{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33361643", "kind": "science-record", "revision": 6, "content_hash": "sha256:9a8e030da42789209f8e1339399e52e90cd84edfd65b614639a6b9ee06f46f3b", "created_at": "2026-11-01T15:41:20Z", "updated_at": "2026-11-01T22:02:48Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of four novel prognosis biomarkers and potential therapeutic drugs for human colorectal cancer by bioinformatics analysis.", "doi": "10.7555/JBR.34.20200021", "pmid": "33361643", "authors": ["Zhen Sun", "Chen Liu", "Steven Y Cheng"], "journal": "Journal of biomedical research", "year": 2020, "abstract": "Colorectal cancer (CRC) is one of the most deadly cancers in the world with few reliable biomarkers that have been selected into clinical guidelines for prognosis of CRC patients. In this study, mRNA microarray datasets GSE113513, GSE21510, GSE44076, and GSE32323 were obtained from the Gene Expression Omnibus (GEO) and analyzed with bioinformatics to identify hub genes in CRC development. Differentially expressed genes (DEGs) were analyzed using the GEO2R tool. Gene ontology (GO) and KEGG analyses were performed through the DAVID database. STRING database and Cytoscape software were used to construct a protein-protein interaction (PPI) network and identify key modules and hub genes. Survival analyses of the DEGs were performed on GEPIA database. The Connectivity Map database was used to screen potential drugs. A total of 865 DEGs were identified, including 374 upregulated and 491 downregulated genes. These DEGs were mainly associated with metabolic pathways, pathways in cancer, cell cycle and so on. The PPI network was identified with 863 nodes and 5817 edges. Survival analysis revealed that HMMR, PAICS, ETFDH, and SCG2 were significantly associated with overall survival of CRC patients. And blebbistatin and sulconazole were identified as candidate drugs. In conclusion, our study found four hub genes involved in CRC, which may provide novel potential biomarkers for CRC prognosis, and two potential candidate drugs for CRC.", "claims": [{"id": "claim-method", "statement": "To identify the DEGs, we used the NCBI-GEO2R online tool to analyze these datasets. Subsequently, adjusted P-value <0.05 and |log 2(fold change)| >1 were set as the cutoff criteria to screen the significant DEGs of each dataset. Finally, Venn diagrams were performed to get the overlap significant DEGs of the 4 datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33361643", "locator": "sections[4] \"Identification of DEGs and data preprocessing\" paragraph 2", "quote": "To identify the DEGs, we used the NCBI-GEO2R online tool to analyze these datasets. Subsequently, adjusted P-value <0.05 and |log 2(fold change)| >1 were set as the cutoff criteria to screen the significant DEGs of each dataset. Finally, Venn diagrams were performed to get the overlap significant DEGs of the 4 datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33361643", "locator": "sections[3] \"Data resources\" paragraph 2", "quote": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323."}], "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:33361643"], "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:GSE113513"], "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:GSE113513"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33361643", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7555/JBR.34.20200021", "sha256": "sha256:deafce3e48cee80f6267ceb07a08248f0e934d74cb715475e27fe2dbe4fb2937", "bytes": 24966, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7555/JBR.34.20200021", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7874272", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE113513", "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=GSE113513", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE113513", "version": null, "note": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM3108231", "GSM3108232", "GSM3108233", "GSM3108234", "GSM3108235", "GSM3108236", "GSM3108237", "GSM3108238", "GSM3108239", "GSM3108240", "GSM3108241", "GSM3108242", "GSM3108243", "GSM3108244", "GSM3108245", "GSM3108246", "GSM3108247", "GSM3108248", "GSM3108249", "GSM3108250", "GSM3108251", "GSM3108252", "GSM3108253", "GSM3108254", "GSM3108255", "GSM3108256", "GSM3108257", "GSM3108258"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Gene expression profile of human colorectal carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE21510", "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=GSE21510", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21510", "version": null, "note": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM537330", "GSM537331", "GSM537332", "GSM537333", "GSM537334", "GSM537335", "GSM537336", "GSM537337", "GSM537338", "GSM537339", "GSM537340", "GSM537341", "GSM537342", "GSM537343", "GSM537344", "GSM537345", "GSM537346", "GSM537347", "GSM537348", "GSM537349", "GSM537350", "GSM537351", "GSM537352", "GSM537353", "GSM537354", "GSM537355", "GSM537356", "GSM537357", "GSM537358", "GSM537359", "GSM537360", "GSM537361", "GSM537362", "GSM537363", "GSM537364", "GSM537365", "GSM537366", "GSM537367", "GSM537368", "GSM537369", "GSM537370", "GSM537371", "GSM537372", "GSM537373", "GSM537374", "GSM537375", "GSM537376", "GSM537377", "GSM537378", "GSM537379", "GSM537380", "GSM537381", "GSM537382", "GSM537383", "GSM537384", "GSM537385", "GSM537386", "GSM537387", "GSM537388", "GSM537389", "GSM537390", "GSM537391", "GSM537392", "GSM537393", "GSM537394", "GSM537395", "GSM537396", "GSM537397", "GSM537398", "GSM537399", "GSM537400", "GSM537401", "GSM537402", "GSM537403", "GSM537404", "GSM537405", "GSM537406", "GSM537407", "GSM537408", "GSM537409", "GSM537410", "GSM537411", "GSM537412", "GSM537413", "GSM537414", "GSM537415", "GSM537416", "GSM537417", "GSM537418", "GSM537419", "GSM537420", "GSM537421", "GSM537422", "GSM537423", "GSM537424", "GSM537425", "GSM537426", "GSM537427", "GSM537428", "GSM537429", "GSM537430", "GSM537431", "GSM537432", "GSM537433", "GSM549099", "GSM549100", "GSM549101", "GSM549102", "GSM549103", "GSM549104", "GSM549105", "GSM549106", "GSM549107", "GSM549108", "GSM549109", "GSM549110", "GSM549111", "GSM549112", "GSM549113", "GSM549114", "GSM549115", "GSM549116", "GSM549117", "GSM549118", "GSM549119", "GSM549120", "GSM549121", "GSM549122", "GSM549123", "GSM549124", "GSM549125", "GSM549126", "GSM549127", "GSM549128", "GSM549129", "GSM549130", "GSM549131", "GSM549132", "GSM549133", "GSM549134", "GSM549135", "GSM549136", "GSM549137", "GSM549138", "GSM549139", "GSM549140", "GSM549141", "GSM549142"], "sample_count": 148, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Clinical Significance of Osteoprotegerin Expression in Human Colorectal Cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE32323", "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=GSE32323", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32323", "version": null, "note": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM800742", "GSM800743", "GSM800744", "GSM800745", "GSM800746", "GSM800747", "GSM800748", "GSM800749", "GSM800750", "GSM800751", "GSM800752", "GSM800753", "GSM800754", "GSM800755", "GSM800756", "GSM800757", "GSM800758", "GSM800759", "GSM800760", "GSM800761", "GSM800762", "GSM800763", "GSM800764", "GSM800765", "GSM800766", "GSM800767", "GSM800768", "GSM800769", "GSM800770", "GSM800771", "GSM800772", "GSM800773", "GSM800774", "GSM800775", "GSM800776", "GSM800777", "GSM800778", "GSM800779", "GSM800780", "GSM800781", "GSM800782", "GSM800783", "GSM800784", "GSM800785"], "sample_count": 44, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Screening for Epigenetically Masked Genes in Colorectal Cancer using 5-aza-2’-deoxycytidine treatment, Microarray and Gene Expression Profile", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE44076", "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=GSE44076", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE44076", "version": null, "note": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1077598", "GSM1077599", "GSM1077600", "GSM1077601", "GSM1077602", "GSM1077603", "GSM1077604", "GSM1077605", "GSM1077606", "GSM1077607", "GSM1077608", "GSM1077609", "GSM1077610", "GSM1077611", "GSM1077612", "GSM1077613", "GSM1077614", "GSM1077615", "GSM1077616", "GSM1077617", "GSM1077618", "GSM1077619", "GSM1077620", "GSM1077621", "GSM1077622", "GSM1077623", "GSM1077624", "GSM1077625", "GSM1077626", "GSM1077627", "GSM1077628", "GSM1077629", "GSM1077630", "GSM1077631", "GSM1077632", "GSM1077633", "GSM1077634", "GSM1077635", "GSM1077636", "GSM1077637", "GSM1077638", "GSM1077639", "GSM1077640", "GSM1077641", "GSM1077642", "GSM1077643", "GSM1077644", "GSM1077645", "GSM1077646", "GSM1077647", "GSM1077648", "GSM1077649", "GSM1077650", "GSM1077651", "GSM1077652", "GSM1077653", "GSM1077654", "GSM1077655", "GSM1077656", "GSM1077657", "GSM1077658", "GSM1077659", "GSM1077660", "GSM1077661", "GSM1077662", "GSM1077663", "GSM1077664", "GSM1077665", "GSM1077666", "GSM1077667", "GSM1077668", "GSM1077669", "GSM1077670", "GSM1077671", "GSM1077672", "GSM1077673", "GSM1077674", "GSM1077675", "GSM1077676", "GSM1077677", "GSM1077678", "GSM1077679", "GSM1077680", "GSM1077681", "GSM1077682", "GSM1077683", "GSM1077684", "GSM1077685", "GSM1077686", "GSM1077687", "GSM1077688", "GSM1077689", "GSM1077690", "GSM1077691", "GSM1077692", "GSM1077693", "GSM1077694", "GSM1077695", "GSM1077696", "GSM1077697", "GSM1077698", "GSM1077699", "GSM1077700", "GSM1077701", "GSM1077702", "GSM1077703", "GSM1077704", "GSM1077705", "GSM1077706", "GSM1077707", "GSM1077708", "GSM1077709", "GSM1077710", "GSM1077711", "GSM1077712", "GSM1077713", "GSM1077714", "GSM1077715", "GSM1077716", "GSM1077717", "GSM1077718", "GSM1077719", "GSM1077720", "GSM1077721", "GSM1077722", "GSM1077723", "GSM1077724", "GSM1077725", "GSM1077726", "GSM1077727", "GSM1077728", "GSM1077729", "GSM1077730", "GSM1077731", "GSM1077732", "GSM1077733", "GSM1077734", "GSM1077735", "GSM1077736", "GSM1077737", "GSM1077738", "GSM1077739", "GSM1077740", "GSM1077741", "GSM1077742", "GSM1077743", "GSM1077744", "GSM1077745", "GSM1077746", "GSM1077747", "GSM1077748", "GSM1077749", "GSM1077750", "GSM1077751", "GSM1077752", "GSM1077753", "GSM1077754", "GSM1077755", "GSM1077756", "GSM1077757", "GSM1077758", "GSM1077759", "GSM1077760", "GSM1077761", "GSM1077762", "GSM1077763", "GSM1077764", "GSM1077765", "GSM1077766", "GSM1077767", "GSM1077768", "GSM1077769", "GSM1077770", "GSM1077771", "GSM1077772", "GSM1077773", "GSM1077774", "GSM1077775", "GSM1077776", "GSM1077777", "GSM1077778", "GSM1077779", "GSM1077780", "GSM1077781", "GSM1077782", "GSM1077783", "GSM1077784", "GSM1077785", "GSM1077786", "GSM1077787", "GSM1077788", "GSM1077789", "GSM1077790", "GSM1077791", "GSM1077792", "GSM1077793", "GSM1077794", "GSM1077795", "GSM1077796", "GSM1077797", "GSM1077798", "GSM1077799", "GSM1077800", "GSM1077801", "GSM1077802", "GSM1077803", "GSM1077804", "GSM1077805", "GSM1077806", "GSM1077807", "GSM1077808", "GSM1077809", "GSM1077810", "GSM1077811", "GSM1077812", "GSM1077813", "GSM1077814", "GSM1077815", "GSM1077816", "GSM1077817", "GSM1077818", "GSM1077819", "GSM1077820", "GSM1077821", "GSM1077822", "GSM1077823", "GSM1077824", "GSM1077825", "GSM1077826", "GSM1077827", "GSM1077828", "GSM1077829", "GSM1077830", "GSM1077831", "GSM1077832", "GSM1077833", "GSM1077834", "GSM1077835", "GSM1077836", "GSM1077837", "GSM1077838", "GSM1077839", "GSM1077840", "GSM1077841", "GSM1077842", "GSM1077843"], "sample_count": 246, "group_sizes": null, "group_sizes_basis": null, "platform": "13667", "taxon": "Homo sapiens", "title": "Gene expression data from healthy, adjacent normal and tumor colon cells", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33361643:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6a0a01a37989eb850007918295baf201d1b156e8f7fdc488dbe31803ee70487c", "bytes": 2440, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Table1", "version": null, "note": "Gene summaries of the four hub genes", "structure": {"pmcid": "PMC7874272", "section_index": 7, "section_title": "Analysis and validation of hub genes", "row_count": 6, "column_count": 6}, "table": {"label": "1", "caption": "Gene summaries of the four hub genes", "rows": [["Gene", "Summary", "Microarray datasets [P-value, log2(fold change)]"], ["GSE113513", "GSE21510", "GSE44076", "GSE32323"], ["HMMR", "The protein encoded by this gene is involved in cell motility. It is expressed in breast tissue and together with other proteins, it forms a complex with BRCA1 and BRCA2, thus is potentially associated with higher risk of breast cancer. Alternatively spliced transcript variants encoding different isoforms have been noted for this gene.", "6.82e−04, 1.11", "3.84e−35, 3.22", "5.32e−22, 1.20", "2.63e−04, 1.63"], ["PAICS", "This gene encodes a bifunctional enzyme containing phosphoribosylaminoimidazole carboxylase activity in its N-terminal region and phosphoribosylaminoimidazole succinocarboxamide synthetase in its C-terminal region. It catalyzes steps 6 and 7 of purine biosynthesis. The gene is closely linked and divergently transcribed with a locus that encodes an enzyme in the same pathway, and transcription of the two genes is coordinately regulated. The human genome contains several pseudogenes of this gene. Multiple transcript variants encoding different isoforms have been found for this gene.", "4.77e−08, 1.31", "5.71e−47, 2.48", "2.14e−55, 1.49", "1.38e−06, 1.73"], ["ETFDH", "This gene encodes a component of the electron-transfer system in mitochondria and is essential for electron transfer from a number of mitochondrial flavin-containing dehydrogenases to the main respiratory chain. Mutations in this gene are associated with glutaric acidemia. Alternatively spliced transcript variants that encode distinct isoforms have been observed.", "1.78e−08, −1.47", "1.67e−27, −1.92", "1.80e−71, −1.85", "3.14e−08, −1.78"], ["SCG2", "The protein encoded by this gene is a member of the chromogranin/secretogranin family of neuroendocrine secretory proteins. Studies in rodents suggest that the full-length protein, secretogranin II, is involved in the packaging or sorting of peptide hormones and neuropeptides into secretory vesicles. The full-length protein is cleaved to produce the active peptide secretoneurin, which exerts chemotaxic effects on specific cell types, and EM66, whose function is unknown.", "2.37e−07, −2.50", "1.13e−17, −1.86", "4.83e−25, −1.90", "2.91e−07, −2.28"]], "row_count": 6, "column_count": 6, "numeric_cells": 22, "header_rows": 2, "locator": "section[13]/table-wrap[1]#Table1"}}, {"id": "asset:table:pmid:33361643:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6a0a01a37989eb850007918295baf201d1b156e8f7fdc488dbe31803ee70487c", "bytes": 2440, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Table1", "version": null, "note": "Gene summaries of the four hub genes", "structure": {"pmcid": "PMC7874272", "section_index": 13, "section_title": "Analysis and validation of hub genes", "row_count": 6, "column_count": 6}, "table": {"label": "1", "caption": "Gene summaries of the four hub genes", "rows": [["Gene", "Summary", "Microarray datasets [P-value, log2(fold change)]"], ["GSE113513", "GSE21510", "GSE44076", "GSE32323"], ["HMMR", "The protein encoded by this gene is involved in cell motility. It is expressed in breast tissue and together with other proteins, it forms a complex with BRCA1 and BRCA2, thus is potentially associated with higher risk of breast cancer. Alternatively spliced transcript variants encoding different isoforms have been noted for this gene.", "6.82e−04, 1.11", "3.84e−35, 3.22", "5.32e−22, 1.20", "2.63e−04, 1.63"], ["PAICS", "This gene encodes a bifunctional enzyme containing phosphoribosylaminoimidazole carboxylase activity in its N-terminal region and phosphoribosylaminoimidazole succinocarboxamide synthetase in its C-terminal region. It catalyzes steps 6 and 7 of purine biosynthesis. The gene is closely linked and divergently transcribed with a locus that encodes an enzyme in the same pathway, and transcription of the two genes is coordinately regulated. The human genome contains several pseudogenes of this gene. Multiple transcript variants encoding different isoforms have been found for this gene.", "4.77e−08, 1.31", "5.71e−47, 2.48", "2.14e−55, 1.49", "1.38e−06, 1.73"], ["ETFDH", "This gene encodes a component of the electron-transfer system in mitochondria and is essential for electron transfer from a number of mitochondrial flavin-containing dehydrogenases to the main respiratory chain. Mutations in this gene are associated with glutaric acidemia. Alternatively spliced transcript variants that encode distinct isoforms have been observed.", "1.78e−08, −1.47", "1.67e−27, −1.92", "1.80e−71, −1.85", "3.14e−08, −1.78"], ["SCG2", "The protein encoded by this gene is a member of the chromogranin/secretogranin family of neuroendocrine secretory proteins. Studies in rodents suggest that the full-length protein, secretogranin II, is involved in the packaging or sorting of peptide hormones and neuropeptides into secretory vesicles. The full-length protein is cleaved to produce the active peptide secretoneurin, which exerts chemotaxic effects on specific cell types, and EM66, whose function is unknown.", "2.37e−07, −2.50", "1.13e−17, −1.86", "4.83e−25, −1.90", "2.91e−07, −2.28"]], "row_count": 6, "column_count": 6, "numeric_cells": 22, "header_rows": 2, "locator": "section[13]/table-wrap[1]#Table1"}}, {"id": "asset:table:pmid:33361643:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:65f342a24095ef3ebc102405b7580262a6116cff7d926a2c0d6ebc27c0d7c787", "bytes": 3613, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Table2", "version": null, "note": "The significant small active molecules that may reverse the DEGs of CRC predicted by CMap", "structure": {"pmcid": "PMC7874272", "section_index": 14, "section_title": "Identification of related active small molecules", "row_count": 39, "column_count": 9}, "table": {"label": "2", "caption": "The significant small active molecules that may reverse the DEGs of CRC predicted by CMap", "rows": [["CMap name", "Count", "Enrichment", "P-value", "", "CMap name", "Count", "Enrichment", "P-value"], ["DL-thiorphan", "2", "−0.976", "0.001 27", "", "8-azaguanine", "4", "−0.644", "0.038 11"], ["Quinostatin", "2", "−0.878", "0.029 90", "", "Acepromazine", "4", "−0.640", "0.040 08"], ["1,4-chrysenequinone", "2", "−0.866", "0.035 75", "", "Doxazosin", "4", "−0.639", "0.040 48"], ["Menadione", "2", "−0.852", "0.043 24", "", "Mefloquine", "5", "−0.637", "0.016 28"], ["Blebbistatin", "2", "−0.844", "0.048 59", "", "Trifluridine", "4", "−0.637", "0.041 87"], ["trazodone", "3", "−0.813", "0.013 20", "", "Clomipramine", "4", "−0.636", "0.042 51"], ["Thioguanosine", "4", "−0.809", "0.002 59", "", "Trioxysalen", "4", "−0.633", "0.044 24"], ["Sulconazole", "4", "−0.805", "0.002 82", "", "Corbadrine", "4", "−0.629", "0.046 73"], ["0297417-0002B", "3", "−0.792", "0.018 27", "", "Etofenamate", "4", "−0.624", "0.049 27"], ["Etacrynic acid", "3", "−0.776", "0.022 99", "", "Phthalylsulfathiazole", "5", "−0.616", "0.022 71"], ["Latamoxef", "3", "−0.759", "0.028 76", "", "Oxetacaine", "5", "−0.610", "0.025 23"], ["GW-8510", "4", "−0.757", "0.007 12", "", "Amiodarone", "5", "−0.601", "0.029 00"], ["Triflusal", "3", "−0.755", "0.030 11", "", "Meticrane", "5", "−0.599", "0.029 62"], ["Piperidolate", "3", "−0.743", "0.034 63", "", "Vorinostat", "12", "−0.596", "0.000 18"], ["Daunorubicin", "4", "−0.733", "0.010 19", "", "Tranylcypromine", "5", "−0.592", "0.032 64"], ["Repaglinide", "4", "−0.727", "0.011 42", "", "Bromocriptine", "5", "−0.573", "0.042 46"], ["Camptothecin", "3", "−0.725", "0.042 85", "", "Zimeldine", "5", "−0.572", "0.043 38"], ["Norcyclobenzaprine", "4", "−0.723", "0.012 02", "", "Clemizole", "5", "−0.568", "0.045 48"], ["Ronidazole", "3", "−0.711", "0.049 19", "", "Astemizole", "5", "−0.567", "0.046 14"], ["Ellipticine", "4", "−0.708", "0.015 14", "", "Meclozine", "5", "−0.565", "0.047 08"], ["Gliclazide", "4", "−0.707", "0.015 28", "", "Procaine", "5", "−0.565", "0.047 46"], ["Phenoxybenzamine", "4", "−0.704", "0.015 76", "", "Cloperastine", "6", "−0.551", "0.031 56"], ["0175029-0000", "6", "−0.701", "0.001 63", "", "Famprofazone", "6", "−0.543", "0.036 21"], ["Tyloxapol", "4", "−0.694", "0.018 52", "", "Dipyridamole", "6", "−0.537", "0.039 63"], ["Skimmianine", "4", "−0.690", "0.020 01", "", "Promazine", "6", "−0.523", "0.047 85"], ["Bisacodyl", "4", "−0.690", "0.020 03", "", "Trifluoperazine", "16", "−0.504", "0.000 20"], ["Resveratrol", "9", "−0.684", "0.000 04", "", "Prochlorperazine", "16", "−0.434", "0.002 99"], ["Medrysone", "6", "−0.680", "0.002 92", "", "LY-294002", "61", "−0.428", "0.000 00"], ["Bepridil", "4", "−0.674", "0.025 22", "", "Trichostatin A", "182", "−0.425", "0.000 00"], ["Pyrvinium", "6", "−0.672", "0.003 34", "", "Fluphenazine", "18", "−0.406", "0.003 80"], ["Nortriptyline", "4", "−0.669", "0.027 07", "", "Thioridazine", "20", "−0.388", "0.003 27"], ["Apigenin", "4", "−0.667", "0.027 65", "", "Alpha-estradiol", "16", "−0.357", "0.025 35"], ["Methylergometrine", "4", "−0.664", "0.028 71", "", "Geldanamycin", "15", "−0.349", "0.039 26"], ["Bufexamac", "4", "−0.660", "0.030 10", "", "Sirolimus", "44", "−0.335", "0.000 08"], ["Prestwick-1084", "4", "−0.656", "0.032 41", "", "Chlorpromazine", "19", "−0.329", "0.024 17"], ["Deptropine", "4", "−0.651", "0.034 95", "", "Wortmannin", "18", "−0.314", "0.046 91"], ["Dextromethorphan", "4", "−0.647", "0.036 86", "", "Tanespimycin", "62", "−0.311", "0.000 00"], ["Protriptyline", "4", "−0.646", "0.037 36", "", "Fulvestrant", "40", "−0.225", "0.029 99"]], "row_count": 39, "column_count": 9, "numeric_cells": 235, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Table2"}}], "gaps": ["asset:data:geo:GSE113513 not downloaded", "asset:data:geo:GSE113513 licence not read", "asset:data:geo:GSE21510 not downloaded", "asset:data:geo:GSE21510 licence not read", "asset:data:geo:GSE32323 not downloaded", "asset:data:geo:GSE32323 licence not read", "asset:data:geo:GSE44076 not downloaded", "asset:data:geo:GSE44076 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": null, "specific": null, "label": "NCBI-GEO2R online tool", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To identify the DEGs, we used the NCBI-GEO2R online tool to analyze these datasets. Subsequently, adjusted P-value <0.05 and |log 2(fold change)| >1 were set as the cutoff criteria to screen the significant DEGs of each dataset. Finally, Venn diagrams were performed to get the overlap significant DEGs of the 4 datasets."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE113513", "GSE21510", "GSE44076", "GSE32323"], "resolved_accessions": ["GSE113513", "GSE21510", "GSE44076", "GSE32323"], "statements": ["A total of 4 GEO datasets were selected, including GSE113513, GSE21510, GSE44076, and GSE32323."], "basis": "The paper names GSE113513, GSE21510, GSE44076, GSE32323 in NCBI Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:33361643", "data:geo:GSE113513", "asset:table:pmid:33361643:1", "asset:table:pmid:33361643:2", "asset:table:pmid:33361643:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE113513"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 20976, "completion_tokens": 1488, "cached_tokens": 784}}, "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:33361643", "type": "paper", "label": "pmid:33361643"}, {"id": "source:pmid:33361643", "type": "manuscript", "label": "PMID 33361643 full text"}, {"id": "data:geo:GSE113513", "type": "dataset", "label": "GEO GSE113513"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33361643", "type": "paper", "label": "pmid:33361643"}, {"id": "source:pmid:33361643", "type": "manuscript", "label": "PMID 33361643 full text"}, {"id": "data:geo:GSE113513", "type": "dataset", "label": "GEO GSE113513"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33361643", "type": "extraction", "used": ["source:pmid:33361643"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE113513", "type": "accession_resolution", "used": ["data:geo:GSE113513"], "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:33361643", "parent_hash": "sha256:b2d3a27476fb48241ad7730d4a0c329678169b130da69f71a0d31add821fb73a", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE113513 licence not read", "asset:data:geo:GSE113513 not downloaded", "asset:data:geo:GSE21510 licence not read", "asset:data:geo:GSE21510 not downloaded", "asset:data:geo:GSE32323 licence not read", "asset:data:geo:GSE32323 not downloaded", "asset:data:geo:GSE44076 licence not read", "asset:data:geo:GSE44076 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ognosis of CRC patients. In this study, mRNA microarray datasets GSE113513, GSE21510, GSE44076, and"], "order_basis": "paper_text_order:293", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "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":"2026-11-04T02:39:23+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}}}