@article{RN250,
   author = {Meng, L. and Endo, H. and Blanc-Mathieu, R. and Chaffron, S. and Hernandez-Velazquez, R. and Kaneko, H. and Ogata, H.},
   title = {Quantitative Assessment of Nucleocytoplasmic Large DNA Virus and Host Interactions Predicted by Co-occurrence Analyses},
   journal = {mSphere},
   volume = {6},
   number = {2},
   abstract = {Nucleocytoplasmic large DNA viruses (NCLDVs) are highly diverse and abundant in marine environments. However, the knowledge of their hosts is limited because only a few NCLDVs have been isolated so far. Taking advantage of the recent large-scale marine metagenomics census, in silico host prediction approaches are expected to fill the gap and further expand our knowledge of virus-host relationships for unknown NCLDVs. In this study, we built co-occurrence networks of NCLDVs and eukaryotic taxa to predict virus-host interactions using Tara Oceans sequencing data. Using the positive likelihood ratio to assess the performance of host prediction for NCLDVs, we benchmarked several co-occurrence approaches and demonstrated an increase in the odds ratio of predicting true positive relationships 4-fold compared to random host predictions. To further refine host predictions from high-dimensional co-occurrence networks, we developed a phylogeny-informed filtering method, Taxon Interaction Mapper, and showed it further improved the prediction performance by 12-fold. Finally, we inferred virophage-NCLDV networks to corroborate that co-occurrence approaches are effective for predicting interacting partners of NCLDVs in marine environments.IMPORTANCE NCLDVs can infect a wide range of eukaryotes, although their life cycle is less dependent on hosts compared to other viruses. However, our understanding of NCLDV-host systems is highly limited because few of these viruses have been isolated so far. Co-occurrence information has been assumed to be useful to predict virus-host interactions. In this study, we quantitatively show the effectiveness of co-occurrence inference for NCLDV host prediction. We also improve the prediction performance with a phylogeny-guided method, which leads to a concise list of candidate host lineages for three NCLDV families. Our results underpin the usage of co-occurrence approaches for the metagenomic exploration of the ecology of this diverse group of viruses.},
   keywords = {Ncldv
Tara Oceans
assessment
co-occurrence
host prediction},
   ISSN = {2379-5042 (Electronic)
2379-5042 (Linking)},
   DOI = {10.1128/mSphere.01298-20},
   url = {https://www.ncbi.nlm.nih.gov/pubmed/33883262},
   year = {2021},
   type = {Journal Article}
}

{"_id":"apexm98FoXh8FfoJH","bibbaseid":"meng-endo-blancmathieu-chaffron-hernandezvelazquez-kaneko-ogata-quantitativeassessmentofnucleocytoplasmiclargednavirusandhostinteractionspredictedbycooccurrenceanalyses-2021","author_short":["Meng, L.","Endo, H.","Blanc-Mathieu, R.","Chaffron, S.","Hernandez-Velazquez, R.","Kaneko, H.","Ogata, H."],"bibdata":{"bibtype":"article","type":"Journal Article","author":[{"propositions":[],"lastnames":["Meng"],"firstnames":["L."],"suffixes":[]},{"propositions":[],"lastnames":["Endo"],"firstnames":["H."],"suffixes":[]},{"propositions":[],"lastnames":["Blanc-Mathieu"],"firstnames":["R."],"suffixes":[]},{"propositions":[],"lastnames":["Chaffron"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Hernandez-Velazquez"],"firstnames":["R."],"suffixes":[]},{"propositions":[],"lastnames":["Kaneko"],"firstnames":["H."],"suffixes":[]},{"propositions":[],"lastnames":["Ogata"],"firstnames":["H."],"suffixes":[]}],"title":"Quantitative Assessment of Nucleocytoplasmic Large DNA Virus and Host Interactions Predicted by Co-occurrence Analyses","journal":"mSphere","volume":"6","number":"2","abstract":"Nucleocytoplasmic large DNA viruses (NCLDVs) are highly diverse and abundant in marine environments. However, the knowledge of their hosts is limited because only a few NCLDVs have been isolated so far. Taking advantage of the recent large-scale marine metagenomics census, in silico host prediction approaches are expected to fill the gap and further expand our knowledge of virus-host relationships for unknown NCLDVs. In this study, we built co-occurrence networks of NCLDVs and eukaryotic taxa to predict virus-host interactions using Tara Oceans sequencing data. Using the positive likelihood ratio to assess the performance of host prediction for NCLDVs, we benchmarked several co-occurrence approaches and demonstrated an increase in the odds ratio of predicting true positive relationships 4-fold compared to random host predictions. To further refine host predictions from high-dimensional co-occurrence networks, we developed a phylogeny-informed filtering method, Taxon Interaction Mapper, and showed it further improved the prediction performance by 12-fold. Finally, we inferred virophage-NCLDV networks to corroborate that co-occurrence approaches are effective for predicting interacting partners of NCLDVs in marine environments.IMPORTANCE NCLDVs can infect a wide range of eukaryotes, although their life cycle is less dependent on hosts compared to other viruses. However, our understanding of NCLDV-host systems is highly limited because few of these viruses have been isolated so far. Co-occurrence information has been assumed to be useful to predict virus-host interactions. In this study, we quantitatively show the effectiveness of co-occurrence inference for NCLDV host prediction. We also improve the prediction performance with a phylogeny-guided method, which leads to a concise list of candidate host lineages for three NCLDV families. Our results underpin the usage of co-occurrence approaches for the metagenomic exploration of the ecology of this diverse group of viruses.","keywords":"Ncldv Tara Oceans assessment co-occurrence host prediction","issn":"2379-5042 (Electronic) 2379-5042 (Linking)","doi":"10.1128/mSphere.01298-20","url":"https://www.ncbi.nlm.nih.gov/pubmed/33883262","year":"2021","bibtex":"@article{RN250,\r\n author = {Meng, L. and Endo, H. and Blanc-Mathieu, R. and Chaffron, S. and Hernandez-Velazquez, R. and Kaneko, H. and Ogata, H.},\r\n title = {Quantitative Assessment of Nucleocytoplasmic Large DNA Virus and Host Interactions Predicted by Co-occurrence Analyses},\r\n journal = {mSphere},\r\n volume = {6},\r\n number = {2},\r\n abstract = {Nucleocytoplasmic large DNA viruses (NCLDVs) are highly diverse and abundant in marine environments. However, the knowledge of their hosts is limited because only a few NCLDVs have been isolated so far. Taking advantage of the recent large-scale marine metagenomics census, in silico host prediction approaches are expected to fill the gap and further expand our knowledge of virus-host relationships for unknown NCLDVs. In this study, we built co-occurrence networks of NCLDVs and eukaryotic taxa to predict virus-host interactions using Tara Oceans sequencing data. Using the positive likelihood ratio to assess the performance of host prediction for NCLDVs, we benchmarked several co-occurrence approaches and demonstrated an increase in the odds ratio of predicting true positive relationships 4-fold compared to random host predictions. To further refine host predictions from high-dimensional co-occurrence networks, we developed a phylogeny-informed filtering method, Taxon Interaction Mapper, and showed it further improved the prediction performance by 12-fold. Finally, we inferred virophage-NCLDV networks to corroborate that co-occurrence approaches are effective for predicting interacting partners of NCLDVs in marine environments.IMPORTANCE NCLDVs can infect a wide range of eukaryotes, although their life cycle is less dependent on hosts compared to other viruses. However, our understanding of NCLDV-host systems is highly limited because few of these viruses have been isolated so far. Co-occurrence information has been assumed to be useful to predict virus-host interactions. In this study, we quantitatively show the effectiveness of co-occurrence inference for NCLDV host prediction. We also improve the prediction performance with a phylogeny-guided method, which leads to a concise list of candidate host lineages for three NCLDV families. Our results underpin the usage of co-occurrence approaches for the metagenomic exploration of the ecology of this diverse group of viruses.},\r\n keywords = {Ncldv\r\nTara Oceans\r\nassessment\r\nco-occurrence\r\nhost prediction},\r\n ISSN = {2379-5042 (Electronic)\r\n2379-5042 (Linking)},\r\n DOI = {10.1128/mSphere.01298-20},\r\n url = {https://www.ncbi.nlm.nih.gov/pubmed/33883262},\r\n year = {2021},\r\n type = {Journal Article}\r\n}\r\n\r\n","author_short":["Meng, L.","Endo, H.","Blanc-Mathieu, R.","Chaffron, S.","Hernandez-Velazquez, R.","Kaneko, H.","Ogata, H."],"key":"RN250","id":"RN250","bibbaseid":"meng-endo-blancmathieu-chaffron-hernandezvelazquez-kaneko-ogata-quantitativeassessmentofnucleocytoplasmiclargednavirusandhostinteractionspredictedbycooccurrenceanalyses-2021","role":"author","urls":{"Paper":"https://www.ncbi.nlm.nih.gov/pubmed/33883262"},"keyword":["Ncldv Tara Oceans assessment co-occurrence host prediction"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/network/files/KMdhxceuwMCTxrPYf","dataSources":["iYLLk93CYsonxaLrY","t7xPM8AA6iLF6Ckv9","jJ47DxiMR6MjLSFRc","9s8gPwvuScLx6XcJT","CG9K4BdddQWrftb7x","GXJLvS6cuRBu7DapG","oN8Wd4zAfgwaCR7pT","Ly5oTfXjg2ogJZ3Mt","WBzsMjaYZGMDcZMoy"],"keywords":["ncldv tara oceans assessment co-occurrence host prediction"],"search_terms":["quantitative","assessment","nucleocytoplasmic","large","dna","virus","host","interactions","predicted","occurrence","analyses","meng","endo","blanc-mathieu","chaffron","hernandez-velazquez","kaneko","ogata"],"title":"Quantitative Assessment of Nucleocytoplasmic Large DNA Virus and Host Interactions Predicted by Co-occurrence Analyses","year":2021}