{"corpus_id":29366884,"paper_sha":"fba84b16c8581ffb830900b079f2e922c16dcd19","doi":"10.1155/2017/4740354","arxiv_id":null,"pmid":29250541,"pmcid":"5698827","mag_id":2767445485,"dblp_id":null,"acl_id":null,"title":"Gene Prediction in Metagenomic Fragments with Deep Learning","year":2017,"publication_date":"2017-11-08","venue":"BioMed Research International","journal":{"name":"BioMed Research International","pages":null,"volume":"2017"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle"],"pubmed_pub_types":["Journal Article"],"s2_fields_of_study":["Biology","Medicine","Computer Science"],"reference_count":60,"citation_count":27,"influential_citation_count":1,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":[{"d":"Bacteria","mj":false,"qs":[{"q":"classification","mj":false,"ui":"Q000145"},{"q":"genetics","mj":true,"ui":"Q000235"}],"ui":"D001419"},{"d":"Databases, Genetic","mj":false,"ui":"D030541"},{"d":"Genes, Bacterial","mj":false,"qs":[{"q":"genetics","mj":true,"ui":"Q000235"}],"ui":"D005798"},{"d":"Machine Learning","mj":true,"ui":"D000069550"},{"d":"Metagenomics","mj":false,"qs":[{"q":"methods","mj":true,"ui":"Q000379"}],"ui":"D056186"},{"d":"Models, Statistical","mj":false,"ui":"D015233"},{"d":"Sequence Analysis, DNA","mj":false,"qs":[{"q":"methods","mj":true,"ui":"Q000379"}],"ui":"D017422"}],"chemicals":null,"comments_corrections":null,"source_flags":5,"s2_open_access_pdf_url":"http://downloads.hindawi.com/journals/bmri/2017/4740354.pdf","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/fba84b16c8581ffb830900b079f2e922c16dcd19","s2_open_access_license":"CCBY","s2_open_access_status":"GOLD","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Next generation sequencing technologies used in metagenomics yield numerous sequencing fragments which come from thousands of different species. Accurately identifying genes from metagenomics fragments is one of the most fundamental issues in metagenomics. In this article, by fusing multifeatures (i.e., monocodon usage, monoamino acid usage, ORF length coverage, and Z-curve features) and using deep stacking networks learning model, we present a novel method (called Meta-MFDL) to predict the metagenomic genes. The results with 10 CV and independent tests show that Meta-MFDL is a powerful tool for identifying genes from metagenomic fragments.","claims":[{"public_id":"cl_246c3f90755b92627128a5f3ada1ddf6","status":"active","text":"Meta-MFDL combines monocodon usage, monoamino acid usage, ORF length coverage, and Z-curve features in a deep stacking networks learning model for metagenomic gene prediction.","confidence":0.98,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_246c3f90755b92627128a5f3ada1ddf6"},{"public_id":"cl_c07ef5ab8bd69e2a07a7380b9a868ad4","status":"active","text":"Meta-MFDL is presented as a novel method for predicting genes from metagenomic fragments.","confidence":0.97,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_c07ef5ab8bd69e2a07a7380b9a868ad4"},{"public_id":"cl_1325557adb2405fe075ff2261bb233c6","status":"active","text":"Results from 10-fold cross-validation and independent tests indicate that Meta-MFDL is a powerful tool for identifying genes from metagenomic fragments.","confidence":0.95,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_1325557adb2405fe075ff2261bb233c6"}],"concepts":[{"public_id":"co_11959e650bc3edfc8dc7f3c10ef5a4cb","status":"active","name":"monoamino acid usage","description":"A feature capturing the frequency or distribution of individual amino acids in a sequence.","types":["feature"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_11959e650bc3edfc8dc7f3c10ef5a4cb"},{"public_id":"co_4d71016b0e832c9435a67f942be58a41","status":"active","name":"deep stacking networks learning model","description":"A deep learning architecture that stacks multiple learning modules for classification or prediction.","types":["model"],"aliases":["deep stacking networks","DSN"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_4d71016b0e832c9435a67f942be58a41"},{"public_id":"co_8873438aef7f7d21139679efdcf57f69","status":"active","name":"metagenomic fragments","description":"Sequencing fragments obtained from mixed microbial communities in metagenomic data.","types":["data"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_8873438aef7f7d21139679efdcf57f69"},{"public_id":"co_899541060c45a6c0c781e62bf3868700","status":"active","name":"independent tests","description":"Separate test evaluations conducted on data not used for model training.","types":["evaluation protocol"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_899541060c45a6c0c781e62bf3868700"},{"public_id":"co_9d4a530637fdc80841b4123165fb3a9c","status":"active","name":"10 CV","description":"Ten-fold cross-validation used to evaluate the prediction method.","types":["evaluation protocol"],"aliases":["10-fold cross-validation"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_9d4a530637fdc80841b4123165fb3a9c"},{"public_id":"co_9ea00b794209086944b1ebcd37ab234a","status":"active","name":"monocodon usage","description":"A feature capturing the frequency or distribution of single codons in a sequence.","types":["feature"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_9ea00b794209086944b1ebcd37ab234a"},{"public_id":"co_a4dfcb6dbd25f5c13d440b5799c632b4","status":"active","name":"multifeatures","description":"A combined set of sequence-derived features used as input to the prediction model.","types":["feature set"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_a4dfcb6dbd25f5c13d440b5799c632b4"},{"public_id":"co_b41cf95f088f0db84a915d11914af22f","status":"active","name":"Z-curve features","description":"Sequence descriptors derived from the Z-curve representation of nucleic acids.","types":["feature"],"aliases":["Z curve features","Z-curve"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_b41cf95f088f0db84a915d11914af22f"},{"public_id":"co_b76756ebd02a8a1a2905edc0ce98a7bb","status":"active","name":"gene prediction","description":"The task of identifying gene-containing regions in sequence data.","types":["task"],"aliases":["gene identification"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_b76756ebd02a8a1a2905edc0ce98a7bb"},{"public_id":"co_e80558ab514df003549090b5c53912c7","status":"active","name":"ORF length coverage","description":"A feature based on the length coverage of open reading frames in sequence fragments.","types":["feature"],"aliases":["open reading frame length coverage"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_e80558ab514df003549090b5c53912c7"},{"public_id":"co_efcee9c87d6473e011d385f37b72ae4d","status":"active","name":"Meta-MFDL","description":"A deep-learning-based method for predicting genes from metagenomic fragments using multiple sequence-derived features.","types":["method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_efcee9c87d6473e011d385f37b72ae4d"}],"external_ids":{"DOI":"10.1155/2017/4740354","ArXiv":null,"PubMed":29250541,"PubMedCentral":"5698827","MAG":2767445485,"DBLP":null,"ACL":null},"open_access":{"is_open_access":true,"pdf_url":"http://downloads.hindawi.com/journals/bmri/2017/4740354.pdf","landing_url":"https://www.semanticscholar.org/paper/fba84b16c8581ffb830900b079f2e922c16dcd19","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"CCBY","status":"GOLD","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":5},"paper_id":632278,"paper_uid":"b9248abf-ad0a-49b0-b1ea-4094a1c20892","canonical_identity":{"paper_id":632278,"paper_uid":"b9248abf-ad0a-49b0-b1ea-4094a1c20892","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/29366884"}