{"corpus_id":26799716,"paper_sha":"b39bf5ae2979c346c3b6d918a809b6c9af5ab02f","doi":"10.1101/GR.1304504","arxiv_id":null,"pmid":14962984,"pmcid":"PMC353230","mag_id":2101199515,"dblp_id":null,"acl_id":null,"title":"The multiassembly problem: reconstructing multiple transcript isoforms from EST fragment mixtures.","year":2004,"publication_date":"2004-03-01","venue":"Genome Research","journal":{"name":"Genome research","pages":"\n          426-41\n        ","volume":"14 3"},"journal_issn":null,"journal_title":null,"publication_types":["Study","JournalArticle"],"pubmed_pub_types":["Comparative Study","Journal Article","Research Support, U.S. Gov't, Non-P.H.S.","Research Support, U.S. Gov't, P.H.S.","Validation Study"],"s2_fields_of_study":["Biology","Medicine","Computer Science"],"reference_count":75,"citation_count":98,"influential_citation_count":4,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":[{"d":"Algorithms","mj":false,"ui":"D000465"},{"d":"Alternative Splicing","mj":false,"qs":[{"q":"genetics","mj":false,"ui":"Q000235"}],"ui":"D017398"},{"d":"Computational Biology","mj":false,"qs":[{"q":"methods","mj":false,"ui":"Q000379"},{"q":"statistics & numerical data","mj":false,"ui":"Q000706"}],"ui":"D019295"},{"d":"Databases, Genetic","mj":false,"qs":[{"q":"statistics & numerical data","mj":false,"ui":"Q000706"}],"ui":"D030541"},{"d":"Exons","mj":false,"qs":[{"q":"genetics","mj":false,"ui":"Q000235"}],"ui":"D005091"},{"d":"Expressed Sequence Tags","mj":true,"ui":"D020224"},{"d":"Human Genome Project","mj":false,"ui":"D016045"},{"d":"Humans","mj":false,"ui":"D006801"},{"d":"Protein Biosynthesis","mj":false,"qs":[{"q":"genetics","mj":false,"ui":"Q000235"}],"ui":"D014176"},{"d":"Protein Isoforms","mj":false,"qs":[{"q":"genetics","mj":false,"ui":"Q000235"}],"ui":"D020033"},{"d":"Transcobalamins","mj":false,"qs":[{"q":"genetics","mj":true,"ui":"Q000235"}],"ui":"D014155"},{"d":"Transcription, Genetic","mj":false,"qs":[{"q":"genetics","mj":true,"ui":"Q000235"}],"ui":"D014158"}],"chemicals":[{"n":"Protein Isoforms","ui":"D020033","reg":"0"},{"n":"Transcobalamins","ui":"D014155","reg":"0"}],"comments_corrections":null,"source_flags":5,"s2_open_access_pdf_url":"https://genome.cshlp.org/content/14/3/426.full.pdf","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/b39bf5ae2979c346c3b6d918a809b6c9af5ab02f","s2_open_access_license":"CCBYNC","s2_open_access_status":"HYBRID","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":"Recent evidence of abundant transcript variation (e.g., alternative splicing, alternative initiation, alternative polyadenylation) in complex genomes indicates that cataloging the complete set of transcripts from an organism is an important project. One challenge is the fact that most high-throughput experimental methods for characterizing transcripts (such as EST sequencing) give highly detailed information about short fragments of transcripts or protein products, instead of a complete characterization of a full-length form. We analyze this \"multiassembly problem\"-reconstructing the most likely set of full-length isoform sequences from a mixture of EST fragment data-and present a graph-based algorithm for solving it. In a variety of tests, we demonstrate that this algorithm deals appropriately with coupling of distinct alternative splicing events, increasing fragmentation of the input data and different types of transcript variation (such as alternative splicing, initiation, polyadenylation, and intron retention). To test the method's performance on pure fragment (EST) data, we removed all mRNA sequences, and found it produced no errors in 40 cases tested. Using this algorithm, we have constructed an Alternatively Spliced Proteins database (ASP) from analysis of human expressed and genomic sequences, consisting of 13,384 protein isoforms of 4422 genes, yielding an average of 3.0 protein isoforms per gene.","claims":[{"public_id":"cl_f196a5876acc339f7cf307c969dfc6e1","status":"active","text":"A graph-based algorithm is presented for reconstructing the most likely set of full-length isoform sequences from a mixture of EST fragment data.","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_f196a5876acc339f7cf307c969dfc6e1"},{"public_id":"cl_c6b0342db295a7f68df5004c34ea8f9d","status":"active","text":"An Alternatively Spliced Proteins database was constructed from human expressed and genomic sequences, containing 13,384 protein isoforms from 4,422 genes and averaging 3.0 protein isoforms per gene.","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_c6b0342db295a7f68df5004c34ea8f9d"},{"public_id":"cl_97c546c68417c4217e68dbb89fb79d6c","status":"active","text":"On pure fragment EST data with all mRNA sequences removed, the method produced no errors in 40 tested cases.","confidence":0.96,"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_97c546c68417c4217e68dbb89fb79d6c"},{"public_id":"cl_18fae60bee0e776e6bec97816a032c60","status":"active","text":"The algorithm handles coupling between distinct alternative splicing events, increasing fragmentation of the input data, and multiple forms of transcript variation.","confidence":0.93,"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_18fae60bee0e776e6bec97816a032c60"}],"concepts":[{"public_id":"co_0d72da0bffd69c8513b9ca141e77f38f","status":"active","name":"protein isoforms","description":"Distinct protein forms encoded by a gene through transcript variation.","types":["biological sequence"],"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_0d72da0bffd69c8513b9ca141e77f38f"},{"public_id":"co_22e5739aa1a2b596c03ecb6efb223472","status":"active","name":"alternative splicing","description":"A form of transcript variation in which exons are joined in different combinations.","types":["transcript variation"],"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_22e5739aa1a2b596c03ecb6efb223472"},{"public_id":"co_2e2479aa6b7ed0fe006997e83d5158d4","status":"active","name":"alternative initiation","description":"A form of transcript variation involving different transcription start sites or initiation points.","types":["transcript variation"],"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_2e2479aa6b7ed0fe006997e83d5158d4"},{"public_id":"co_3a4f22f45d22a927884ace35133b69b3","status":"active","name":"multiassembly problem","description":"The task of reconstructing a likely full-length transcript isoform set from mixed fragment evidence.","types":["problem"],"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_3a4f22f45d22a927884ace35133b69b3"},{"public_id":"co_49b2e683b710322910f504daad35f77c","status":"active","name":"Alternatively Spliced Proteins database","description":"A database of predicted protein isoforms assembled from human expressed and genomic sequence analysis.","types":["database"],"aliases":["ASP"],"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_49b2e683b710322910f504daad35f77c"},{"public_id":"co_4af87c2148354c0281006a4d78f89187","status":"active","name":"alternative polyadenylation","description":"A form of transcript variation involving different polyadenylation sites.","types":["transcript variation"],"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_4af87c2148354c0281006a4d78f89187"},{"public_id":"co_59577c3dad05523b290c6248925bc309","status":"active","name":"intron retention","description":"A form of transcript variation in which an intron remains present in the mature transcript.","types":["transcript variation"],"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_59577c3dad05523b290c6248925bc309"},{"public_id":"co_8143828d5fd3bb984099b59053800891","status":"active","name":"human expressed and genomic sequences","description":"Human transcript and genome sequence sources analyzed to construct the isoform database.","types":["sequence 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_8143828d5fd3bb984099b59053800891"},{"public_id":"co_88ba6269479a12798eb48a1c369ee2cd","status":"active","name":"graph-based algorithm","description":"An algorithm that uses graph structure to infer full-length isoform sequences from fragment data.","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_88ba6269479a12798eb48a1c369ee2cd"},{"public_id":"co_8ab536f1638889afa863a85215b8f283","status":"active","name":"EST fragment data","description":"Expressed sequence tag fragment observations used as partial transcript evidence.","types":["data"],"aliases":["EST data"],"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_8ab536f1638889afa863a85215b8f283"},{"public_id":"co_ae613a0e4dcff6715ce024223860eb8f","status":"active","name":"transcript variation","description":"Differences among transcript forms arising from processes such as splicing, initiation, polyadenylation, or intron retention.","types":["biological phenomenon"],"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_ae613a0e4dcff6715ce024223860eb8f"},{"public_id":"co_ec1f9efae34ff5210cd032800b60f40f","status":"active","name":"mRNA sequences","description":"Full-length messenger RNA sequences used as reference sequence information.","types":["sequence data"],"aliases":["mRNA"],"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_ec1f9efae34ff5210cd032800b60f40f"}],"external_ids":{"DOI":"10.1101/GR.1304504","ArXiv":null,"PubMed":14962984,"PubMedCentral":"PMC353230","MAG":2101199515,"DBLP":null,"ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://genome.cshlp.org/content/14/3/426.full.pdf","landing_url":"https://www.semanticscholar.org/paper/b39bf5ae2979c346c3b6d918a809b6c9af5ab02f","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"CCBYNC","status":"HYBRID","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":637457,"paper_uid":"d13073cb-5f09-479c-a10b-6386a4ee3960","canonical_identity":{"paper_id":637457,"paper_uid":"d13073cb-5f09-479c-a10b-6386a4ee3960","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/26799716"}