a machine learning model, with a cross-validation accuracy of 89.2% relative to an author-annotated corpus, and 82.2% accuracy against a publicly-annotated corpus. This finding provides an opportunity for contextual metadata related to certainty to be captured as a part of text-mining pipelines, which currently miss these subtle linguistic cues. We provide an exemplar machine-accessible representation - a Nanopublication - where certainty category is embedded as metadata in a formal, ontology-based manner within text-mined scholarly assertions.

@article{
 title = {The FAIR Funder pilot programme to make it easy for funders to require and for grantees to produce FAIR Data},
 type = {article},
 year = {2019},
 volume = {arXiv:1902},
 websites = {http://arxiv.org/abs/1902.11162},
 month = {2},
 day = {26},
 id = {f39a4f13-5b8c-3244-bf01-a974ea4ad345},
 created = {2019-09-06T09:36:15.367Z},
 accessed = {2019-03-01},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2020-07-10T11:55:06.930Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wittenburg2019},
 private_publication = {false},
 abstract = {There is a growing acknowledgement in the scientific community of the importance of making experimental data machine findable, accessible, interoperable, and reusable (FAIR). Recognizing that high quality metadata are essential to make datasets FAIR, members of the GO FAIR Initiative and the Research Data Alliance (RDA) have initiated a series of workshops to encourage the creation of Metadata for Machines (M4M), enabling any self-identified stakeholder to define and promote the reuse of standardized, comprehensive machine-actionable metadata. The funders of scientific research recognize that they have an important role to play in ensuring that experimental results are FAIR, and that high quality metadata and careful planning for FAIR data stewardship are central to these goals. We describe the outcome of a recent M4M workshop that has led to a pilot programme involving two national science funders, the Health Research Board of Ireland (HRB) and the Netherlands Organisation for Health Research and Development (ZonMW). These funding organizations will explore new technologies to define at the time that a request for proposals is issued the minimal set of machine-actionable metadata that they would like investigators to use to annotate their datasets, to enable investigators to create such metadata to help make their data FAIR, and to develop data-stewardship plans that ensure that experimental data will be managed appropriately abiding by the FAIR principles. The FAIR Funders design envisions a data-management workflow having seven essential stages, where solution providers are openly invited to participate. The initial pilot programme will launch using existing computer-based tools of those who attended the M4M Workshop.},
 bibtype = {article},
 author = {Wittenburg, P. and Sustkova, H. Pergl and Montesanti, A. and Bloemers, S. M. and de Waard, S. H. and Musen, M. A. and Graybeal, J. B. and Hettne, K. M. and Jacobsen, A. and Pergl, R. and Hooft, R. W. W. and Staiger, C. and van Gelder, C. W. G. and Knijnenburg, S. L. and van Arkel, A. C. and Meerman, B. and Wilkinson, M. D. and Sansone, S-A and Rocca-Serra, P. and McQuilton, P. and Gonzalez-Beltran, A. N. and Aben, G. J. C. and Henning, P. and Alencar, S. and Ribeiro, C. and Silva, C. R. L. and Sayao, L. and Sales, L. and Veiga, V. and Lima, J. and Dib, S. and Xavier, P. and Murtinho, R. and Tendel, J. and Schaap, B. F. and Brouwer, P. M. and Gavai, A. K. and Bouzembrak, Y. and Marvin, H. J. P. and Mons, A. and Kuhn, T. and Gambardella, A. A. and Azevedo, R. de Miranda and Muhonen, V. and van der Naald, M. and Smit, N. W. and Buys, M. J. and de Bruin, T. F. and Schoots, F. and Goodson, H. J. E. and Rzepa, H. S. and Jeffery, K. G. and Shanahan, H. P. and Axton, M. and Tkachenko, V. and Maya, A. D. and Meyers, N. K. and Conlon, M. and Haak, L. L. and Schultes, E. A.},
 journal = {arXiv}
}

There is a growing acknowledgement in the scientific community of the importance of making experimental data machine findable, accessible, interoperable, and reusable (FAIR). Recognizing that high quality metadata are essential to make datasets FAIR, members of the GO FAIR Initiative and the Research Data Alliance (RDA) have initiated a series of workshops to encourage the creation of Metadata for Machines (M4M), enabling any self-identified stakeholder to define and promote the reuse of standardized, comprehensive machine-actionable metadata. The funders of scientific research recognize that they have an important role to play in ensuring that experimental results are FAIR, and that high quality metadata and careful planning for FAIR data stewardship are central to these goals. We describe the outcome of a recent M4M workshop that has led to a pilot programme involving two national science funders, the Health Research Board of Ireland (HRB) and the Netherlands Organisation for Health Research and Development (ZonMW). These funding organizations will explore new technologies to define at the time that a request for proposals is issued the minimal set of machine-actionable metadata that they would like investigators to use to annotate their datasets, to enable investigators to create such metadata to help make their data FAIR, and to develop data-stewardship plans that ensure that experimental data will be managed appropriately abiding by the FAIR principles. The FAIR Funders design envisions a data-management workflow having seven essential stages, where solution providers are openly invited to participate. The initial pilot programme will launch using existing computer-based tools of those who attended the M4M Workshop.

@article{
 title = {Evaluating FAIR Maturity Through a Scalable, Automated, Community-Governed Framework},
 type = {article},
 year = {2019},
 websites = {https://www.biorxiv.org/content/early/2019/05/28/649202},
 publisher = {Cold Spring Harbor Laboratory},
 id = {eb8c11c4-3bc8-3dcc-ac4d-fbf3fcf87f10},
 created = {2019-09-06T09:36:15.372Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2019-09-06T09:36:15.372Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wilkinson649202},
 source_type = {article},
 private_publication = {false},
 abstract = {Transparent evaluations of FAIRness are increasingly required by a wide range of stakeholders, from scientists to publishers, funding agencies and policy makers. We propose a scalable, automatable framework to evaluate digital resources that encompasses measurable indicators, open source tools, and participation guidelines, which come together to accommodate domain relevant community-defined FAIR assessments. The components of the framework are: (1) Maturity Indicators - community-authored specifications that delimit a specific automatically-measurable FAIR behavior; (2) Compliance Tests - small Web apps that test digital resources against individual Maturity Indicators; and (3) the Evaluator, a Web application that registers, assembles, and applies community-relevant sets of Compliance Tests against a digital resource, and provides a detailed report about what a machine \textquotedblleftsees\textquotedblright when it visits that resource. We discuss the technical and social considerations of FAIR assessments, and how this translates to our community-driven infrastructure. We then illustrate how the output of the Evaluator tool can serve as a roadmap to assist data stewards to incrementally and realistically improve the FAIRness of their resources.},
 bibtype = {article},
 author = {Wilkinson, Mark D and Dumontier, Michel and Sansone, Susanna-Assunta and da Silva Santos, Luiz Olavo Bonino and Prieto, Mario and Batista, Dominique and McQuilton, Peter and Kuhn, Tobias and Rocca-Serra, Philippe and Crosas, Mercè and Schultes, Erik},
 doi = {10.1101/649202},
 journal = {bioRxiv}
}

Transparent evaluations of FAIRness are increasingly required by a wide range of stakeholders, from scientists to publishers, funding agencies and policy makers. We propose a scalable, automatable framework to evaluate digital resources that encompasses measurable indicators, open source tools, and participation guidelines, which come together to accommodate domain relevant community-defined FAIR assessments. The components of the framework are: (1) Maturity Indicators - community-authored specifications that delimit a specific automatically-measurable FAIR behavior; (2) Compliance Tests - small Web apps that test digital resources against individual Maturity Indicators; and (3) the Evaluator, a Web application that registers, assembles, and applies community-relevant sets of Compliance Tests against a digital resource, and provides a detailed report about what a machine \textquotedblleftsees\textquotedblright when it visits that resource. We discuss the technical and social considerations of FAIR assessments, and how this translates to our community-driven infrastructure. We then illustrate how the output of the Evaluator tool can serve as a roadmap to assist data stewards to incrementally and realistically improve the FAIRness of their resources.

@article{
 title = {Evaluating FAIR maturity through a scalable, automated, community-governed framework},
 type = {article},
 year = {2019},
 pages = {174},
 volume = {6},
 websites = {http://www.nature.com/articles/s41597-019-0184-5},
 month = {12},
 day = {20},
 id = {82fd6792-a170-36f2-a24b-681cb4b0030c},
 created = {2019-09-24T07:01:57.136Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2020-07-10T11:55:06.850Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wilkinson2019},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Wilkinson, Mark D. and Dumontier, Michel and Sansone, Susanna-Assunta and Bonino da Silva Santos, Luiz Olavo and Prieto, Mario and Batista, Dominique and McQuilton, Peter and Kuhn, Tobias and Rocca-Serra, Philippe and Crosas, Mercѐ and Schultes, Erik},
 doi = {10.1038/s41597-019-0184-5},
 journal = {Scientific Data},
 number = {1}
}

@article{
 title = {BioHackathon series in 2013 and 2014: improvements of semantic interoperability in life science data and services},
 type = {article},
 year = {2019},
 pages = {1677},
 volume = {8},
 websites = {https://f1000research.com/articles/8-1677/v1},
 month = {9},
 day = {23},
 id = {9671f940-ee07-31d4-9f88-f1f5f588e123},
 created = {2019-09-24T07:01:57.153Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2019-09-24T07:01:58.345Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {Publishing databases in the Resource Description Framework (RDF) model is becoming widely accepted to maximize the syntactic and semantic interoperability of open data in life sciences. Here we report advancements made in the 6th and 7th annual BioHackathons which were held in Tokyo and Miyagi respectively. This review consists of two major sections covering: 1) improvement and utilization of RDF data in various domains of the life sciences and 2) meta-data about these RDF data, the resources that store them, and the service quality of SPARQL Protocol and RDF Query Language (SPARQL) endpoints. The first section describes how we developed RDF data, ontologies and tools in genomics, proteomics, metabolomics, glycomics and by literature text mining. The second section describes how we defined descriptions of datasets, the provenance of data, and quality assessment of services and service discovery. By enhancing the harmonization of these two layers of machine-readable data and knowledge, we improve the way community wide resources are developed and published. Moreover, we outline best practices for the future, and prepare ourselves for an exciting and unanticipatable variety of real world applications in coming years.},
 bibtype = {article},
 author = {Katayama, Toshiaki and Kawashima, Shuichi and Micklem, Gos and Kawano, Shin and Kim, Jin-Dong and Kocbek, Simon and Okamoto, Shinobu and Wang, Yue and Wu, Hongyan and Yamaguchi, Atsuko and Yamamoto, Yasunori and Antezana, Erick and Aoki-Kinoshita, Kiyoko F. and Arakawa, Kazuharu and Banno, Masaki and Baran, Joachim and Bolleman, Jerven T. and Bonnal, Raoul J.P. and Bono, Hidemasa and Fernández-Breis, Jesualdo T. and Buels, Robert and Campbell, Matthew P. and Chiba, Hirokazu and Cock, Peter J. A. and Cohen, Kevin B. and Dumontier, Michel and Fujisawa, Takatomo and Fujiwara, Toyofumi and Garcia, Leyla and Gaudet, Pascale and Hattori, Emi and Hoehndorf, Robert and Itaya, Kotone and Ito, Maori and Jamieson, Daniel and Jupp, Simon and Juty, Nick and Kalderimis, Alex and Kato, Fumihiro and Kawaji, Hideya and Kawashima, Takeshi and Kinjo, Akira R. and Komiyama, Yusuke and Kotera, Masaaki and Kushida, Tatsuya and Malone, James and Matsubara, Masaaki and Mizuno, Satoshi and Mizutani, Sayaka and Mori, Hiroshi and Moriya, Yuki and Murakami, Katsuhiko and Nakazato, Takeru and Nishide, Hiroyo and Nishimura, Yosuke and Ogishima, Soichi and Ohta, Tazro and Okuda, Shujiro and Ono, Hiromasa and Perez-Riverol, Yasset and Shinmachi, Daisuke and Splendiani, Andrea and Strozzi, Francesco and Suzuki, Shinya and Takehara, Junichi and Thompson, Mark and Tokimatsu, Toshiaki and Uchiyama, Ikuo and Verspoor, Karin and Wilkinson, Mark D. and Wimalaratne, Sarala and Yamada, Issaku and Yamamoto, Nozomi and Yarimizu, Masayuki and Kawamoto, Shoko and Takagi, Toshihisa},
 doi = {10.12688/f1000research.18238.1},
 journal = {F1000Research}
}

Publishing databases in the Resource Description Framework (RDF) model is becoming widely accepted to maximize the syntactic and semantic interoperability of open data in life sciences. Here we report advancements made in the 6th and 7th annual BioHackathons which were held in Tokyo and Miyagi respectively. This review consists of two major sections covering: 1) improvement and utilization of RDF data in various domains of the life sciences and 2) meta-data about these RDF data, the resources that store them, and the service quality of SPARQL Protocol and RDF Query Language (SPARQL) endpoints. The first section describes how we developed RDF data, ontologies and tools in genomics, proteomics, metabolomics, glycomics and by literature text mining. The second section describes how we defined descriptions of datasets, the provenance of data, and quality assessment of services and service discovery. By enhancing the harmonization of these two layers of machine-readable data and knowledge, we improve the way community wide resources are developed and published. Moreover, we outline best practices for the future, and prepare ourselves for an exciting and unanticipatable variety of real world applications in coming years.

@article{
 title = {Genome-wide analysis of the H3K27me3 epigenome and transcriptome in Brassica rapa},
 type = {article},
 year = {2019},
 volume = {8},
 websites = {https://doi.org/10.1093/gigascience/giz147,https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giz147/5652252},
 month = {12},
 day = {1},
 id = {ec5a6ab6-8387-313f-9991-ac1bbbedb081},
 created = {2019-12-11T07:07:49.276Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2020-02-03T07:06:34.461Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {10.1093/gigascience/giz147},
 source_type = {article},
 notes = {giz147},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {Genome-wide maps of histone modifications have been obtained for several plant species. However, most studies focus on model systems and do not enforce FAIR data management principles. Here we study the H3K27me3 epigenome and associated transcriptome of Brassica rapa, an important vegetable cultivated worldwide.We performed H3K27me3 chromatin immunoprecipitation followed by high-throughput sequencing and transcriptomic analysis by 3′-end RNA sequencing from B. rapa leaves and inflorescences. To analyze these data we developed a Reproducible Epigenomic Analysis pipeline using Galaxy and Jupyter, packaged into Docker images to facilitate transparency and reuse. We found that H3K27me3 covers roughly one-third of all B. rapa protein-coding genes and its presence correlates with low transcript levels. The comparative analysis between leaves and inflorescences suggested that the expression of various floral regulatory genes during development depends on H3K27me3. To demonstrate the importance of H3K27me3 for B. rapa development, we characterized a mutant line deficient in the H3K27 methyltransferase activity. We found that braA.clf mutant plants presented pleiotropic alterations, e.g., curly leaves due to increased expression and reduced H3K27me3 levels at AGAMOUS-like loci.We characterized the epigenetic mark H3K27me3 at genome-wide levels and provide genetic evidence for its relevance in B. rapa development. Our work reveals the epigenomic landscape of H3K27me3 in B. rapa and provides novel genomics datasets and bioinformatics analytical resources. We anticipate that this work will lead the way to further epigenomic studies in the complex genome of Brassica crops.},
 bibtype = {article},
 author = {Payá-Milans, Miriam and Poza-Viejo, Laura and Martín-Uriz, Patxi San and Lara-Astiaso, David and Wilkinson, Mark D and Crevillén, Pedro},
 doi = {10.1093/gigascience/giz147},
 journal = {GigaScience},
 number = {12}
}

Genome-wide maps of histone modifications have been obtained for several plant species. However, most studies focus on model systems and do not enforce FAIR data management principles. Here we study the H3K27me3 epigenome and associated transcriptome of Brassica rapa, an important vegetable cultivated worldwide.We performed H3K27me3 chromatin immunoprecipitation followed by high-throughput sequencing and transcriptomic analysis by 3′-end RNA sequencing from B. rapa leaves and inflorescences. To analyze these data we developed a Reproducible Epigenomic Analysis pipeline using Galaxy and Jupyter, packaged into Docker images to facilitate transparency and reuse. We found that H3K27me3 covers roughly one-third of all B. rapa protein-coding genes and its presence correlates with low transcript levels. The comparative analysis between leaves and inflorescences suggested that the expression of various floral regulatory genes during development depends on H3K27me3. To demonstrate the importance of H3K27me3 for B. rapa development, we characterized a mutant line deficient in the H3K27 methyltransferase activity. We found that braA.clf mutant plants presented pleiotropic alterations, e.g., curly leaves due to increased expression and reduced H3K27me3 levels at AGAMOUS-like loci.We characterized the epigenetic mark H3K27me3 at genome-wide levels and provide genetic evidence for its relevance in B. rapa development. Our work reveals the epigenomic landscape of H3K27me3 in B. rapa and provides novel genomics datasets and bioinformatics analytical resources. We anticipate that this work will lead the way to further epigenomic studies in the complex genome of Brassica crops.

@article{
 title = {Conserved Roles of the H3K27ME3 Epigenome on Plant Development},
 type = {article},
 year = {2019},
 pages = {28},
 websites = {http://www.sebiology.org/docs/default-source/event-documents/seb_nucleus-impact_satellite-programme_nov19-digital.pdf},
 publisher = {The Society for Experimental Biology},
 city = {Madrid, 9-11 DECEMBER, 2019},
 id = {5605f7fd-24d3-3a23-af75-c34d6865aece},
 created = {2019-12-11T09:00:00.443Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2020-12-01T10:10:41.952Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Crevillen2019},
 private_publication = {false},
 abstract = {The study of the epigenome and its relation with the underlying genome sequence has become a central question in Biology nowadays. Genome-wide maps of histone modifications have been obtained for several plant species. However, most studies focus on model systems and do not enforce FAIR data management principles. We have developed a Reproducible Epigenomics Analysis (REA) pipeline combining a Galaxy environment for data analysis and Jupyter notebooks for results visualization composed into Docker. We successfully applied this REA pipeline to study of the H3K27m3 epigenome on leaves and flowers of plant model (Arabidopsis thaliana) and crop (Brassica rapa) species. The comparative analysis between leaves and inflorescences genomic datasets suggested that the expression of various floral regulatory genes during development is controlled by H3K27 methylation. H3K27me3 is a repressive epigenetic mark set by Polycomb protein complexes and counteracted by the histone demethylase activity of specific Jumonji domain proteins. We are also studying the role of these epigenetic factors in A. thaliana and B. rapa. Mutant analyses have shown that these epigenetic factors regulate a wide range of developmental responses including flowering time. The similarities and differences between model and crop systems on the role of H3K27me},
 bibtype = {article},
 author = {Crevillén, Pedro and Poza-Viejo, Laura and Payá-Milans, Miriam and Del Olmo, IVÁN and Wilkinson​, Mark D},
 journal = {IMPACT OF CHROMATIN DOMAINS ON PLANT PHENOTYPES}
}

The study of the epigenome and its relation with the underlying genome sequence has become a central question in Biology nowadays. Genome-wide maps of histone modifications have been obtained for several plant species. However, most studies focus on model systems and do not enforce FAIR data management principles. We have developed a Reproducible Epigenomics Analysis (REA) pipeline combining a Galaxy environment for data analysis and Jupyter notebooks for results visualization composed into Docker. We successfully applied this REA pipeline to study of the H3K27m3 epigenome on leaves and flowers of plant model (Arabidopsis thaliana) and crop (Brassica rapa) species. The comparative analysis between leaves and inflorescences genomic datasets suggested that the expression of various floral regulatory genes during development is controlled by H3K27 methylation. H3K27me3 is a repressive epigenetic mark set by Polycomb protein complexes and counteracted by the histone demethylase activity of specific Jumonji domain proteins. We are also studying the role of these epigenetic factors in A. thaliana and B. rapa. Mutant analyses have shown that these epigenetic factors regulate a wide range of developmental responses including flowering time. The similarities and differences between model and crop systems on the role of H3K27me

@article{
 title = {Erratum: Addendum: The FAIR Guiding Principles for scientific data management and stewardship (Scientific data (2016) 3 (160018))},
 type = {article},
 year = {2019},
 volume = {6},
 id = {2aeacd52-ca87-3b7d-810d-ddaed2736630},
 created = {2019-04-01T23:59:00.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2021-02-05T08:40:11.317Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 bibtype = {article},
 author = {Wilkinson, M.D. and Dumontier, M. and Jan Aalbersberg, I. and Appleton, G. and Axton, M. and Baak, A. and Blomberg, N. and Boiten, J.-W. and da Silva Santos, L.B. and Bourne, P.E. and Bouwman, J. and Brookes, A.J. and Clark, T. and Crosas, M. and Dillo, I. and Dumon, O. and Edmunds, S. and Evelo, C.T. and Finkers, R. and Gonzalez-Beltran, A. and Gray, A.J.G. and Groth, P. and Goble, C. and Grethe, J.S. and Heringa, J. and Hoen, P.A.C.'. and Hooft, R. and Kuhn, T. and Kok, R. and Kok, J. and Lusher, S.J. and Martone, M.E. and Mons, A. and Packer, A.L. and Persson, B. and Rocca-Serra, P. and Roos, M. and van Schaik, R. and Sansone, S.-A. and Schultes, E. and Sengstag, T. and Slater, T. and Strawn, G. and Swertz, M.A. and Thompson, M. and van der Lei, J. and van Mulligen, E. and Jan Velterop, undefined and Waagmeester, A. and Wittenburg, P. and Wolstencroft, K. and Zhao, J. and Mons, B.},
 doi = {10.1038/s41597-019-0009-6},
 journal = {Scientific data},
 number = {1}
}

@article{
 title = {Author Correction: Evaluating FAIR maturity through a scalable, automated, community-governed framework (Scientific Data, (2019), 6, 1, (174), 10.1038/s41597-019-0184-5)},
 type = {article},
 year = {2019},
 volume = {6},
 id = {45031bc9-d260-31ff-95c0-63730ccf2c36},
 created = {2019-10-26T23:59:00.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2021-02-05T08:40:11.211Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {The affiliation of Mark Wilkinson and Mario Prieto was incompletely stated in the original publication. It is: Centro de Biotecnología y Genómica de Plantas, Universidad Politécnica de Madrid (UPM) – Instituto Nacional de Investigación y Tecnología Agraria y Alimentaria (INIA), Departamento de Biotecnología-Biología Vegetal, Escuela Técnica Superior de Ingeniería Agronómica, Alimentaria y de Biosistemas, Universidad Politécnica de Madrid (UPM), Madrid, Spain This has now been corrected in the HTML and PDF versions.},
 bibtype = {article},
 author = {Wilkinson, Mark D. and Dumontier, Michel and Sansone, Susanna Assunta and Bonino da Silva Santos, Luiz Olavo and Prieto, Mario and Batista, Dominique and McQuilton, Peter and Kuhn, Tobias and Rocca-Serra, Philippe and Crosas, Mercѐ and Schultes, Erik},
 doi = {10.1038/s41597-019-0248-6},
 journal = {Scientific Data},
 number = {1}
}

The affiliation of Mark Wilkinson and Mario Prieto was incompletely stated in the original publication. It is: Centro de Biotecnología y Genómica de Plantas, Universidad Politécnica de Madrid (UPM) – Instituto Nacional de Investigación y Tecnología Agraria y Alimentaria (INIA), Departamento de Biotecnología-Biología Vegetal, Escuela Técnica Superior de Ingeniería Agronómica, Alimentaria y de Biosistemas, Universidad Politécnica de Madrid (UPM), Madrid, Spain This has now been corrected in the HTML and PDF versions.

@inproceedings{
 title = {Enrichment of rare disease patient registries by FAIRification},
 type = {inproceedings},
 year = {2018},
 pages = {POSTER},
 id = {2a9d7868-3741-3e08-aa7c-f485ea8b4f5b},
 created = {2018-02-20T07:14:26.635Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-09-02T13:34:04.956Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Jacobsen2018a},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Jacobsen, Annika and Thompson, Mark and Schultes, Erik A. and Cornet, Ronald and Wilkinson, Mark and Thompson, Rachel and Mordenti, Marina and Sangiorgi, Luca and Carta, Claudio and Groenen, Karlijn and Kersloot, Martijn and Schultze Kool, Leo and van Enckevort, David and Roos, Marco},
 booktitle = {ECRD 2018}
}

@inproceedings{
 title = {FAIRification of rare disease patient registries},
 type = {inproceedings},
 year = {2018},
 city = {Athens, Greece, April 16-18, 2018},
 id = {6af3091c-3a48-3f7a-babf-8f91a3ab5247},
 created = {2018-02-28T10:26:39.701Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-09-02T13:34:05.267Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Jacobsen2018},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Jacobsen, Annika and Thompson, Mark and Sernadela, Pedro and Ehrhart, Friederike and Carta, Claudio and Groenen, Karlijn and Kersloot, Martijn and Kool, Leo Schultze and Mordenti, Marina and Locatelli, Manuela and Sangiorgi, Luca and Schultes, Erik A. and Cornet, Ronald and Wilkinson, Mark D and Taruscio, Domenica and Thompson, Rachel and van Enckevort, David and Evelo, Chris and Roos, Marco},
 booktitle = {Proceedings of the 2018 Annual Partner Meeting of RD Connect}
}

@article{
 title = {A design framework and exemplar metrics for FAIRness},
 type = {article},
 year = {2018},
 pages = {180118},
 volume = {5},
 websites = {http://www.nature.com/articles/sdata2018118},
 month = {6},
 day = {26},
 id = {602e5f7e-f081-3302-bb0f-63df7bf45258},
 created = {2018-07-06T08:42:56.294Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-09-02T13:34:04.930Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wilkinson2018},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Wilkinson, Mark D. and Sansone, Susanna-Assunta and Schultes, Erik and Doorn, Peter and Bonino da Silva Santos, Luiz Olavo and Dumontier, Michel},
 doi = {10.1038/sdata.2018.118},
 journal = {Scientific Data}
}

@article{
 title = {MECP2 variation in Rett syndrome-An overview of current coverage of genetic and phenotype data within existing databases},
 type = {article},
 year = {2018},
 pages = {914-924},
 volume = {39},
 websites = {http://doi.wiley.com/10.1002/humu.23542},
 month = {7},
 id = {cd1896c8-4bea-3388-8ba4-afaf63f4d67a},
 created = {2018-09-02T13:34:04.300Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-10-15T08:36:22.870Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Townend2018},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Townend, Gillian S. and Ehrhart, Friederike and van Kranen, Henk J. and Wilkinson, Mark and Jacobsen, Annika and Roos, Marco and Willighagen, Egon L. and van Enckevort, David and Evelo, Chris T. and Curfs, Leopold M. G.},
 doi = {10.1002/humu.23542},
 journal = {Human Mutation},
 number = {7}
}

@article{
 title = {Virulence- and signaling-associated genes display a preference for long 3′UTRs during rice infection and metabolic stress in the rice blast fungus},
 type = {article},
 year = {2018},
 websites = {http://doi.wiley.com/10.1111/nph.15405},
 month = {8},
 day = {31},
 id = {e3f93b5b-0542-34e3-83d4-6940cf7410b5},
 created = {2018-09-02T13:34:04.331Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-10-15T08:36:22.855Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Rodriguez-Romero2018},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Rodríguez-Romero, Julio and Marconi, Marco and Ortega-Campayo, Víctor and Demuez, Marie and Wilkinson, Mark D. and Sesma, Ane},
 doi = {10.1111/nph.15405},
 journal = {New Phytologist}
}

@article{
 title = {MDPbiome: microbiome engineering through prescriptive perturbations},
 type = {article},
 year = {2018},
 pages = {i838-i847},
 volume = {34},
 websites = {https://academic.oup.com/bioinformatics/article/34/17/i838/5093255},
 month = {9},
 day = {1},
 id = {52d411e0-1b84-376c-ad16-ddc5f1cef03e},
 created = {2018-09-02T13:43:07.616Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-10-15T08:36:22.851Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Garcia-Jimenez2018},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {García-Jiménez, Beatriz and de la Rosa, Tomás and Wilkinson, Mark Denis},
 doi = {10.1093/bioinformatics/bty562},
 journal = {Bioinformatics},
 number = {17}
}

@article{
 title = {Evaluating FAIR-Compliance Through an Objective, Automated, Community-Governed Framework},
 type = {article},
 year = {2018},
 websites = {http://biorxiv.org/content/early/2018/09/16/418376.abstract},
 month = {1},
 day = {1},
 id = {d430a4a2-3a04-3ed8-a33e-da6d5c24699a},
 created = {2018-09-19T09:04:32.869Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-10-15T08:36:22.866Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wilkinson2018},
 source_type = {JOUR},
 private_publication = {false},
 abstract = {With the increased adoption of the FAIR Principles, a wide range of stakeholders, from scientists to publishers, funding agencies and policy makers, are seeking ways to transparently evaluate resource FAIRness. We describe the FAIR Evaluator, a software infrastructure to register and execute tests of compliance with the recently published FAIR Metrics. The Evaluator enables digital resources to be assessed objectively and transparently. We illustrate its application to three widely used generalist repositories - Dataverse, Dryad, and Zenodo - and report their feedback. Evaluations allow communities to select relevant Metric subsets to deliver FAIRness measurements in diverse and specialized applications. Evaluations are executed in a semi-automated manner through Web Forms filled-in by a user, or through a JSON-based API. A comparison of manual vs automated evaluation reveals that automated evaluations are generally stricter, resulting in lower, though more accurate, FAIRness scores. Finally, we highlight the need for enhanced infrastructure such as standards registries, like FAIRsharing, as well as additional community involvement in domain-specific data infrastructure creation.},
 bibtype = {article},
 author = {Wilkinson, Mark D and Dumontier, Michel and Sansone, Susanna-Assunta and Bonino da Silva Santos, Luiz Olavo and Prieto, Mario and Gautier, Julian and McQuilton, Peter and Murphy, Derek and Crosas, Merce and Schultes, Erik},
 journal = {bioRxiv}
}

With the increased adoption of the FAIR Principles, a wide range of stakeholders, from scientists to publishers, funding agencies and policy makers, are seeking ways to transparently evaluate resource FAIRness. We describe the FAIR Evaluator, a software infrastructure to register and execute tests of compliance with the recently published FAIR Metrics. The Evaluator enables digital resources to be assessed objectively and transparently. We illustrate its application to three widely used generalist repositories - Dataverse, Dryad, and Zenodo - and report their feedback. Evaluations allow communities to select relevant Metric subsets to deliver FAIRness measurements in diverse and specialized applications. Evaluations are executed in a semi-automated manner through Web Forms filled-in by a user, or through a JSON-based API. A comparison of manual vs automated evaluation reveals that automated evaluations are generally stricter, resulting in lower, though more accurate, FAIRness scores. Finally, we highlight the need for enhanced infrastructure such as standards registries, like FAIRsharing, as well as additional community involvement in domain-specific data infrastructure creation.

@article{
 title = {Genome-wide polyadenylation site mapping datasets in the rice blast fungus Magnaporthe oryzae},
 type = {article},
 year = {2018},
 pages = {180271},
 volume = {5},
 websites = {http://www.nature.com/articles/sdata2018271},
 month = {11},
 day = {27},
 id = {e45f5172-2841-3e2a-a9f0-df5ad2524122},
 created = {2018-10-15T08:36:22.612Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2019-02-27T14:00:31.296Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Marconi2018},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Marconi, Marco and Sesma, Ane and Rodríguez-Romero, Julio Luis and González, María Lourdes Rosano and Wilkinson, Mark D.},
 doi = {10.1038/sdata.2018.271},
 journal = {Scientific Data}
}

@article{
 title = {Automatic definition of robust microbiome sub-states in longitudinal data},
 type = {article},
 year = {2018},
 keywords = {Clustering,Longitudinal dataset,Machine Learning,Metagenomics,Microbiome,Sub-states},
 pages = {e26657v1},
 volume = {6},
 websites = {https://doi.org/10.7287/peerj.preprints.26657v1},
 month = {3},
 id = {8d4d3cd8-ce00-3d2b-ad84-1ea7fa6fc109},
 created = {2018-10-15T08:36:22.612Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-10-15T08:36:22.612Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {10.7287/peerj.preprints.26657v1},
 source_type = {article},
 private_publication = {false},
 abstract = {
The analysis of microbiome dynamics would allow us to elucidate patterns within microbial community evolution; however, microbiome state-transition dynamics have been scarcely studied. This is in part because a necessary first-step in such analyses has not been well-defined: how to deterministically describe a microbiome’s ”state”. Clustering in states have been widely studied, although no standard has been concluded yet. We propose a generic, domain-independent and automatic procedure to determine a reliable set of microbiome sub-states within a specific dataset, and with respect to the conditions of the study. The robustness of sub-state identification is established by the combination of diverse techniques for stable cluster verification. We reuse four distinct longitudinal microbiome datasets to demonstrate the broad applicability of our method, analysing results with different taxa subset allowing to adjust it depending on the application goal, and showing that the methodology provides a set of robust sub-states to examine in downstream studies about dynamics in microbiome.
},
 bibtype = {article},
 author = {García-Jiménez, Beatriz and Wilkinson, Mark D},
 doi = {10.7287/peerj.preprints.26657v1},
 journal = {PeerJ Preprints}
}

The analysis of microbiome dynamics would allow us to elucidate patterns within microbial community evolution; however, microbiome state-transition dynamics have been scarcely studied. This is in part because a necessary first-step in such analyses has not been well-defined: how to deterministically describe a microbiome’s ”state”. Clustering in states have been widely studied, although no standard has been concluded yet. We propose a generic, domain-independent and automatic procedure to determine a reliable set of microbiome sub-states within a specific dataset, and with respect to the conditions of the study. The robustness of sub-state identification is established by the combination of diverse techniques for stable cluster verification. We reuse four distinct longitudinal microbiome datasets to demonstrate the broad applicability of our method, analysing results with different taxa subset allowing to adjust it depending on the application goal, and showing that the methodology provides a set of robust sub-states to examine in downstream studies about dynamics in microbiome.

@article{
 title = {FAIRsharing, a cohesive community approach to the growth in standards, repositories and policies},
 type = {article},
 year = {2018},
 websites = {https://www.biorxiv.org/content/early/2018/09/26/245183},
 publisher = {Cold Spring Harbor Laboratory},
 id = {9bac8942-3ab1-3a6c-942e-dea31770bb4f},
 created = {2018-10-15T12:55:11.513Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-10-15T12:55:12.777Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Sansone245183},
 source_type = {article},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {In this modern, data-driven age, governments, funders and publishers expect greater transparency and reuse of research data, as well as greater access to and preservation of the data that supports research findings. Community-developed standards, such as those for the identification and reporting of data, underpin reproducible and reusable research, aid scholarly publishing, and drive both the discovery and evolution of scientific practice. The number of these standardization efforts, driven by large organizations or at the grass root level, has been on the rise since the early 2000s. Thousands of community-developed standards are available (across all disciplines), many of which have been created and/or implemented by several thousand data repositories. Nevertheless, their uptake by the research community, however, has been slow and uneven. This is mainly because investigators lack incentives to follow and adopt standards. The situation is exacerbated if standards are not promptly implemented by databases, repositories and other research tools, or endorsed by infrastructures. Furthermore, the fragmentation of community efforts results in the development of arbitrarily different, incompatible standards. In turn, this leads to standards becoming rapidly obsolete in fast-evolving research areas. As with any other digital object, standards, databases and repositories are dynamic in nature, with a life cycle that encompasses formulation, development and maintenance; their status in this cycle may vary depending on the level of activity of the developing group or community. There is an urgent need for a service that enhances the information available on the evolving constellation of heterogeneous standards, databases and repositories, guides users in the selection of these resources, and that works with developers and maintainers of these resources to foster collaboration and promote harmonization. Such an informative and educational service is vital to reduce the knowledge gap among those involved in producing, managing, serving, curating, preserving, publishing or regulating data. A diverse set of stakeholders-representing academia, industry, funding agencies, standards organizations, infrastructure providers and scholarly publishers, both national and domain-specific as well global and general organizations, have come together as a community, representing the core adopters, advisory board members, and/or key collaborators of the FAIRsharing resource. Here, we introduce its mission and community network. We present an evaluation of the standards landscape, focusing on those for reporting data and metadata - the most diverse and numerous of the standards - and their implementation by databases and repositories. We report on the ongoing challenge to recommend resources, and we discuss the importance of making standards invisible to the end users. We report on the ongoing challenge to recommend resources, and we discuss the importance of making standards invisible to the end users. We present guidelines that highlight the role each stakeholder group must play to maximize the visibility and adoption of standards, databases and repositories.},
 bibtype = {article},
 author = {Sansone, Susanna-Assunta and McQuilton, Peter and Rocca-Serra, Philippe and Gonzalez-Beltran, Alejandra and Izzo, Massimiliano and Lister, Allyson and Thurston, Milo and Batista, Dominique and Granell, Ramon and Adekale, Melanie and Dauga, Delphine and Ganley, Emma and Hodson, Simon and Lawrence, Rebecca and Khodiyar, Varsha and Tenenbaum, Jessica and Axton, J Myles and Ball, Michael and Besson, Sebastien and Bloom, Theodora and Bonazzi, Vivien and Jimenez, Rafael and Carr, David and Chan, Wei Mun and Chung, Caty and Clement-Stoneham, Geraldine and Cousijn, Helena and Dayalan, Saravanan and Dumontier, Michel and Dzale Yeumo, Esther and Edmunds, Scott and Everitt, Nicholas and Fripp, Dom and Goble, Carole and Golebiewski, Martin and Hall, Neil and Hanisch, Robert and Hucka, Michael and Huerta, Michael and Kenall, Amye and Kiley, Robert and Klenk, Juergen and Koureas, Dimitrios and Larkin, Jennie and Lemberger, Thomas and Lynch, Nick and Schriml, Lynn and Ma\textquoterightayan, Avi and MacCallum, Catriona and Mons, Barend and Moore, Josh and Muller, Wolfgang and Murray, Hollydawn and Nobusada, Tomoe and Noesgaard, Daniel and Paxton-Boyd, Jennifer and Orchard, Sandra and Rustici, Gabriella and Schurer, Stephan and Sharples, Kathryn and e Silva, Marina and Stanford, Natalie J and Subirats-Coll, Inmaculada and Swedlow, Jason and Tong, Weida and Wilkinson, Mark and Wise, John and Yilmaz, Pelin},
 doi = {10.1101/245183},
 journal = {bioRxiv}
}

In this modern, data-driven age, governments, funders and publishers expect greater transparency and reuse of research data, as well as greater access to and preservation of the data that supports research findings. Community-developed standards, such as those for the identification and reporting of data, underpin reproducible and reusable research, aid scholarly publishing, and drive both the discovery and evolution of scientific practice. The number of these standardization efforts, driven by large organizations or at the grass root level, has been on the rise since the early 2000s. Thousands of community-developed standards are available (across all disciplines), many of which have been created and/or implemented by several thousand data repositories. Nevertheless, their uptake by the research community, however, has been slow and uneven. This is mainly because investigators lack incentives to follow and adopt standards. The situation is exacerbated if standards are not promptly implemented by databases, repositories and other research tools, or endorsed by infrastructures. Furthermore, the fragmentation of community efforts results in the development of arbitrarily different, incompatible standards. In turn, this leads to standards becoming rapidly obsolete in fast-evolving research areas. As with any other digital object, standards, databases and repositories are dynamic in nature, with a life cycle that encompasses formulation, development and maintenance; their status in this cycle may vary depending on the level of activity of the developing group or community. There is an urgent need for a service that enhances the information available on the evolving constellation of heterogeneous standards, databases and repositories, guides users in the selection of these resources, and that works with developers and maintainers of these resources to foster collaboration and promote harmonization. Such an informative and educational service is vital to reduce the knowledge gap among those involved in producing, managing, serving, curating, preserving, publishing or regulating data. A diverse set of stakeholders-representing academia, industry, funding agencies, standards organizations, infrastructure providers and scholarly publishers, both national and domain-specific as well global and general organizations, have come together as a community, representing the core adopters, advisory board members, and/or key collaborators of the FAIRsharing resource. Here, we introduce its mission and community network. We present an evaluation of the standards landscape, focusing on those for reporting data and metadata - the most diverse and numerous of the standards - and their implementation by databases and repositories. We report on the ongoing challenge to recommend resources, and we discuss the importance of making standards invisible to the end users. We report on the ongoing challenge to recommend resources, and we discuss the importance of making standards invisible to the end users. We present guidelines that highlight the role each stakeholder group must play to maximize the visibility and adoption of standards, databases and repositories.

@article{
 title = {Molecular characterization of a novel ssRNA ourmia-like virus from the rice blast fungus Magnaporthe oryzae},
 type = {article},
 year = {2017},
 pages = {891-895},
 volume = {162},
 websites = {http://link.springer.com/10.1007/s00705-016-3144-9},
 month = {3},
 day = {17},
 id = {a9879f17-4aea-3ccc-a6df-5910e9aa6794},
 created = {2016-10-13T06:51:27.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Illana2016},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Illana, Adriana and Marconi, Marco and Rodríguez-Romero, Julio and Xu, Ping and Dalmay, Tamas and Wilkinson, Mark D. and Ayllón, Maria Ángeles and Sesma, Ane},
 doi = {10.1007/s00705-016-3144-9},
 journal = {Archives of Virology},
 number = {3}
}

@article{
 title = {Cloudy, increasingly FAIR; revisiting the FAIR Data guiding principles for the European Open Science Cloud},
 type = {article},
 year = {2017},
 pages = {49-56},
 volume = {37},
 websites = {http://www.medra.org/servlet/aliasResolver?alias=iospress&doi=10.3233/ISU-170824},
 month = {3},
 day = {7},
 id = {724e6af8-6e2e-3555-8d0e-ccf6064061c7},
 created = {2017-02-10T08:14:07.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-06-26T09:29:22.219Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Mons2017},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Mons, Barend and Neylon, Cameron and Velterop, Jan and Dumontier, Michel and da Silva Santos, Luiz Olavo Bonino and Wilkinson, Mark D},
 doi = {10.3233/ISU-170824},
 journal = {Information Services & Use},
 number = {1}
}

@article{
 title = {Identifying Bioinformatics Subworkflows with SCOFF: Semantic Clustering Of Functional Fragments},
 type = {article},
 year = {2017},
 id = {ea1a8dcb-244f-3a48-9ca1-535f26a8ed8d},
 created = {2017-02-10T08:17:11.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 bibtype = {article},
 author = {García-Jiménez, Beatriz and Wilkinson​, Mark D},
 journal = {SUBMITTED}
}

@inproceedings{
 title = {Boosting health care and life science research on rare diseases by creating a robust infrastructure of independently Findable, Accessible, Interoperable, and Reusable (FAIR) biobanks, registries, and molecular data resources},
 type = {inproceedings},
 year = {2017},
 websites = {http://irdirc-conference.org/wp-content/uploads/2017/02/IRDiRC-2017_Conference-book_final.pdf},
 id = {29656dfd-0e5c-33de-8331-dc3769e20cf6},
 created = {2017-02-21T08:48:24.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-05-07T09:56:59.017Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Enckevort2017b},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Enckevort, David van and Thompson, Rachel and Carta, Claudio and Wilkinson, Mark and Roos, Marco},
 booktitle = {IRDiRC 2017}
}

@inproceedings{
 title = {Boosting genotype-phenotype and translational research on rare diseases by establishing Findable, Accessible, Interoperable and Reusable data resources through data linking technologies},
 type = {inproceedings},
 year = {2017},
 websites = {http://www.abstractsonline.com/Plan/ViewAbstract.aspx?sKey=d9a7502e-a4d5-4bde-8329-8e609d95cd6f&cKey=1f9e2b9b-3380-44c6-928d-03e1a9914236&mKey=%7B15A3630E-7769-4D64-A80A-47F190AC2F4F%7D},
 id = {16917374-f4df-3614-ba3f-7deaca657b4b},
 created = {2017-02-21T08:48:24.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-05-07T09:56:59.049Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Enckevort2017},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Enckevort, David van and Carta, Claudio and Thompson, Rachel and Thompson, Mark and Ehrhart, Friederieke and Kaliyaperumal, Rajaram and Sernadela, Pedro and Reihs, Robert and Jacobsen, Annika and da Silva Santos, Luiz Olavo Bonino and Wilkinson, Mark D and Muller, Heimo and Oliviera, Jose Luis and Evelo, Chris T. and Taruscio, Domenica and ‘t Hoen, Peter A.C. and Roos, Marco},
 booktitle = {ESHG 2017}
}

@techreport{
 title = {Findable, Accessible, Interoperable and Reusable data resources to speed up research on rare diseases.},
 type = {techreport},
 year = {2017},
 pages = {Poster 94, p19},
 websites = {http://docplayer.it/60979940-Poster-76-il-controllo-microbiologico-delle-acque-obiettivi-antichi-tecniche-sempre-nuove.html},
 id = {28d51c69-571a-3f2b-9f16-97304f0ceef2},
 created = {2017-02-21T08:48:24.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-11-28T09:52:39.898Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Carta2017a},
 private_publication = {false},
 abstract = {CELEBRATION OF 83 YEARS OF CNMR-ISS, ITALY},
 bibtype = {techreport},
 author = {Carta, Claudio and Roos, Marco and Jansen, Mascha and Enckevort, David van and Wilkinson, Mark D and Kaliyaperumal, Rajaram and Thompson, Mark and Torreri, Paola and da Silva Santos, Luiz Olavo Bonino and Cornet, Ronald and Kodra, Yllka and Taruscio, Domenica}
}

CELEBRATION OF 83 YEARS OF CNMR-ISS, ITALY

@inbook{
 type = {inbook},
 year = {2017},
 pages = {165-179},
 websites = {http://link.springer.com/10.1007/978-3-319-67144-4_9},
 publisher = {Springer International Publishing AG},
 id = {8e8e0286-4e6c-36fc-b4b4-579825b2009d},
 created = {2017-02-21T09:01:13.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-05-07T09:56:59.153Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Roos2017},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {inbook},
 author = {Roos, Marco and López Martin, Estrella and Wilkinson, Mark D},
 editor = {Posada, Manuel and Groft, Stephen},
 doi = {10.1007/978-3-319-67144-4_9},
 chapter = {Preparing Data at the Source to Foster Interoperability across Rare Disease Resources},
 title = {Rare Diseases Epidemiology: Update and overview 2nd Edition}
}

@inproceedings{
 title = {Boosting genotype-phenotype and translational research on rare diseases by establishing Findable, Accessible, Interoperable and Reusable data resources through data linking technologies},
 type = {inproceedings},
 year = {2017},
 id = {ba9b0368-16af-3a16-9712-63dc06e7b3a8},
 created = {2017-04-07T11:33:23.737Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-06-26T09:29:22.281Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Enckevort2017a},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Enckevort, David van and Claudio, Carta and Thompson, Rachel and Thompson, Mark and Ehrhart, Friederieke and Kaliyaperumal, Rajaram and Sernadela, Pedro and Da Silva Santos, Luiz Olavo Bonino and Jacobsen, Annika and Wilkinson, Mark and Müller, Heimo and Reihs, Robert and Oliviera, Jose Luis and Evelo, Chris and Taruscio, Domenica and 'T Hoen, Peter-Bram and Roos, Marco},
 booktitle = {BioSB2017}
}

@article{
 title = {Interoperability and FAIRness through a novel combination of Web technologies},
 type = {article},
 year = {2017},
 pages = {e110},
 volume = {3},
 websites = {https://peerj.com/articles/cs-110},
 month = {4},
 day = {24},
 id = {dac66ef0-6ad2-32e1-9ccc-c90fb6fa6148},
 created = {2017-04-27T09:39:28.379Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2019-03-29T08:40:49.637Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wilkinson2017},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {Data in the life sciences are extremely diverse and are stored in a broad spectrum of repositories ranging from those designed for particular data types (such as KEGG for pathway data or UniProt for protein data) to those that are general-purpose (such as FigShare, Zenodo, Dataverse or EUDAT). These data have widely different levels of sensitivity and security considerations. For example, clinical observations about genetic mutations in patients are highly sensitive, while observations of species diversity are generally not. The lack of uniformity in data models from one repository to another, and in the richness and availability of metadata descriptions, makes integration and analysis of these data a manual, time-consuming task with no scalability. Here we explore a set of resource-oriented Web design patterns for data discovery, accessibility, transformation, and integration that can be implemented by any general- or special-purpose repository as a means to assist users in finding and reusing their data holdings. We show that by using off-the-shelf technologies, interoperability can be achieved atthe level of an individual spreadsheet cell. We note that the behaviours of this architecture compare favourably to the desiderata defined by the FAIR Data Principles, and can therefore represent an exemplar implementation of those principles. The proposed interoperability design patterns may be used to improve discovery and integration of both new and legacy data, maximizing the utility of all scholarly outputs.},
 bibtype = {article},
 author = {Wilkinson, Mark D. and van Mulligen, Erik M. and Ciccarese, Paolo and Schultes, Erik A. and Verborgh, Ruben and Kaliyaperumal, Rajaram and Clark, Tim and Bolleman, Jerven T. and Thompson, Mark and Kelpin, Fleur D.L. and Swertz, Morris A. and Dumontier, Michel and Bonino da Silva Santos, Luiz Olavo and Gray, Alasdair J.G. and Kuzniar, Arnold and Gavai, Anand},
 doi = {10.7717/peerj-cs.110},
 journal = {PeerJ Computer Science}
}

Data in the life sciences are extremely diverse and are stored in a broad spectrum of repositories ranging from those designed for particular data types (such as KEGG for pathway data or UniProt for protein data) to those that are general-purpose (such as FigShare, Zenodo, Dataverse or EUDAT). These data have widely different levels of sensitivity and security considerations. For example, clinical observations about genetic mutations in patients are highly sensitive, while observations of species diversity are generally not. The lack of uniformity in data models from one repository to another, and in the richness and availability of metadata descriptions, makes integration and analysis of these data a manual, time-consuming task with no scalability. Here we explore a set of resource-oriented Web design patterns for data discovery, accessibility, transformation, and integration that can be implemented by any general- or special-purpose repository as a means to assist users in finding and reusing their data holdings. We show that by using off-the-shelf technologies, interoperability can be achieved atthe level of an individual spreadsheet cell. We note that the behaviours of this architecture compare favourably to the desiderata defined by the FAIR Data Principles, and can therefore represent an exemplar implementation of those principles. The proposed interoperability design patterns may be used to improve discovery and integration of both new and legacy data, maximizing the utility of all scholarly outputs.

@inproceedings{
 title = {Overview of a suite of tools and training material for implementing FAIR data principles},
 type = {inproceedings},
 year = {2017},
 websites = {https://www.elixir-europe.org/events/webinar-fair},
 id = {52a37984-f009-376f-b10b-46c958c4dd4b},
 created = {2017-09-29T13:12:18.895Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-05-07T09:56:59.131Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Thompson2017},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Thompson, Mark and Wilkinson, Mark and Kaliyaperumal, Rajaram and Burger, Kees and Leeuwen, Shamanou van and Jacobsen, Annika and Carta, Claudio and Schultes, Erik and Finkers, Richard and Enckevort, David van and Jansen, Mascha and Roos, Marco and Mons, Barend and Bonino, Luiz},
 booktitle = {ELIXIR Webinar}
}

@inproceedings{
 title = {Implementing ELSI 2.0 for international collaborative research: improving access to clinical and genetics data by connecting ELSI policies, FAIR data software solutions, and ELIXIR-AAI},
 type = {inproceedings},
 year = {2017},
 pages = {POSTER},
 id = {8e0e63bc-6fbd-376f-aba8-fa750920c844},
 created = {2017-09-29T13:12:18.896Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-07-06T08:42:56.712Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Gainotti, Sabina and Petrini, Carlo and Mascalzoni, Deborah and Floridia, Giovanna and Riva, Luciana and Wilkinson, Mark and Roos, Marco},
 booktitle = {SWAT4HCLS 2017}
}

@inproceedings{
 title = {The FAIRification of data and the potentialities of FAIR resources showed, in practice, at the Rome “Bring Your Own Data” workshop},
 type = {inproceedings},
 year = {2017},
 websites = {http://ceur-ws.org/Vol-2042/paper27.pdf},
 id = {8becf279-54a5-3a0b-980a-c45a1fd31bf0},
 created = {2017-10-05T10:54:57.957Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-05-07T09:56:59.165Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Carta2017},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Carta, Claudio and Roos, Marco and Jacobsen, Annika and Kaliyaperumal, Rajaram and Thompson, Mark and Wilkinson, Mark and Cornet, Ronald and Waagmeester, Andra and van Enckevort, David and Jansen, Mascha and Licata, Luana and Via, Allegra and Taruscio, Domenica},
 booktitle = {Proceedings of SWAT4HCLS 2017}
}

@techreport{
 title = {FAIRMetrics/Metrics: Initial set of proposed FAIR Metrics for community discussion},
 type = {techreport},
 year = {2017},
 keywords = {Archival,Digital Objects,FAIR Data,FAIR Metrics,Interoperability,Quality Control,Research Objects,Reusability},
 websites = {https://doi.org/10.5281/zenodo.1065974},
 month = {11},
 day = {24},
 id = {57e20fe8-f40b-3da3-a076-bf8c3ab69293},
 created = {2017-11-27T08:25:47.562Z},
 accessed = {2017-11-27},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-05-07T09:56:59.149Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wilkinson2017},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {techreport},
 author = {Wilkinson, Mark and Sansone, Susanna-Assunta and Bonino, Luiz Olavo and Schultes, Erik and Doorn, Peter and Dumontier, Michel},
 doi = {10.5281/ZENODO.1065974}
}

@article{
 title = {A design framework and exemplar metrics for FAIRness},
 type = {article},
 year = {2017},
 id = {c1efd63b-a71f-34c4-a2e2-9cdc8c420dae},
 created = {2017-11-28T09:52:39.493Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-11-28T09:52:39.493Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 bibtype = {article},
 author = {Wilkinson, Mark D and Sansone, Susanna-Assunta and Schultes, Erik and Doorn, Peter and da Silva Santos, Luiz Olavo Bonino and Dumontier, Michel},
 doi = {10.1101/225490},
 journal = {bioRxiv}
}

@inproceedings{
 title = {Overview of a suite of middle-ware services for implementing FAIR data principles},
 type = {inproceedings},
 year = {2017},
 volume = {2042},
 id = {be57fabb-5b3d-373a-9592-0ecbd363ab51},
 created = {2018-02-21T02:58:48.547Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-05-07T09:56:59.031Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Thompson, M. and Bonino, L. and Wilkinson, M.D. and Kaliyaperumal, R. and Burger, K. and Van Leeuwen, S. and Jacobsen, A. and Carta, C. and Schultes, E. and Van Enckevort, D. and Finkers, R. and Jansen, M. and Mons, B. and Roos, M.},
 booktitle = {CEUR Workshop Proceedings}
}

@inproceedings{
 title = {Bring Your Own Data workshop is an excellent tool to promote the establishment of Findable, Accessible, Interoperable, and Reusable rare disease registries},
 type = {inproceedings},
 year = {2017},
 websites = {http://www.abstractsonline.com/Plan/ViewAbstract.aspx?sKey=23903b09-5750-4359-ad3a-157d48dc9c04&cKey=2e3c9531-7a52-437d-aff1-fb6a8dcead6b&mKey=%7B15A3630E-7769-4D64-A80A-47F190AC2F4F%7D},
 id = {94545155-81fb-307d-8b1d-3854e5d2b2a4},
 created = {2018-05-07T09:56:58.768Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-09-02T13:34:05.267Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Carta2017},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Carta, Claudio and Roos, Marco and Jansen, Mascha and Wilkinson, Mark D and Bonino da Silva Santos, Luis and van Enckevort, David and Taruscio, Domenica},
 booktitle = {Procedigs of the European Human Genetics Conference 2017}
}

@article{
 title = {The FAIR Guiding Principles for scientific data management and stewardship},
 type = {article},
 year = {2016},
 pages = {160018},
 volume = {3},
 websites = {http://www.nature.com/articles/sdata201618},
 month = {3},
 day = {15},
 id = {c99aac47-49c5-35e1-a8f7-08a234da22e7},
 created = {2016-03-16T08:48:02.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wilkinson2016},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Wilkinson, Mark D. and Dumontier, Michel and Aalbersberg, IJsbrand Jan and Appleton, Gabrielle and Axton, Myles and Baak, Arie and Blomberg, Niklas and Boiten, Jan-Willem and da Silva Santos, Luiz Bonino and Bourne, Philip E. and Bouwman, Jildau and Brookes, Anthony J. and Clark, Tim and Crosas, Mercè and Dillo, Ingrid and Dumon, Olivier and Edmunds, Scott and Evelo, Chris T. and Finkers, Richard and Gonzalez-Beltran, Alejandra and Gray, Alasdair J.G. and Groth, Paul and Goble, Carole and Grethe, Jeffrey S. and Heringa, Jaap and ’t Hoen, Peter A.C and Hooft, Rob and Kuhn, Tobias and Kok, Ruben and Kok, Joost and Lusher, Scott J. and Martone, Maryann E. and Mons, Albert and Packer, Abel L. and Persson, Bengt and Rocca-Serra, Philippe and Roos, Marco and van Schaik, Rene and Sansone, Susanna-Assunta and Schultes, Erik and Sengstag, Thierry and Slater, Ted and Strawn, George and Swertz, Morris A. and Thompson, Mark and van der Lei, Johan and van Mulligen, Erik and Velterop, Jan and Waagmeester, Andra and Wittenburg, Peter and Wolstencroft, Katherine and Zhao, Jun and Mons, Barend},
 doi = {10.1038/sdata.2016.18},
 journal = {Scientific Data}
}

@article{
 title = {Temporal microbiome road-maps guided by perturbations},
 type = {article},
 year = {2016},
 pages = {049510},
 websites = {http://www.biorxiv.org/content/early/2016/04/20/049510.abstract},
 month = {4},
 day = {20},
 id = {3e5b993a-e919-3c91-b655-f647297f8df2},
 created = {2016-04-22T08:12:54.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-06-26T10:23:27.782Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Garcia-Jimenez2016a},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {Motivation: There are few tools that allow longitudinal analysis of metagenomic data subjected to distinct perturbations. Methods: This study examines longitudinal metagenomics data modelled as a Markov Decision Process (MDP). Given an external perturbation, the MDP predicts the next microbiome state in a temporal sequence, selected from a finite set of possible microbiome states. Results: We examined three distinct datasets to demonstrate this approach. An MDP created for a vaginal microbiome time series generates a variety of behaviour policies. For example, that moving from a state associated with bacterial vaginosis to a healthier one, requires avoiding perturbations such as lubricant, sex toys, tampons and anal sex. The flexibility of our proposal is verified after applying MDPs to human gut and chick gut microbiomes, taking nutritional intakes, or salmonella and probiotic treatments, respectively, as perturbations. In the latter case, MDPs provided a quantitative explanation for why salmonella vaccine accelerates microbiome maturation in chicks. This novel analytical approach has applications in, for example, medicine where the MDP could suggest the sequence of perturbations (e.g. clinical interventions) to apply to follow the best path from any given starting state, to a desired (healthy) state, avoiding strongly negative states.},
 bibtype = {article},
 author = {García-Jiménez, Beatriz and Wilkinson, Mark},
 doi = {10.1101/049510},
 journal = {bioRxiv}
}

Motivation: There are few tools that allow longitudinal analysis of metagenomic data subjected to distinct perturbations. Methods: This study examines longitudinal metagenomics data modelled as a Markov Decision Process (MDP). Given an external perturbation, the MDP predicts the next microbiome state in a temporal sequence, selected from a finite set of possible microbiome states. Results: We examined three distinct datasets to demonstrate this approach. An MDP created for a vaginal microbiome time series generates a variety of behaviour policies. For example, that moving from a state associated with bacterial vaginosis to a healthier one, requires avoiding perturbations such as lubricant, sex toys, tampons and anal sex. The flexibility of our proposal is verified after applying MDPs to human gut and chick gut microbiomes, taking nutritional intakes, or salmonella and probiotic treatments, respectively, as perturbations. In the latter case, MDPs provided a quantitative explanation for why salmonella vaccine accelerates microbiome maturation in chicks. This novel analytical approach has applications in, for example, medicine where the MDP could suggest the sequence of perturbations (e.g. clinical interventions) to apply to follow the best path from any given starting state, to a desired (healthy) state, avoiding strongly negative states.

@article{
 title = {Publishing FAIR Data: An Exemplar Methodology Utilizing PHI-Base},
 type = {article},
 year = {2016},
 volume = {7},
 websites = {http://journal.frontiersin.org/article/10.3389/fpls.2016.00641,http://journal.frontiersin.org/Article/10.3389/fpls.2016.00641/abstract},
 month = {5},
 day = {12},
 id = {21d13287-b6e0-3198-9000-0a662ac291ad},
 created = {2016-04-25T06:42:57.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Rodriguez-Iglesias2016},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Rodríguez-Iglesias, Alejandro and Rodríguez-González, Alejandro and Irvine, Alistair G and Sesma, Ane and Urban, Martin and Hammond-Kosack, Kim Elizabeth and Wilkinson, Mark D},
 doi = {10.3389/fpls.2016.00641},
 journal = {Frontiers in Plant Science}
}

@inproceedings{
 title = {MDPbiome: Predicting temporal microbiome dynamics influenced by external perturbations},
 type = {inproceedings},
 year = {2016},
 websites = {http://jbi2016.webs.upv.es/wp-content/uploads/2016/05/JBI2016.AbstractsBooklet-1.pdf},
 city = {May 10-13, Valencia, Spain},
 id = {8dfd58de-680a-3e56-b738-6eaf8dadd24b},
 created = {2016-04-25T06:42:57.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Garcia-Jimenez2016},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {García-Jiménez, Beatriz and Wilkinson, Mark},
 booktitle = {XIII Symposium on Bioinformatics}
}

@inproceedings{
 title = {From hypothesis construction, through experimental execution, to result publication and citation},
 type = {inproceedings},
 year = {2016},
 pages = {14},
 websites = {http://repositorio.upct.es/bitstream/handle/10317/5290/isbn9788460853992.pdf?sequence=4&isAllowed=y},
 city = {Cartagena, Spain},
 id = {2ca52c7c-561b-3ec7-b3ee-aac2d6bd5b2d},
 created = {2016-04-26T06:00:30.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wilkinson2016a},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Wilkinson, Mark D},
 editor = {Francisco de Asis, Artés Hernández and Gutiérrez-Cortines, Marcos Egea and Fernández Hernández, Juan Antonio and Baille, Alain Daniel and Calatrava Leyva, Javier},
 booktitle = {Proceedings of the 4th Workshop on agri-food research}
}

@article{
 title = {Interoperability and FAIRness through a novel combination of Web technologies},
 type = {article},
 year = {2016},
 volume = {4},
 id = {16c454dd-d903-3a37-b8ee-d9b49e841cfa},
 created = {2016-10-14T07:04:19.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wilkinson2016b},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Wilkinson​, Mark D and Verborgh, Ruben and da Silva Santos, Luiz Olavo Bonino and Clark, Tim and Swertz, Morris A and Kelpin, Fleur D.L. and Gray, Alasdair J. G. and Schultes, Erik A. and Mulligen, Erik M. van and Ciccarese, Paolo and Thompson, Mark and Kaliyaperumal, Rajaram and Bolleman, Jerven T. and Dumontier, Michel},
 doi = {10.7287/peerj.preprints.2522v1},
 journal = {PeerJ Preprints},
 number = {e2522v1}
}

@inbook{
 type = {inbook},
 year = {2016},
 pages = {270-279},
 websites = {http://www.iste.co.uk/index.php?f=a&ACTION=View&id=1073},
 publisher = {iSTE Press},
 id = {bbdcb2f5-3e8c-33f4-865f-41c042ec66d4},
 created = {2016-10-27T12:36:22.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {BoninoDaSilvaSantos2016},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {inbook},
 author = {Bonino Da Silva Santos, L.O. and Wilkinson, Mark D. and Kuzniar, A. and Kaliyaperumal, R. and Thompson, M. and Dumontier, M. and Burger, K.},
 editor = {Zelm, Martin and Doumeingts, Guy and Mendonça, Joao Pedro},
 chapter = {FAIR Data Points Supporting Big Data Interoperability},
 title = {Enterprise Interoperability in the Digitized and Networked Factory of the Future}
}

@inproceedings{
 title = {Registries of domain-relevant semantic reference models help bootstrap interoperability in domains with fragmented data resources},
 type = {inproceedings},
 year = {2016},
 websites = {http://ceur-ws.org/Vol-1795/paper16.pdf},
 publisher = {CEUR Workshop Proceedings},
 city = {Amsterdam},
 id = {64b412ee-a51f-3e0b-b921-3a7f01784ed2},
 created = {2017-02-21T09:01:13.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2018-05-07T09:56:59.220Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Roos2016},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Roos, Marco and Wilkinson, Mark D and Kaliyaperumal, Rajaram and Thompson, Mark and Carta, Claudio and Cornet, Ronald and van Enckevort, David and Bonino, Luiz},
 editor = {Paschke, Adrian and Burger, Albert and Splendiani, Andrea and Marshall, M. Scott and Romano, Paolo},
 booktitle = {Proceedings of the 9th International Conference Semantic Web Applications and Tools for Life Sciences}
}

@article{
 title = {<b><i>VPS13D</i></b> Gene Variant Is Associated with Altered IL-6 Production and Mortality in Septic Shock},
 type = {article},
 year = {2015},
 pages = {545-553},
 volume = {7},
 websites = {http://www.karger.com/?doi=10.1159/000381265},
 month = {4},
 day = {17},
 id = {6aa7ec52-052d-37db-abac-d975e80746a3},
 created = {2014-12-17T07:07:43.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Nakada2015},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Nakada, Taka-aki and Boyd, John H. and Russell, James A. and Aguirre-Hern�ndez, Rosal�a and Wilkinson, Mark D. and Thair, Simone A. and Nakada, Emiri and McConechy, Melissa K. and Fjell, Christopher D. and Walley, Keith R.},
 doi = {10.1159/000381265},
 journal = {Journal of Innate Immunity},
 number = {5}
}

@article{
 title = {Quantitative evaluation of bias in PCR amplification and next-generation sequencing derived from metabarcoding samples.},
 type = {article},
 year = {2015},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/25577362},
 month = {1},
 day = {11},
 id = {a6e0ca44-2856-387a-a4c4-a5d769948c12},
 created = {2014-12-09T11:42:19.000Z},
 accessed = {2015-01-13},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Pawluczyk2015},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {Unbiased identification of organisms by PCR reactions using universal primers followed by DNA sequencing assumes positive amplification. We used six universal loci spanning 48 plant species and quantified the bias at each step of the identification process from end point PCR to next-generation sequencing. End point amplification was significantly different for single loci and between species. Quantitative PCR revealed that Cq threshold for various loci, even within a single DNA extraction, showed 2,000-fold differences in DNA quantity after amplification. Next-generation sequencing (NGS) experiments in nine species showed significant biases towards species and specific loci using adaptor-specific primers. NGS sequencing bias may be predicted to some extent by the Cq values of qPCR amplification.},
 bibtype = {article},
 author = {Pawluczyk, Marta and Weiss, Julia and Links, Matthew G and Egaña Aranguren, Mikel and Wilkinson, Mark D and Egea-Cortines, Marcos},
 doi = {10.1007/s00216-014-8435-y},
 journal = {Analytical and bioanalytical chemistry}
}

Unbiased identification of organisms by PCR reactions using universal primers followed by DNA sequencing assumes positive amplification. We used six universal loci spanning 48 plant species and quantified the bias at each step of the identification process from end point PCR to next-generation sequencing. End point amplification was significantly different for single loci and between species. Quantitative PCR revealed that Cq threshold for various loci, even within a single DNA extraction, showed 2,000-fold differences in DNA quantity after amplification. Next-generation sequencing (NGS) experiments in nine species showed significant biases towards species and specific loci using adaptor-specific primers. NGS sequencing bias may be predicted to some extent by the Cq values of qPCR amplification.

@inbook{
 type = {inbook},
 year = {2015},
 pages = {79-87},
 websites = {http://link.springer.com/10.1007/978-3-319-19776-0_9},
 publisher = {Springer International Publishing},
 id = {8b1a9673-9669-341b-a1b7-4ca59c97cb8d},
 created = {2015-07-09T11:49:42.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Rodriguez-Gonzalez2015},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 abstract = {In the creation of diagnostic decision support systems (DDSS) it is crucial to have validated and precise knowledge in order to create accurate systems. Typically, medical experts are the source of this knowledge, but it is not always possible to obtain all the desired information from them. Another valuable source could be medical books or articles describing the diagnosis of diseases managed by the DDSS, but again, it is not easy to extract this information. In this paper we present the results of our research, in which we have used Web scraping and a combination of natural language processing techniques to extract diagnostic criteria from MedlinePlus articles about infectious diseases.},
 bibtype = {inbook},
 author = {Rodríguez-González, Alejandro and Martínez-Romero, Marcos and Costumero, Roberto and Wilkinson, Mark D. and Menasalvas-Ruiz, Ernestina},
 editor = {Overbeek, Ross and Rocha, Miguel P. and Fdez-Riverola, Florentino and Paz, Juan F. De},
 doi = {10.1007/978-3-319-19776-0_9},
 chapter = {Diagnostic Knowledge Extraction from MedlinePlus: An Application for Infectious Diseases},
 title = {9th International Conference on Practical Applications of Computational Biology and Bioinformatics}
}

In the creation of diagnostic decision support systems (DDSS) it is crucial to have validated and precise knowledge in order to create accurate systems. Typically, medical experts are the source of this knowledge, but it is not always possible to obtain all the desired information from them. Another valuable source could be medical books or articles describing the diagnosis of diseases managed by the DDSS, but again, it is not easy to extract this information. In this paper we present the results of our research, in which we have used Web scraping and a combination of natural language processing techniques to extract diagnostic criteria from MedlinePlus articles about infectious diseases.

@misc{
 title = {DataFairPort: The Perl libraries version 0.231},
 type = {misc},
 year = {2015},
 websites = {http://dx.doi.org/10.5281/zenodo.33584},
 month = {11},
 id = {5a073330-f305-33ec-8a6d-a80920d586d2},
 created = {2015-11-18T07:53:57.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {mark_wilkinson_2015_33584},
 source_type = {misc},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {misc},
 author = {Wilkinson, Mark and Dumontier, Michel and Durbin, Philip},
 doi = {10.5281/zenodo.33584}
}

@article{
 title = {Enhanced reproducibility of SADI web service workflows with Galaxy and Docker},
 type = {article},
 year = {2015},
 pages = {59},
 volume = {4},
 websites = {http://www.gigasciencejournal.com/content/4/1/59},
 month = {12},
 day = {3},
 id = {cb951481-aff2-3792-8db0-af7e7f4815f9},
 created = {2015-12-09T08:08:36.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Aranguren2015},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Aranguren, Mikel Egaña and Wilkinson, Mark D.},
 doi = {10.1186/s13742-015-0092-3},
 journal = {GigaScience},
 number = {1}
}

@book{
 title = {Erratum to: Diagnostic knowledge extraction from MedlinePlus: An application for infectious diseases (9th International Conference on Practical Applications of Computational Biology and Bioinformatics, Advances in Intelligent Systems and Computing 375, 10},
 type = {book},
 year = {2015},
 source = {Advances in Intelligent Systems and Computing},
 volume = {375},
 id = {96af3c35-b93e-35ef-8a35-ebbbd853e963},
 created = {2017-12-03T10:44:25.891Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-12-12T09:00:53.458Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 bibtype = {book},
 author = {Rodríguez-González, A. and Martínez-Romero, M. and Costumero, R. and Wilkinson, M.D. and Menasalvas-Ruiz, E.},
 doi = {10.1007/978-3-319-19776-0_16}
}

@article{
 title = {Executing SADI services in Galaxy},
 type = {article},
 year = {2014},
 pages = {42},
 volume = {5},
 websites = {http://www.jbiomedsem.com/content/5/1/42},
 id = {95e6db0a-202a-3397-bbeb-27bb4afa9634},
 created = {2013-12-12T11:12:08.000Z},
 accessed = {2014-09-23},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {EganaAranguren2014},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {article},
 author = {Egaña Aranguren, Mikel and Rodríguez González, Alejandro and Wilkinson, Mark D.},
 doi = {10.1186/2041-1480-5-42},
 journal = {Journal of Biomedical Semantics},
 number = {1}
}

@inproceedings{
 title = {Nanopublishing clinical diagnoses: tracking diagnostic knowledge base content and utilization},
 type = {inproceedings},
 year = {2014},
 pages = {335-340},
 id = {d20b763e-810c-303e-a692-19f9a5035867},
 created = {2014-01-23T08:32:49.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Rodriguez-Gonzalez2014},
 folder_uuids = {ec2ec352-fa41-43db-919d-f96649955c40},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Rodríguez-González, Alejandro and Martinez-Romero, Marcos and Aranguren, Mikel Egaña and Wilkinson, Mark D.},
 doi = {10.1109/CBMS.2014.82},
 booktitle = {CBMS '14 Proceedings of the 2014 IEEE 27th International Symposium on Computer-Based Medical Systems}
}

@inbook{
 type = {inbook},
 year = {2014},
 pages = {371-391},
 websites = {http://link.springer.com/chapter/10.1007/978-3-319-05687-6_15},
 publisher = {Springer International Publishing},
 chapter = {Bioinformatics Tools for Next-Generation RNA Sequencing Analysis},
 id = {8a36acd0-ce7f-3168-b83d-2da0a2c5f4bb},
 created = {2014-07-02T09:11:39.000Z},
 file_attached = {false},
 profile_id = {17c87d5d-2470-32d7-b273-0734a1d9195f},
 last_modified = {2017-03-22T07:45:59.566Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Marconi2014},
 private_publication = {false},
 abstract = {The purpose of this chapter is to introduce the reader to some of the most popular bioinformatics tools and resources available for RNA analysis. The introduction of RNA next-generation sequencing led to an explosion in the amount of quantitative transcript sequence data, which necessitated the development of adequate tools to process and make a sense of these rich and complex datasets. A large number of programs, platforms, and databases dedicated to RNA analysis have been produced over the past approximately 20 years; however, like so much other bioinformatics software, only a small portion of them are still available and in-use. As such, we will focus only on those tools and applications still in common use. This chapter is composed of three sections: the description of the general protocols for RNA sequence (generically called RNA-Seq) analyses, an outline of the most common approaches to map polyadenylation sites, and a brief introduction to noncoding RNA (ncRNA) analysis. The first section will describe the composition of steps within a typical RNA-Seq study: the experimental design, the sequencing methods, the data quality control, the read mapping, and the differential expression analysis. The second section will introduce a few recent methods developed to map polyadenylation sites: the experimental protocols (which are variations of RNA-Seq), polyadenylation site databases and prediction programs, and cis-regulatory elements discovery. The third and final section will present several of the ncRNA databases and prediction tools.},
 bibtype = {inbook},
 author = {Marconi, Marco and Rodriguez-Romero, Julio and Sesma, Ane and Wilkinson, Mark D.},
 editor = {Sesma, Ane and von der Haar, T.},
 doi = {10.1007/978-3-319-05687-6_15},
 title = {Fungal RNA biology}
}