{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:24555089", "kind": "science-record", "revision": 6, "content_hash": "sha256:dc769f2b6800993ee31056ea49a13325ea1185a63855815a84aafec1d4147969", "created_at": "2026-11-01T15:40:04Z", "updated_at": "2026-11-01T21:19:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Thousands of exon skipping events differentiate among splicing patterns in sixteen human tissues.", "doi": "10.12688/f1000research.2-188.v2", "pmid": "24555089", "authors": ["Liliana Florea", "Li Song", "Steven L Salzberg"], "journal": "F1000Research", "year": 2013, "abstract": "Alternative splicing is widely recognized for its roles in regulating genes and creating gene diversity. However, despite many efforts, the repertoire of gene splicing variation is still incompletely characterized, even in humans. Here we describe a new computational system, ASprofile, and its application to RNA-seq data from Illumina's Human Body Map project (>2.5 billion reads). Using the system, we identified putative alternative splicing events in 16 different human tissues, which provide a dynamic picture of splicing variation across the tissues. We detected 26,989 potential exon skipping events representing differences in splicing patterns among the tissues. A large proportion of the events (>60%) were novel, involving new exons (~3000), new introns (~16000), or both. When tracing these events across the sixteen tissues, only a small number (4-7%) appeared to be differentially expressed ('switched') between two tissues, while 30-45% showed little variation, and the remaining 50-65% were not present in one or both tissues compared. Novel exon skipping events appeared to be slightly less variable than known events, but were more tissue-specific. Our study represents the first effort to build a comprehensive catalog of alternative splicing in normal human tissues from RNA-seq data, while providing insights into the role of alternative splicing in shaping tissue transcriptome differences. The catalog of events and the ASprofile software are freely available from the Zenodo repository ( http://zenodo.org/record/7068; doi: 10.5281/zenodo.7068) and from our web site http://ccb.jhu.edu/software/ASprofile.", "claims": [{"id": "claim-method", "statement": "Novel events are depleted in ‘switches’ compared to known events (test of homogeneity, df=2, chi-square 274.7, p = 0.0).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:24555089", "locator": "sections[20] \"S7. Reproducibility of exon skipping event discovery with other assembly methods\" paragraph 10", "quote": "Novel events are depleted in ‘switches’ compared to known events (test of homogeneity, df=2, chi-square 274.7, p = 0.0)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "These data are publicly available as the Illumina Human Body Map project (EMBL accession ENA-ERP000546; ArrayExpress accession: E-MTAB-513; http://www.ebi.ac.uk/arrayexpress/browse.html?keywords=E-MTAB-513&expandefo=on).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:24555089", "locator": "sections[3] \"A global view of alternative splicing in the 16 tissues\" paragraph 2", "quote": "These data are publicly available as the Illumina Human Body Map project (EMBL accession ENA-ERP000546; ArrayExpress accession: E-MTAB-513; http://www.ebi.ac.uk/arrayexpress/browse.html?keywords=E-MTAB-513&expandefo=on)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:24555089"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:E-MTAB-513"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:E-MTAB-513"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:24555089", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12688/f1000research.2-188.v2", "sha256": "sha256:a4e3691420db92594113397804bdd694b8328bdf3a8ba3c350eace9fe174e20b", "bytes": 53995, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12688/f1000research.2-188.v2", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3892928", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-513", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=E-MTAB-513", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-513", "version": null, "note": "These data are publicly available as the Illumina Human Body Map project (EMBL accession ENA-ERP000546; ArrayExpress accession: E-MTAB-513; http://www.ebi.ac.uk/arrayexpress/browse.html?keywords=E-MTAB-513&expandefo=on).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "These data are publicly available as the Illumina Human Body Map project (EMBL accession ENA-ERP000546; ArrayExpress accession: E-MTAB-513; http://www.ebi.ac.uk/arrayexpress/browse.html?keywords=E-MTAB-513&expandefo=on).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:29:01Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:24555089:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8c3a4327c55a372f8bad6c575ea3a84333abd1578c6228401cbc3d8a19699e01", "bytes": 1546, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#TS1", "version": null, "note": "Total number of RNA-seq reads from each of 16 human tissues.\"Mapped\" refers to the number of reads that had at least one and no more than ten alignments to the genome.", "structure": {"pmcid": "PMC3892928", "section_index": 17, "section_title": "Supplementary materials", "row_count": 18, "column_count": 4}, "table": {"label": "Table S1.", "caption": "Total number of RNA-seq reads from each of 16 human tissues.\"Mapped\" refers to the number of reads that had at least one and no more than ten alignments to the genome.", "rows": [["Tissue", "Reads", "Mapped", "Properly paired"], ["Adipose", "154,600,144", "138,872,338 (88.9%)", "76,196,138 (49.3%)"], ["Adrenal", "148,945,742", "133,883,290 (89.9%)", "78,356,524 (52.6%)"], ["Brain", "147,026,094", "134,791,012 (91.7%)", "87,153,922 (59.3%)"], ["Breast", "151,724,430", "135,987,146 (89.6%)", "78,111,468 (51.5%)"], ["Colon", "164,874,886", "150,966,150 (91.6%)", "83,026,962 (50.4%)"], ["Heart", "165,837,568", "155,841,749 (94.0%)", "102,600,102 (61.9%)"], ["Kidney", "160,794,674", "143,888,751 (89.5%)", "84,285,000 (52.4%)"], ["Liver", "160,097,246", "149,817,522 (93.6%)", "94,840,760 (59.2%)"], ["Lung", "158,593,810", "144,039,113 (90.8%)", "90,728,136 (57.2%)"], ["Lymph", "164,156,314", "146,044,267 (89.0%)", "89,437,520 (54.5%)"], ["Ovary", "161,892,520", "147,588,256 (91.2%)", "81,207,460 (50.2%)"], ["Prostate", "164,668,152", "150,477,990 (92.2%)", "94,643,390 (57.5%)"], ["Skeletal muscle", "164,222,278", "151,847,711 (91.6%)", "95,036,702 (57.9%)"], ["Testes", "163,672,398", "149,727,704 (91.5%)", "83,729,866 (51.2%)"], ["Thyroid", "163,825,774", "148,942,521 (90.9%)", "80,513,364 (49.1%)"], ["White blood cell", "162,434,296", "149,167,286 (91.8%)", "87,806,618 (54.1%)"], ["Total", "2,557,366,326", "2,333,252,527 (91.2%)", "1,387,673,932 (54.3%)"]], "row_count": 18, "column_count": 4, "numeric_cells": 51, "header_rows": 1, "locator": "section[17]/table-wrap[1]#TS1"}}, {"id": "asset:table:pmid:24555089:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2bbc6dd107dc4d59be066f4a0cfaf20e57cf1afbcceeaa2549d307ad7659ebe3", "bytes": 534, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#TS2", "version": null, "note": "Performance of four transcript assembly programs in capturing exon skipping events from simulated RNA-seq data. Recall = TP/(TP+FN), Precision = TP/(TP+FP).", "structure": {"pmcid": "PMC3892928", "section_index": 18, "section_title": "S2. Evaluation of transcript assemblers in detecting exon skipping (ES) events", "row_count": 6, "column_count": 5}, "table": {"label": "Table S2.", "caption": "Performance of four transcript assembly programs in capturing exon skipping events from simulated RNA-seq data. Recall = TP/(TP+FN), Precision = TP/(TP+FP).", "rows": [["Exon skipping (ES)"], ["", "Predicted", "Correct", "Recall", "Precision"], ["Cufflinks", "632", "561", "0.42", "0.89"], ["IsoCEM", "940", "496", "0.37", "0.53"], ["SLIDE", "3022", "311", "0.23", "0.10"], ["Scripture", "1724", "1045", "0.78", "0.61"]], "row_count": 6, "column_count": 5, "numeric_cells": 16, "header_rows": 2, "locator": "section[18]/table-wrap[1]#TS2"}}, {"id": "asset:table:pmid:24555089:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aeeb0bd53234b4a1458e70f3ea88078af804ab6855eea4c94c7ea7b063376472", "bytes": 1637, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[2]#TS3", "version": null, "note": "Overview of results from the Cufflinks transcript assembly process.Cufflinks assembles short reads aligned to a genome into a set of transcript fragments (‘transfrags’ or ‘transcripts’ or ‘txpts’, below), grouped by locus (‘gene’).", "structure": {"pmcid": "PMC3892928", "section_index": 18, "section_title": "S2. Evaluation of transcript assemblers in detecting exon skipping (ES) events", "row_count": 17, "column_count": 8}, "table": {"label": "Table S3.", "caption": "Overview of results from the Cufflinks transcript assembly process.Cufflinks assembles short reads aligned to a genome into a set of transcript fragments (‘transfrags’ or ‘transcripts’ or ‘txpts’, below), grouped by locus (‘gene’).", "rows": [["Tissue", "Genes*", "Multi-exon", "Txpts/gene †", "Transfrags", "Single exon", "Multiexon", "Exons/txpt ‡"], ["Adrenal", "307,088", "23,135", "2.0", "357,774", "311,766", "46,008", "5.6"], ["Adipose", "134,348", "21,793", "1.5", "158,142", "126,207", "31,935", "6"], ["Brain", "239,971", "24,435", "1.8", "218,818", "238,497", "43,321", "6"], ["Breast", "191,620", "23,553", "1.6", "222,525", "185,869", "36,656", "5.5"], ["Colon", "116,723", "23,503", "1.3", "133,953", "103,071", "30,882", "5.1"], ["Heart", "149,951", "21,537", "1.5", "177,059", "144,829", "32,230", "6.5"], ["Kidney", "171,862", "24,000", "1.5", "197,742", "162,910", "34,832", "5.4"], ["Liver", "95,495", "21,228", "1.3", "110,116", "82,732", "27,384", "5"], ["Lung", "172,439", "25,176", "1.4", "194,640", "159,123", "35,517", "4.9"], ["Lymph", "188,709", "23,766", "1.5", "216,692", "179,938", "36,754", "4.9"], ["Ovary", "210,035", "22,949", "1.8", "252,081", "210,391", "41,690", "6.5"], ["Prostate", "161,526", "24,584", "1.4", "186,159", "150,732", "35,427", "5.5"], ["Skel_muscle", "95,684", "19,695", "1.2", "105,209", "82,359", "22,850", "4.7"], ["Testes", "220,459", "29,546", "1.6", "259,043", "212,894", "46,169", "5.9"], ["Thyroid", "187,169", "23,357", "1.8", "224,647", "184,751", "39,896", "6.3"], ["White_blood", "98,731", "19,943", "1.3", "113,656", "88,538", "25,118", "5.5"]], "row_count": 17, "column_count": 8, "numeric_cells": 112, "header_rows": 1, "locator": "section[18]/table-wrap[2]#TS3"}}, {"id": "asset:table:pmid:24555089:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:539dd38e336f162f897dfe70e84656c5f0e019d83b1a00a0ba6ec0810bcf8a26", "bytes": 1473, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[3]#TS4", "version": null, "note": "Novel and known gene splice forms in the sixteen tissues, determined by comparison to the ENSEMBL v.61 annotation database using the program Cuffcompare.Cuffcompare compares each predicted transcript’s intron chain against those of the reference transcripts and classifies the transfrag as: ‘equal’ to a reference transcript, if their intron chains are identical; ‘contained’, if included in a reference transcript’s; or as a ‘new splice form’, if the intron chain has at least one splice junction in common with the reference transcripts (n.b., other Cuffcompare codes are not relevant and were omitted).", "structure": {"pmcid": "PMC3892928", "section_index": 18, "section_title": "S2. Evaluation of transcript assemblers in detecting exon skipping (ES) events", "row_count": 18, "column_count": 4}, "table": {"label": "Table S4.", "caption": "Novel and known gene splice forms in the sixteen tissues, determined by comparison to the ENSEMBL v.61 annotation database using the program Cuffcompare.Cuffcompare compares each predicted transcript’s intron chain against those of the reference transcripts and classifies the transfrag as: ‘equal’ to a reference transcript, if their intron chains are identical; ‘contained’, if included in a reference transcript’s; or as a ‘new splice form’, if the intron chain has at least one splice junction in common with the reference transcripts (n.b., other Cuffcompare codes are not relevant and were omitted).", "rows": [["Set", "Comparison to ENSEMBL v.61"], ["", "Full-length (Equal)", "Partial (Contained)", "New splice forms"], ["Adrenal", "5,705", "22,613", "22,592"], ["Adipose", "5,593", "22,293", "11,233"], ["Brain", "6,497", "20,673", "19,329"], ["Breast", "5,665", "24,190", "13,665"], ["Colon", "4,689", "28,715", "9,310"], ["Heart", "6,103", "17,614", "11,701"], ["Kidney", "5,501", "26,615", "11,775"], ["Liver", "4,483", "24,563", "7,692"], ["Lung", "4,958", "33,735", "12,346"], ["Lymph", "4,574", "33,682", "14,364"], ["Ovary", "7,017", "18,667", "18,048"], ["Prostate", "5,673", "27,183", "12,470"], ["Skel_muscle", "3,318", "33,999", "4,999"], ["Testes", "7,077", "23,648", "17,306"], ["Thyroid", "6,487", "21,098", "16,667"], ["White_blood", "4,568", "25,004", "6,533"]], "row_count": 18, "column_count": 4, "numeric_cells": 49, "header_rows": 2, "locator": "section[18]/table-wrap[3]#TS4"}}, {"id": "asset:table:pmid:24555089:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:de8ae29a5d8bfc0c7622fa2fe9a12f62d2c706920c9680f83377140fef0fddd5", "bytes": 631, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[4]#TS5", "version": null, "note": "Numbers of candidate alternative splicing events found in the Illumina Human Body Map data, by type.", "structure": {"pmcid": "PMC3892928", "section_index": 18, "section_title": "S2. Evaluation of transcript assemblers in detecting exon skipping (ES) events", "row_count": 8, "column_count": 3}, "table": {"label": "Table S5.", "caption": "Numbers of candidate alternative splicing events found in the Illumina Human Body Map data, by type.", "rows": [["Event type", "Code", "Count"], ["Exon skipping (single exon)", "SKIP", "26,989"], ["Exon skipping (multiple exons)", "MSKIP", "13,814"], ["Alternative 5´ terminal exon*", "TSS", "97,399"], ["Alternative 3´ terminal exon*", "TTS", "45,609"], ["Intron retention (single intron)", "IR", "16,671"], ["Intron retention (multiple introns)", "MIR", "2,636"], ["Alternative exon boundaries", "AE", "22,767"]], "row_count": 8, "column_count": 3, "numeric_cells": 9, "header_rows": 1, "locator": "section[18]/table-wrap[4]#TS5"}}, {"id": "asset:table:pmid:24555089:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e90467926691c404cc961fde0507e217184f98799ad28b2d195d2a7ba0c96970", "bytes": 1441, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#TS6", "version": null, "note": "Comparison of co-located ES events among the 26,989 events discovered from the Illumina Human Body Map data and the 25,114 exon skipping (ES) events extracted from the Ensembl v.61 annotations. All – all events co-located within V bp; Loci – clusters of co-located events (each with a representative ‘anchor’); Var ( =All-Loci) – variations (not including ‘anchors’), representing potential mapping artifacts.", "structure": {"pmcid": "PMC3892928", "section_index": 19, "section_title": "S6. Potential effects of imprecise splice junctions on the exon skipping (ES) estimates", "row_count": 12, "column_count": 11}, "table": {"label": "Table S6.", "caption": "Comparison of co-located ES events among the 26,989 events discovered from the Illumina Human Body Map data and the 25,114 exon skipping (ES) events extracted from the Ensembl v.61 annotations. All – all events co-located within V bp; Loci – clusters of co-located events (each with a representative ‘anchor’); Var ( =All-Loci) – variations (not including ‘anchors’), representing potential mapping artifacts.", "rows": [["V", "Cufflinks (26,989 events)", "Ensembl 61 (25,114 events)", "% Diff", "Potential artifacts"], ["All", "Loci", "Var.", "%", "All", "Loci", "Var.", "%"], ["1", "647", "300", "347", "1.29", "90", "45", "45", "0.18", "1.10", "298"], ["2", "1271", "585", "686", "2.54", "143", "71", "72", "0.29", "2.26", "608"], ["3", "2394", "1153", "1241", "4.60", "530", "262", "268", "1.07", "3.53", "953"], ["4", "3079", "1476", "1603", "5.94", "724", "359", "365", "1.45", "4.49", "1210"], ["5", "3507", "1685", "1822", "6.75", "839", "412", "427", "1.70", "5.05", "1363"], ["6", "3803", "1832", "1971", "7.30", "894", "440", "454", "1.81", "5.49", "1483"], ["7", "3923", "1890", "2033", "7.53", "930", "456", "474", "1.89", "5.65", "1523"], ["8", "4003", "1929", "2074", "7.68", "959", "471", "488", "1.94", "5.74", "1549"], ["9", "4126", "1991", "2135", "7.91", "1020", "502", "518", "2.06", "5.85", "1578"], ["10", "4192", "2057", "2135", "7.91", "1068", "500", "568", "2.26", "5.65", "1524"]], "row_count": 12, "column_count": 11, "numeric_cells": 112, "header_rows": 2, "locator": "section[19]/table-wrap[1]#TS6"}}, {"id": "asset:table:pmid:24555089:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:673b401b227db41b41881138c6afa756e32b0d87b2ea333577ba5de274d5fd35", "bytes": 599, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#TS7", "version": null, "note": "Reproducibility of exon skipping (ES) discovery from transcripts assembled with different methods, and robustness with varying cutoffs (V bp) for the margin of error when comparing exon and intron boundaries.", "structure": {"pmcid": "PMC3892928", "section_index": 20, "section_title": "S7. Reproducibility of exon skipping event discovery with other assembly methods", "row_count": 6, "column_count": 5}, "table": {"label": "Table S7.", "caption": "Reproducibility of exon skipping (ES) discovery from transcripts assembled with different methods, and robustness with varying cutoffs (V bp) for the margin of error when comparing exon and intron boundaries.", "rows": [["Method", "ES events", "Found by other methods"], ["V=0", "V=5", "V=10"], ["Cufflinks", "2,934", "2,471", "2,480", "2,482"], ["IsoCEM", "1,486", "1,361", "1,364", "1,365"], ["SLIDE", "1,418", "860", "884", "895"], ["Scripture", "4,770", "2,984", "3,072", "3,096"]], "row_count": 6, "column_count": 5, "numeric_cells": 19, "header_rows": 2, "locator": "section[20]/table-wrap[1]#TS7"}}, {"id": "asset:table:pmid:24555089:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e9862890d9e7581d352da420851dca796ab58cdfb77b7b41222025c3f5e2a69b", "bytes": 608, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[2]#TS9", "version": null, "note": "Summary of novel features by comparison to four annotation databases (CCDS, UCSC Genes, Ensembl v. 61, and H-DBAS).Exon and intron boundaries were compared allowing for a small difference (up to V=0, 5 and 10 bp). Values in bold are those reported in the main text.", "structure": {"pmcid": "PMC3892928", "section_index": 20, "section_title": "S7. Reproducibility of exon skipping event discovery with other assembly methods", "row_count": 5, "column_count": 4}, "table": {"label": "Table S9.", "caption": "Summary of novel features by comparison to four annotation databases (CCDS, UCSC Genes, Ensembl v. 61, and H-DBAS).Exon and intron boundaries were compared allowing for a small difference (up to V=0, 5 and 10 bp). Values in bold are those reported in the main text.", "rows": [["Novel feature", "V=0", "V=5", "V=10"], ["Exon+Intron", "2,518", "1,430", "1,214"], ["Exon only", "1,954", "1,484", "1,368"], ["Intron only", "13,531", "14,528", "14,726"], ["Known", "8,986", "9,547", "9,681"]], "row_count": 5, "column_count": 4, "numeric_cells": 15, "header_rows": 1, "locator": "section[20]/table-wrap[2]#TS9"}}, {"id": "asset:table:pmid:24555089:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:505d507ac8ab134a7d19a16144a2fd4fc32f0c4a7b6c4688b402dcabb6cfe0f5", "bytes": 932, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[3]#TS11", "version": null, "note": "Exon skipping events expressed in each tissue sample, and number/percentage of these events that have only one expressed isoform in the sample.", "structure": {"pmcid": "PMC3892928", "section_index": 20, "section_title": "S7. Reproducibility of exon skipping event discovery with other assembly methods", "row_count": 17, "column_count": 3}, "table": {"label": "Table S11.", "caption": "Exon skipping events expressed in each tissue sample, and number/percentage of these events that have only one expressed isoform in the sample.", "rows": [["Tissue", "Events", "Single variant"], ["Adrenal", "16,736", "13,403 (80.1%)"], ["Adipose", "16,045", "13,819 (86.1%)"], ["Brain", "17,415", "13,865 (79.6%)"], ["Breast", "16,087", "13,870 (86.2%)"], ["Colon", "13,802", "12,464 (90.3%)"], ["Heart", "17,048", "14,769 (86.6%)"], ["Kidney", "15,319", "13,785 (90.0%)"], ["Liver", "12,390", "11,388 (91.9%)"], ["Lung", "13,736", "12,310 (89.6%)"], ["Lymph", "13,393", "11,765 (87.8%)"], ["Ovary", "19,209", "15,052 (78.4%)"], ["Prostate", "16,011", "14,316 (89.4%)"], ["Skel_muscle", "10,160", "9,614 (94.6%)"], ["Testes", "19,124", "15,127 (79.1%)"], ["Thyroid", "18,689", "14,362 (76.8%)"], ["White_blood", "12,954", "12,017 (92.8%)"]], "row_count": 17, "column_count": 3, "numeric_cells": 32, "header_rows": 1, "locator": "section[20]/table-wrap[3]#TS11"}}, {"id": "asset:table:pmid:24555089:10", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8d8e3145cfef761e10f5b7d1eb2151521cc5e4901ddcb3603205dbdf1caaa3d3", "bytes": 522, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[4]#TS13", "version": null, "note": "Variability of novel exon skipping events compared to known events.Novel events are depleted in ‘switches’ compared to known events (test of homogeneity, df=2, chi-square 274.7, p = 0.0).", "structure": {"pmcid": "PMC3892928", "section_index": 20, "section_title": "S7. Reproducibility of exon skipping event discovery with other assembly methods", "row_count": 4, "column_count": 5}, "table": {"label": "Table S13.", "caption": "Variability of novel exon skipping events compared to known events.Novel events are depleted in ‘switches’ compared to known events (test of homogeneity, df=2, chi-square 274.7, p = 0.0).", "rows": [["Events", "Stable", "Variable", "Switches", "Total"], ["Novel", "1,788", "5,334", "10,320", "17,442"], ["Known", "688", "2,241", "6,618", "9,547"], ["Total", "2,476", "7,575", "16,938", "26,989"]], "row_count": 4, "column_count": 5, "numeric_cells": 12, "header_rows": 1, "locator": "section[20]/table-wrap[4]#TS13"}}], "gaps": ["asset:data:geo:E-MTAB-513 not downloaded", "asset:data:geo:E-MTAB-513 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Novel events are depleted in ‘switches’ compared to known events (test of homogeneity, df=2, chi-square 274.7, p = 0.0)."}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["chi_square_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: chi_square."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["E-MTAB-513"], "resolved_accessions": ["E-MTAB-513"], "statements": ["These data are publicly available as the Illumina Human Body Map project (EMBL accession ENA-ERP000546; ArrayExpress accession: E-MTAB-513; http://www.ebi.ac.uk/arrayexpress/browse.html?keywords=E-MTAB-513&expandefo=on)."], "basis": "The paper names E-MTAB-513 in ArrayExpress and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["chi_square_test"], "assets": ["source:pmid:24555089", "data:geo:E-MTAB-513", "asset:table:pmid:24555089:1", "asset:table:pmid:24555089:2", "asset:table:pmid:24555089:3", "asset:table:pmid:24555089:4", "asset:table:pmid:24555089:5", "asset:table:pmid:24555089:6", "asset:table:pmid:24555089:7", "asset:table:pmid:24555089:8", "asset:table:pmid:24555089:9", "asset:table:pmid:24555089:10"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-513"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:04:07Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 38886, "completion_tokens": 1698, "cached_tokens": 38486}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:24555089", "type": "paper", "label": "pmid:24555089"}, {"id": "source:pmid:24555089", "type": "manuscript", "label": "PMID 24555089 full text"}, {"id": "data:geo:E-MTAB-513", "type": "dataset", "label": "GEO E-MTAB-513"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:24555089", "type": "paper", "label": "pmid:24555089"}, {"id": "source:pmid:24555089", "type": "manuscript", "label": "PMID 24555089 full text"}, {"id": "data:geo:E-MTAB-513", "type": "dataset", "label": "GEO E-MTAB-513"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-24555089", "type": "extraction", "used": ["source:pmid:24555089"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-513", "type": "accession_resolution", "used": ["data:geo:E-MTAB-513"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:24555089", "parent_hash": "sha256:2014e6a00bc88f1b5e8d70081d2739b12b28a3c8654c40cd1625957f53017a18", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:E-MTAB-513 licence not read", "asset:data:geo:E-MTAB-513 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["al system, ASprofile, and its application to RNA-seq data from Illumina's Human Body Map project", "native splicing in normal human tissues from RNA-seq data, while providing insights into the role", "hods Supplementary materials Total number of RNA-seq reads from each of 16 human tissues.\"Mapped\"", "le of alternative splicing in shaping tissue transcriptome differences. The catalog of events and the A"], "order_basis": "paper_text_order:363", "id": "assay:1"}, {"role": "analysis", "definition_id": "contingency_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["chi_square_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Novel events are depleted in ‘switches’ compared to known events (test of homogeneity, df=2, chi-square 274.7, p = 0.0)."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:43:28+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}