@techreport{
 title = {Mining Microbial Genomes from Datasets on the Sequence Read Archive},
 type = {techreport},
 year = {2020},
 keywords = {NCGAS,Presentation,database,sequence read archive,sequencing},
 websites = {https://www.ncbi.nlm.nih.gov/sra},
 month = {1},
 day = {15},
 id = {600076d4-8b4d-3b61-a350-94146245ee5d},
 created = {2020-04-29T22:01:25.547Z},
 accessed = {2020-03-21},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:25.608Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {This research is based upon work supported by the National Science Foundation under grant No. ABI-1759906 to Indiana University.},
 bibtype = {techreport},
 author = {Papudeshi, Bhavya and Leffler, Haley and Ganapaneni, Sruthi and Ganote, Carrie and Sanders, Sheri A and Doak, Thomas G}
}

This research is based upon work supported by the National Science Foundation under grant No. ABI-1759906 to Indiana University.

@inproceedings{
 title = {Abstract 5109: National cyberinfrastructure and bioinformatic analysis support available to the cancer research community},
 type = {inproceedings},
 year = {2019},
 pages = {5109-5109},
 websites = {http://cancerres.aacrjournals.org/lookup/doi/10.1158/1538-7445.AM2019-5109},
 month = {7},
 publisher = {American Association for Cancer Research},
 day = {1},
 id = {fa4503c9-9ab2-3b95-b7fb-9393229da21e},
 created = {2020-04-29T22:01:25.927Z},
 accessed = {2019-08-11},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:25.985Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Papudeshi, Bhavya and Ganote, Carrie and Sanders, Sheri and Doak, Thomas G.},
 doi = {10.1158/1538-7445.AM2019-5109},
 booktitle = {Bioinformatics, Convergence Science, and Systems Biology}
}

@article{
 title = {Developing a workflow for bioacoustic recording devices and frog call analysis within Jetstream},
 type = {article},
 year = {2019},
 keywords = {IoT,Jetstream,Presentation,bioacoustics,bioinformatics,raspberry pi},
 month = {4},
 publisher = {Center of Excellence for Women & Technology},
 day = {12},
 id = {f673cd27-f0c0-3724-95d7-747a2b4b43c4},
 created = {2020-04-29T22:01:26.076Z},
 accessed = {2019-08-05},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.158Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {This research is based upon work supported by the National Science Foundation under grant No. ABI-1759906 to Indiana University.},
 bibtype = {article},
 author = {Foran, Eliza and Anderson, Jazzly and Slayton, Thomas and Guido, Emmanuel and Doak, Thomas and Sanders, Sheri}
}

This research is based upon work supported by the National Science Foundation under grant No. ABI-1759906 to Indiana University.

@article{
 title = {Automatic recognition of frog calls},
 type = {article},
 year = {2019},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/23260},
 id = {f2a70b54-062f-357d-a073-18f6f54fc302},
 created = {2020-04-29T22:01:26.088Z},
 accessed = {2019-08-05},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.192Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {Recording animal calls and vocalizations is a time-honored data collection method in various fields of biological and environmental science. In the past, the only method available for analyzing such recordings involved extensive training of human experts. Now, however, machine learning techniques have made automatic recognition of such vocalizations possible. Automatic recognition of animal calls and vocalizations is desirable on two fronts: it reduces the burden of (at least initial) data analysis, and supports non-intrusive environmental monitoring. Here, we outline a proof-of-concept workflow that will make the quest from collecting data to understanding data more attainable for researchers. We simulate this data collection process by collecting animal (frog) calls using recording devices and Raspberry Pi's, then feed this data to a database and virtual machine hosted on XSEDE resources (i.e. Jetstream and Wrangler). We then show how database pulling, machine learning, and visualization works on Jetstream.},
 bibtype = {article},
 author = {Foran, Eliza G.; Suggs, Evan D.; Underwood, Tenecious A.; Snapp-Childs, Winona; Sanders, Sheri A.},
 doi = {10.5967/PS4S-D421}
}

Recording animal calls and vocalizations is a time-honored data collection method in various fields of biological and environmental science. In the past, the only method available for analyzing such recordings involved extensive training of human experts. Now, however, machine learning techniques have made automatic recognition of such vocalizations possible. Automatic recognition of animal calls and vocalizations is desirable on two fronts: it reduces the burden of (at least initial) data analysis, and supports non-intrusive environmental monitoring. Here, we outline a proof-of-concept workflow that will make the quest from collecting data to understanding data more attainable for researchers. We simulate this data collection process by collecting animal (frog) calls using recording devices and Raspberry Pi's, then feed this data to a database and virtual machine hosted on XSEDE resources (i.e. Jetstream and Wrangler). We then show how database pulling, machine learning, and visualization works on Jetstream.

@article{
 title = {The Genome of Fish Tapeworm Nippotaenia percotti as a Potential Bookmark for Gene Loci that Facilitates Anthropogenic Infection.},
 type = {article},
 year = {2019},
 keywords = {CAFE,NCGAS,Presentation,genome assembly,genomic evolution,tapeworm,transcriptome assembly},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/22656},
 month = {1},
 publisher = {Plant and Animal Genome XXVII},
 day = {14},
 id = {dd45f3bc-8cc3-35fb-a482-17d6ab3aa36e},
 created = {2020-04-29T22:01:26.131Z},
 accessed = {2019-01-28},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.212Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {This research is based upon work supported by the National Science Foundation under grant No. ABI-1759906 to Indiana University.},
 bibtype = {article},
 author = {Sanders, Sheri and Papudeshi, Bhavya and Ganote, Carrie and Doak, Tom and Chafin, Tyler and Reshetnikov, Andrey and Sokolov, Sergey and Pummil, Jeff and Douglas, Marlis and Douglas, Michael}
}

This research is based upon work supported by the National Science Foundation under grant No. ABI-1759906 to Indiana University.

@article{
 title = {Population Genetics of Tree Swallows, in Collaboration with NCGAS},
 type = {article},
 year = {2019},
 keywords = {NCGAS,Presentation,exotoxicology,population genetics,transcriptome assembly},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/22657},
 month = {1},
 publisher = {Plant and Animal Genome XXVII},
 day = {14},
 id = {7459c13c-be94-38c5-b0da-d72294a5e328},
 created = {2020-04-29T22:01:26.183Z},
 accessed = {2019-01-28},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.272Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {This research is based upon work supported by the National Science Foundation under grant No. ABI-1759906 to Indiana University.},
 bibtype = {article},
 author = {Sanders, Sheri and Papudeshi, Bhavya and Ganote, Carrie and Doak, Tom and Mansfield, Charles and Tseng, Chi Yen and Custer, Thomas and Custer, Christine and Matson, Cole}
}

This research is based upon work supported by the National Science Foundation under grant No. ABI-1759906 to Indiana University.

@article{
 title = {Reconstruction of Metagenome-Assembled Microbial Genomes from a Micro-biome (Poster)},
 type = {article},
 year = {2018},
 keywords = {PY8},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/21901},
 month = {1},
 publisher = {Plant and Animal Genomics 2018},
 day = {15},
 id = {a9d2448c-e811-3d73-b5e5-c4cf767fb958},
 created = {2020-04-29T22:01:26.349Z},
 accessed = {2018-08-10},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.491Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Papudeshi2018},
 private_publication = {false},
 abstract = {This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.},
 bibtype = {article},
 author = {Papudeshi, Bhavya}
}

This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.

@article{
 title = {Stilbenoid prenylation pathway discovery in peanut using targeted transcriptomics (Poster)},
 type = {article},
 year = {2018},
 keywords = {PY8},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/21902},
 month = {1},
 publisher = {Plant and Animal Genomics 2018},
 day = {15},
 id = {19362d15-6986-35b1-bb01-810e8c8f340b},
 created = {2020-04-29T22:01:26.396Z},
 accessed = {2018-08-10},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.478Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Sanders2018},
 private_publication = {false},
 abstract = {This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.},
 bibtype = {article},
 author = {Sanders, Sheri and Podicheti, Ram and Yang, Tianhong and Fang, Lingling and Jayanthi, Srinivas and Rajan, Gayathri and Kumar, Thallapuranam Krishnaswarmy Suresh and Medina-Bolivar, Fabricio and Mockaitis, Keithanne}
}

This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.

@article{
 title = {Solving the challenges of complex genome analysis collaborations on-line using XSEDE resources (Poster)},
 type = {article},
 year = {2018},
 keywords = {PY8},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/21903},
 month = {1},
 publisher = {Plant and Animal Genomics 2018},
 day = {15},
 id = {816d8743-4291-3bcf-980b-b4bf5aad253a},
 created = {2020-04-29T22:01:26.465Z},
 accessed = {2018-08-10},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.590Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Ganote2018},
 private_publication = {false},
 abstract = {This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.},
 bibtype = {article},
 author = {Ganote, Carrie and Sanders, Sheri and Wu, Le-Shin and Doak, Tom and Mockaitis, Keithanne}
}

This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.

@article{
 title = {National Center for Genome Analysis Support (NCGAS) as a platform for metagenomic analysis},
 type = {article},
 year = {2017},
 websites = {https://www.iscb.org/cms_addon/conferences/rocky2017/track/posters.php},
 id = {a53a61b7-902b-3961-b632-9d5d05b779b4},
 created = {2020-04-29T22:01:26.202Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.257Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Bhavya2017},
 private_publication = {false},
 abstract = {A metagenome contains all the microbial genetic material from an environmental sample, and could be from a human fecal sample to study human gut microbiome, a hospital environmental sample to study the microbes present within neonatal intensive care units, a freshwater sample to monitor invasive species, or water from Great Barrier reef to study coral disease. The vast applications of these techniques in biology has led to a drastic increase in the number of metagenomic-related projects, generating large datasets that exceed the ability of a personal computer to analyze. High Performance Computing (HPC) is being applied to these challenges, but most biologists do not have the necessary background to run analyses on HPC clusters. NCGAS is a collaborative project between Indiana University and Pittsburg Supercomputing Center to enable the genomics community to analyze sequence data by providing HPC computational resources, data storage, and training and project consultation. Metagenomic analysis continues to evolve rapidly, with a wide array of bioinformatics software to select from at each step in an analysis. Selection of tools therefore remains a concern, and is being addressed by the metagenomics community through critical assessment of metagenomic interpretation (CAMI), to derive best practices and pipelines. NCGAS will continue providing training in HPC, data management and consultation to the metagenomics community, as well as work with users to accumulate user feedback on metagenomic tools, and feedback to the metagenomics community through CAMI and conferences, working towards establishing pipelines and reproducibility. I will use marine metagenomes to illustrate this process.},
 bibtype = {article},
 author = {Bhavya, Papudeshi and Sanders, Sheri and Ganote, Carrie and Blood, Philip and Doak, Thomas},
 keywords = {py8}
}

A metagenome contains all the microbial genetic material from an environmental sample, and could be from a human fecal sample to study human gut microbiome, a hospital environmental sample to study the microbes present within neonatal intensive care units, a freshwater sample to monitor invasive species, or water from Great Barrier reef to study coral disease. The vast applications of these techniques in biology has led to a drastic increase in the number of metagenomic-related projects, generating large datasets that exceed the ability of a personal computer to analyze. High Performance Computing (HPC) is being applied to these challenges, but most biologists do not have the necessary background to run analyses on HPC clusters. NCGAS is a collaborative project between Indiana University and Pittsburg Supercomputing Center to enable the genomics community to analyze sequence data by providing HPC computational resources, data storage, and training and project consultation. Metagenomic analysis continues to evolve rapidly, with a wide array of bioinformatics software to select from at each step in an analysis. Selection of tools therefore remains a concern, and is being addressed by the metagenomics community through critical assessment of metagenomic interpretation (CAMI), to derive best practices and pipelines. NCGAS will continue providing training in HPC, data management and consultation to the metagenomics community, as well as work with users to accumulate user feedback on metagenomic tools, and feedback to the metagenomics community through CAMI and conferences, working towards establishing pipelines and reproducibility. I will use marine metagenomes to illustrate this process.

@article{
 title = {deNovo assembly and annotation of Ambystoma laterale and Ambystoma jeffersonianum transcriptomes: the first steps toward investigating polyploid salamander expression},
 type = {article},
 year = {2017},
 keywords = {de novo transcriptome,polyploid,salamander},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/21599},
 month = {6},
 day = {25},
 id = {1196faaa-08a7-315f-80c1-947a4db48c4f},
 created = {2020-04-29T22:01:26.622Z},
 accessed = {2018-08-10},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.745Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Sanders2017},
 private_publication = {false},
 abstract = {This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.},
 bibtype = {article},
 author = {Sanders, Sheri and Pfrender, Michael}
}

This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.

@inproceedings{
 title = {NCGAS: National Resources for Computationally Intensive Bioinformatics},
 type = {inproceedings},
 year = {2017},
 keywords = {PY8},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/21606},
 publisher = {PEARC 2017},
 id = {15745405-38a0-3346-b5d6-459b19cef117},
 created = {2020-04-29T22:01:26.726Z},
 accessed = {2017-09-05},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.818Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Doak2017},
 private_publication = {false},
 abstract = {This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.},
 bibtype = {inproceedings},
 author = {Doak, Tom and Ganote, Carrie and Sanders, Sheri and Hallock, Barb},
 booktitle = {Practice & Experience in Advanced Research Computing}
}

This research is based upon work supported by the National Science Foundation under grant No. ABI-1458641 to Indiana University.

@inproceedings{
 title = {Pushing the limites of job flexibility},
 type = {inproceedings},
 year = {2017},
 websites = {https://scholarworks.iu.edu/dspace/bitstream/handle/2022/21603/tringal9.pdf?sequence=1&isAllowed=y},
 id = {60764e13-5850-3d33-b9f9-cdca68118029},
 created = {2020-04-29T22:01:26.735Z},
 accessed = {2017-09-05},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.833Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Ganote2017},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Ganote, Carrie and Sanders, Sheri and Doak, Tom and Brokaw, Cicada and Bhavya, N P and Haas, Brian},
 booktitle = {Galaxy community confernece}
}

@inproceedings{
 title = {Computational Considerations in Transcriptome Assemblies and Their Evaluation, using High Quality Human RNA-Seq data},
 type = {inproceedings},
 year = {2016},
 keywords = {PY6},
 pages = {1-4},
 websites = {http://dl.acm.org/citation.cfm?doid=2949550.2949572},
 publisher = {ACM Press},
 city = {New York, New York, USA},
 id = {85d1f0d0-9a9f-3d49-907b-0bde948a1275},
 created = {2020-04-29T22:01:25.040Z},
 accessed = {2017-09-05},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:25.150Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Ghaffari2016},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Ghaffari, Noushin and Abante, Jordi and Singh, Raminder and Blood, Philip D. and Johnson, Charles D.},
 doi = {10.1145/2949550.2949572},
 booktitle = {Proceedings of the XSEDE16 on Diversity, Big Data, and Science at Scale - XSEDE16}
}

@inproceedings{
 title = {Indiana University Founds the National Center for Genome Analysis Support: Now Open for Business},
 type = {inproceedings},
 year = {2016},
 websites = {https://pag.confex.com/pag/xx/webprogram/Paper3094.html},
 id = {c0e38723-8a45-39b6-a678-712d1da0c258},
 created = {2020-04-29T22:01:27.167Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:27.220Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Doak2016},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Doak, T},
 booktitle = {Plant and Animal Genome XX Conference}
}

@inproceedings{
 title = {The National Center for Genomic Analysis Support: creating a national cyberinfrastructure environment for genomics researchers.},
 type = {inproceedings},
 year = {2015},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/20455},
 id = {65ac5b76-bd1b-3e74-ada0-2d7f12905c83},
 created = {2020-04-29T22:01:26.795Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.853Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Barnett2015},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Barnett, W and Doak, T and Wu, LS and Ganote, C},
 booktitle = {European Grid Infrastructure}
}

@inproceedings{
 title = {A Comparison of Transcript Discovery with Different de novo Assembly Software Tools},
 type = {inproceedings},
 year = {2015},
 websites = {https://pag.confex.com/pag/xxiii/webprogram/Paper16878.html},
 id = {805d0f25-573a-348c-8d2d-9ee2063b7169},
 created = {2020-04-29T22:01:27.023Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:27.075Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Wu2015},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Wu, LS},
 booktitle = {Plant and Animal Genome XXIII Conference}
}

@inproceedings{
 title = {National Resources for Computationally Intensive Genomics},
 type = {inproceedings},
 year = {2015},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/20456},
 id = {387f7bcc-1b28-3e1c-b95c-7ed2141090e3},
 created = {2020-04-29T22:01:27.165Z},
 accessed = {2017-05-12},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:27.237Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Ganote2015},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Ganote, C and Hallock, B},
 booktitle = {Plant and Animal Genome Conference, 2015}
}

@inproceedings{
 title = {Resolution of Whole-Genome Duplications in Paramecium Species},
 type = {inproceedings},
 year = {2014},
 websites = {https://pag.confex.com/pag/xxii/webprogram/Paper12136.html},
 id = {892f4c61-a5b5-3067-ad5a-b3f553d7112a},
 created = {2020-04-29T22:01:27.077Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:27.161Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Doak2014},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Doak, T},
 booktitle = {Plant and Animal Genome XXII Conference}
}

@inproceedings{
 title = {National Center for Genome Analysis Support Leverages XSEDE to Support Life Science Research},
 type = {inproceedings},
 year = {2013},
 keywords = {PY2},
 pages = {13:1--13:7},
 websites = {http://dl.acm.org/citation.cfm?id=2484790,http://doi.acm.org/10.1145/2484762.2484790,https://scholarworks.iu.edu/dspace/handle/2022/16402},
 publisher = {ACM},
 city = {New York, NY, USA},
 series = {XSEDE '13},
 id = {0bdc9950-3341-31b5-b822-ceae4f35f9f7},
 created = {2020-04-29T22:01:25.122Z},
 accessed = {2017-05-12},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:25.203Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {LeDuc:2013:NCG:2484762.2484790},
 source_type = {inproceedings},
 private_publication = {false},
 abstract = {To be presented at XSEDE Conference 2013, San Diego, CA},
 bibtype = {inproceedings},
 author = {LeDuc, Richard D. RD Richard D and Wu, LS Le-Shin and Ganote, Carrie L. and Doak, Thomas and Blood, Philip D. PD Philip D and Vaughn, Matthew and Wu, LS Le-Shin and Blood, Philip D. PD Philip D and Ganote, Carrie L. and Vaughn, Matthew},
 doi = {10.1145/2484762.2484790},
 booktitle = {Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery}
}

To be presented at XSEDE Conference 2013, San Diego, CA

@inproceedings{
 title = {NCGAS (Poster at AMIA Translational Bioinformatics Summit)},
 type = {inproceedings},
 year = {2013},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/15582},
 id = {d255671c-64fa-33d9-bacc-505ddf3d2acb},
 created = {2020-04-29T22:01:27.024Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:27.084Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Barnett2013},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Barnett, WK and LeDuc, RD},
 booktitle = {AMIA Translational Bioinformatics Summit}
}

@inproceedings{
 title = {National Center for Genome Analysis Support (Poster)},
 type = {inproceedings},
 year = {2012},
 keywords = {Presentation,genomics,ncgas,research cyberinfrastructure},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/14539},
 id = {5496727a-5b5b-3885-aa1f-31c4341e6bb3},
 created = {2020-04-29T22:01:26.661Z},
 accessed = {2017-09-05},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.739Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Doak2012},
 private_publication = {false},
 abstract = {This document was developed with support from National Science Foundation (NSF) grant OCI-1053575. Any opinions, findings, and conclusions or recommendations expressed in this material are those of the author(s) and do not necessarily reflect the views of the NSF.},
 bibtype = {inproceedings},
 author = {Doak, Thomas G. and Wu, Le-Shin and Stewart, Craig A. and Henschel, Robert and Barnett, William K.},
 booktitle = {Plant and Animal Genome XXIII Conference}
}

This document was developed with support from National Science Foundation (NSF) grant OCI-1053575. Any opinions, findings, and conclusions or recommendations expressed in this material are those of the author(s) and do not necessarily reflect the views of the NSF.

@inproceedings{
 title = {National Center for Genome Analysis Support},
 type = {inproceedings},
 year = {2012},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/14539},
 id = {b9a1a84f-f2f2-3b9b-b43d-88b7e0b2ef6f},
 created = {2020-04-29T22:01:26.933Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.997Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Doak2012a},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Doak, TG and Wu, LS and Stewart, CA and Henschel, R and Barnett, WK},
 booktitle = {Pacific Bioscience Computing}
}

@techreport{
 title = {Example to make a scientific poster},
 type = {techreport},
 keywords = {PowerPoint,create,custom,design,download,example,poster,presentation,printing,research,sample,scientific,symposium,template},
 websites = {https://github.com/NCGAS/CEWiT-REU-},
 id = {2664d835-2676-3bb9-8a02-44dc979a80d8},
 created = {2020-04-29T22:01:25.742Z},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:25.867Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 bibtype = {techreport},
 author = {Graphicsland, undefined and MakeSignscom, undefined}
}

@techreport{
 title = {Navigating the Sequence Read Archive to identify crAssphage, an ubiquitous inhabitant of the human microbiome},
 type = {techreport},
 id = {4849e600-18a1-3051-8f4e-6edb69854e8b},
 created = {2020-04-29T22:01:25.805Z},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:25.880Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 bibtype = {techreport},
 author = {Cai, Jasmine X and Weathers, Jania G and Leffler, Haley and Ganapaneni, Sruthi and Papudeshi, Bhavya and Sanders, Sheri A and Doak, Thomas G}
}

@techreport{
 title = {Mining the Sequence Read Archive to identify crAssphage, a ubiquitous inhabitant of the human microbiome, in dog and pig samples},
 type = {techreport},
 websites = {https://github.com/NCGAS/CEWiT-REU-},
 id = {67f104c5-cc37-3987-af82-5966c9a643f0},
 created = {2020-04-29T22:01:26.067Z},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.148Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 bibtype = {techreport},
 author = {Leffler, Haley and Ganapaneni, Sruthi and Papudeshi, Bhavya and Sanders, Sheri A and Doak, Thomas G}
}

@article{
 title = {National Center for Genome Analysis Support (NCGAS): Genomics and other Science in the NSF-Funded Jetstream Cloud},
 type = {article},
 websites = {http://hdl.handle.net/2022/25301},
 id = {67dcc162-185a-3d20-b1cb-fd5368a5ec4a},
 created = {2020-04-29T22:01:26.340Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.433Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {The National Center for Genome Analysis Support (NCGAS) is an NSF-funded (NSF-1445604) center that helps all NSF-funded researchers doing genomics research. Genomics includes transcriptomics, metagenomics, genome annotation, etc. Our support includes providing access to large memory computing, maintaining curated sets of genomics applications, providing one-on-one consultation, and creating educational opportunities. A resource that we have come to rely on for providing these services is the NSF-funded Jetstream Cloud—maintained by Indiana University (led by the Indiana University Pervasive Technology Institute (PTI) and the University of Texas at Austin's Texas Advanced Computing Center (TACC). Additionally, we leverage Globus data transfer tools. Globus at the University of Chicago is responsible for integrating Jetstream with the NSF-funded Extreme Science and Engineering Discovery Environment (XSEDE), and for integrating Globus data movement and management tools, as well as Globus-based secure user authentication. With a focus on ease of use and broad accessibility, Jetstream is designed for those who have not previously used high performance computing and software resources—for researchers who need more than desktop-strength computing but less than full-scale High Performance Computing (HPC). Jetstream features a web-based user interface based on the popular Atmosphere cloud computing environment—developed by CyVerse—extended to support science and engineering research generally. The system is particularly geared toward 21st-century workforce development at small colleges and universities – especially historically black colleges and universities, minority serving institutions, tribal colleges, and higher education institutions in EPSCoR States. Jetstream provides a library of virtual machines designed to do discipline-specific scientific analysis, but researchers can also develop their own VMs, with their own software sets, or sets specialized to a particular task. These VMs can be both saved and shared with collaborators. Currently there are 19 genomics VMs, including RStudio instances with bioconductor, ready-made genome browsers with JBrowse/Tripal, and metagenomic tools like QIIME2 and Anvi’o. biology and molecular biology researchers are the largest users of Jetstream. NCGAS has found VMs extremely useful in education and workshops: we develop class-specific VMs, with all the applications needed, then clone, so that each student has their own VM to work on (making courses easy to scale). In addition to on-demand VMs, persistent science gateways can be established using template VMs NCGAS has built. These can be used to provide services to collaborators or to the world. Users can easily create Galaxy servers on Jetstream: each server comes preconfigured with hundreds of tools and commonly used reference datasets—once running, researchers can use it or customize it. Many NCGAS users establish genome browsers—specific to their organism—that are shared with small sets of collaborating researchers—but can be shared to the world. Jetstream is accessed via an allocation process at XSEDE—a startup allocation is typically approved within a day.},
 bibtype = {article},
 author = {Doak, Thomas and Sanders, Sheri and Ganote, Carrie and Papudeshi, Bhavya and Fischer, Jeremy and Hancock, David Y}
}

The National Center for Genome Analysis Support (NCGAS) is an NSF-funded (NSF-1445604) center that helps all NSF-funded researchers doing genomics research. Genomics includes transcriptomics, metagenomics, genome annotation, etc. Our support includes providing access to large memory computing, maintaining curated sets of genomics applications, providing one-on-one consultation, and creating educational opportunities. A resource that we have come to rely on for providing these services is the NSF-funded Jetstream Cloud—maintained by Indiana University (led by the Indiana University Pervasive Technology Institute (PTI) and the University of Texas at Austin's Texas Advanced Computing Center (TACC). Additionally, we leverage Globus data transfer tools. Globus at the University of Chicago is responsible for integrating Jetstream with the NSF-funded Extreme Science and Engineering Discovery Environment (XSEDE), and for integrating Globus data movement and management tools, as well as Globus-based secure user authentication. With a focus on ease of use and broad accessibility, Jetstream is designed for those who have not previously used high performance computing and software resources—for researchers who need more than desktop-strength computing but less than full-scale High Performance Computing (HPC). Jetstream features a web-based user interface based on the popular Atmosphere cloud computing environment—developed by CyVerse—extended to support science and engineering research generally. The system is particularly geared toward 21st-century workforce development at small colleges and universities – especially historically black colleges and universities, minority serving institutions, tribal colleges, and higher education institutions in EPSCoR States. Jetstream provides a library of virtual machines designed to do discipline-specific scientific analysis, but researchers can also develop their own VMs, with their own software sets, or sets specialized to a particular task. These VMs can be both saved and shared with collaborators. Currently there are 19 genomics VMs, including RStudio instances with bioconductor, ready-made genome browsers with JBrowse/Tripal, and metagenomic tools like QIIME2 and Anvi’o. biology and molecular biology researchers are the largest users of Jetstream. NCGAS has found VMs extremely useful in education and workshops: we develop class-specific VMs, with all the applications needed, then clone, so that each student has their own VM to work on (making courses easy to scale). In addition to on-demand VMs, persistent science gateways can be established using template VMs NCGAS has built. These can be used to provide services to collaborators or to the world. Users can easily create Galaxy servers on Jetstream: each server comes preconfigured with hundreds of tools and commonly used reference datasets—once running, researchers can use it or customize it. Many NCGAS users establish genome browsers—specific to their organism—that are shared with small sets of collaborating researchers—but can be shared to the world. Jetstream is accessed via an allocation process at XSEDE—a startup allocation is typically approved within a day.

@article{
 title = {Harvesting Field Station Data: Automating Raspberry Pi Sensors to Collaborative Websites, and Update},
 type = {article},
 websites = {https://scholarworks.iu.edu/dspace/handle/2022/25303},
 id = {663767aa-136d-382d-b236-f892d3584eec},
 created = {2020-04-29T22:01:26.449Z},
 accessed = {2020-03-21},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.546Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 bibtype = {article},
 author = {Sanders, Sheri and Foran, Eliza and Guido, Emmanuel and Anderson, Jazzly and Slayton, Thomas and Doak, Thomas}
}

@techreport{
 title = {Coupling metagenomics with high-performance computing to mine the Sequence Read Archive (SRA) to analyze Pseudomonas phage PAK-P1},
 type = {techreport},
 websites = {https://use.jetstream-},
 id = {31e149a6-cdb0-3db7-9b70-546a11b140c4},
 created = {2020-04-29T22:01:26.645Z},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {dd609669-8d76-3d22-8b9b-f61e92589a8a},
 last_modified = {2020-04-29T22:01:26.845Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 bibtype = {techreport},
 author = {Ganapaneni, Sruthi and Leffler, Haley and Papudeshi, Bhavya and Sanders, Sheri A and Doak, Thomas A}
}