The increasing number of sequenced plant genomes is placing new demands on the methods applied to analyze, annotate, and model these genomes. Today's annotation pipelines result in inconsistent gene assignments that complicate comparative analyses and prevent efficient construction of metabolic models. To overcome these problems, we have developed the PlantSEED, an integrated, metabolism-centric database to support subsystems-based annotation and metabolic model reconstruction for plant genomes. PlantSEED combines SEED subsystems technology, first developed for microbial genomes, with refined protein families and biochemical data to assign fully consistent functional annotations to orthologous genes, particularly those encoding primary metabolic pathways. Seamless integration with its parent, the prokaryotic SEED database, makes PlantSEED a unique environment for cross-kingdom comparative analysis of plant and bacterial genomes. The consistent annotations imposed by PlantSEED permit rapid reconstruction and modeling of primary metabolism for all plant genomes in the database. This feature opens the unique possibility of model-based assessment of the completeness and accuracy of gene annotation and thus allows computational identification of genes and pathways that are restricted to certain genomes or need better curation. We demonstrate the PlantSEED system by producing consistent annotations for 10 reference genomes. We also produce a functioning metabolic model for each genome, gapfilling to identify missing annotations and proposing gene candidates for missing annotations. Models are built around an extended biomass composition representing the most comprehensive published to date. To our knowledge, our models are the first to be published for seven of the genomes analyzed.
%0 Journal Article
%1 Seaver2014Highthroughput
%A Seaver, Samuel M.
%A Gerdes, Svetlana
%A Frelin, Océane
%A Lerma-Ortiz, Claudia
%A Bradbury, Louis M.
%A Zallot, Rémi
%A Hasnain, Ghulam
%A Niehaus, Thomas D.
%A El Yacoubi, Basma
%A Pasternak, Shiran
%A Olson, Robert
%A Pusch, Gordon
%A Overbeek, Ross
%A Stevens, Rick
%A de Crécy-Lagard, Valérie
%A Ware, Doreen
%A Hanson, Andrew D.
%A Henry, Christopher S.
%D 2014
%J Proceedings of the National Academy of Sciences of the United States of America
%K database metabolic-networks plants reconstruction
%R 10.1073/pnas.1401329111
%T High-throughput comparison, functional annotation, and metabolic modeling of plant genomes using the PlantSEED resource.
%U http://dx.doi.org/10.1073/pnas.1401329111
%X The increasing number of sequenced plant genomes is placing new demands on the methods applied to analyze, annotate, and model these genomes. Today's annotation pipelines result in inconsistent gene assignments that complicate comparative analyses and prevent efficient construction of metabolic models. To overcome these problems, we have developed the PlantSEED, an integrated, metabolism-centric database to support subsystems-based annotation and metabolic model reconstruction for plant genomes. PlantSEED combines SEED subsystems technology, first developed for microbial genomes, with refined protein families and biochemical data to assign fully consistent functional annotations to orthologous genes, particularly those encoding primary metabolic pathways. Seamless integration with its parent, the prokaryotic SEED database, makes PlantSEED a unique environment for cross-kingdom comparative analysis of plant and bacterial genomes. The consistent annotations imposed by PlantSEED permit rapid reconstruction and modeling of primary metabolism for all plant genomes in the database. This feature opens the unique possibility of model-based assessment of the completeness and accuracy of gene annotation and thus allows computational identification of genes and pathways that are restricted to certain genomes or need better curation. We demonstrate the PlantSEED system by producing consistent annotations for 10 reference genomes. We also produce a functioning metabolic model for each genome, gapfilling to identify missing annotations and proposing gene candidates for missing annotations. Models are built around an extended biomass composition representing the most comprehensive published to date. To our knowledge, our models are the first to be published for seven of the genomes analyzed.
@article{Seaver2014Highthroughput,
abstract = {The increasing number of sequenced plant genomes is placing new demands on the methods applied to analyze, annotate, and model these genomes. Today's annotation pipelines result in inconsistent gene assignments that complicate comparative analyses and prevent efficient construction of metabolic models. To overcome these problems, we have developed the {PlantSEED}, an integrated, metabolism-centric database to support subsystems-based annotation and metabolic model reconstruction for plant genomes. {PlantSEED} combines {SEED} subsystems technology, first developed for microbial genomes, with refined protein families and biochemical data to assign fully consistent functional annotations to orthologous genes, particularly those encoding primary metabolic pathways. Seamless integration with its parent, the prokaryotic {SEED} database, makes {PlantSEED} a unique environment for cross-kingdom comparative analysis of plant and bacterial genomes. The consistent annotations imposed by {PlantSEED} permit rapid reconstruction and modeling of primary metabolism for all plant genomes in the database. This feature opens the unique possibility of model-based assessment of the completeness and accuracy of gene annotation and thus allows computational identification of genes and pathways that are restricted to certain genomes or need better curation. We demonstrate the {PlantSEED} system by producing consistent annotations for 10 reference genomes. We also produce a functioning metabolic model for each genome, gapfilling to identify missing annotations and proposing gene candidates for missing annotations. Models are built around an extended biomass composition representing the most comprehensive published to date. To our knowledge, our models are the first to be published for seven of the genomes analyzed.},
added-at = {2018-12-02T16:09:07.000+0100},
author = {Seaver, Samuel M. and Gerdes, Svetlana and Frelin, Oc\'{e}ane and Lerma-Ortiz, Claudia and Bradbury, Louis M. and Zallot, R\'{e}mi and Hasnain, Ghulam and Niehaus, Thomas D. and El Yacoubi, Basma and Pasternak, Shiran and Olson, Robert and Pusch, Gordon and Overbeek, Ross and Stevens, Rick and de Cr\'{e}cy-Lagard, Val\'{e}rie and Ware, Doreen and Hanson, Andrew D. and Henry, Christopher S.},
biburl = {https://www.bibsonomy.org/bibtex/21286ef84df0d37cb195e4567fb5c6227/karthikraman},
citeulike-article-id = {13227502},
citeulike-linkout-0 = {http://dx.doi.org/10.1073/pnas.1401329111},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/24927599},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=24927599},
day = 9,
doi = {10.1073/pnas.1401329111},
interhash = {b48d96ef544fe7ea0f50b6f725c2dc49},
intrahash = {1286ef84df0d37cb195e4567fb5c6227},
issn = {1091-6490},
journal = {Proceedings of the National Academy of Sciences of the United States of America},
keywords = {database metabolic-networks plants reconstruction},
month = jun,
pmid = {24927599},
posted-at = {2014-06-16 06:25:59},
priority = {2},
timestamp = {2018-12-02T16:09:07.000+0100},
title = {High-throughput comparison, functional annotation, and metabolic modeling of plant genomes using the {PlantSEED} resource.},
url = {http://dx.doi.org/10.1073/pnas.1401329111},
year = 2014
}