← All .science files
pmid:33193601
Identification of Potential Core Genes Associated With the Progression of Stomach Adenocarcinoma Using Bioinformatic Analysis.
Biao Yang · Meijing Zhang · Tianhang Luo
Frontiers in genetics · 2020 doi:10.3389/fgene.2020.517362
Paper
complete
Experiment
complete
Data
partial
Analysis
partial
Execution
absent
Execution evidence has not yet been added to this .science file. Explore its methods, data and open questions to plan the next step.
Record details sci_version · id · kind · revision · content_hash · schema · created_at · updated_at · generator
paper object · 10 fields
authors array · 3 items
claims array · 2 items
[0] object · 6 fields
evidence array · 1 item
[0] object · 3 fields
[1] object · 6 fields
evidence array · 1 item
[0] object · 3 fields
gaps array · 0 items
experiment object · 8 fields
steps array · 3 items
[0] object · 13 fields
parameters object · 0 fields
inputs array · 1 item
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
[1] object · 13 fields
parameters object · 0 fields
inputs array · 1 item
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
[2] object · 13 fields
parameters object · 0 fields
inputs array · 1 item
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
materials array · 0 items
instruments array · 0 items
reagents array · 0 items
conditions object · 0 fields
gaps array · 0 items
data object · 3 fields
assets array · 12 items
[0] object · 15 fields
structure object · 4 fields
[1] object · 15 fields
structure object · 15 fields
sample_accessions array · 69 items
[2] object · 15 fields
structure object · 15 fields
sample_accessions array · 27 items
[3] object · 15 fields
structure object · 15 fields
sample_accessions array · 132 items
[4] object · 15 fields
structure object · 15 fields
sample_accessions array · 64 items
[5] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 3 items
[0] array · 6 items
[1] array · 6 items
[2] array · 6 items
[6] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 5 items
[0] array · 5 items
[1] array · 5 items
[2] array · 5 items
[3] array · 5 items
[4] array · 5 items
[7] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 13 items
[0] array · 2 items
[1] array · 11 items
[2] array · 11 items
[3] array · 11 items
[4] array · 11 items
[5] array · 11 items
[6] array · 11 items
[7] array · 11 items
[8] array · 11 items
[9] array · 11 items
[10] array · 11 items
[11] array · 11 items
[12] array · 11 items
[8] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 31 items
[0] array · 6 items
[1] array · 6 items
[2] array · 6 items
[3] array · 6 items
[4] array · 6 items
[5] array · 6 items
[6] array · 6 items
[7] array · 6 items
[8] array · 6 items
[9] array · 6 items
[10] array · 6 items
[11] array · 6 items
[12] array · 6 items
[13] array · 6 items
[14] array · 6 items
[15] array · 6 items
[16] array · 6 items
[17] array · 6 items
[18] array · 6 items
[19] array · 6 items
[20] array · 6 items
[21] array · 6 items
[22] array · 6 items
[23] array · 6 items
[24] array · 6 items
[25] array · 6 items
[26] array · 6 items
[27] array · 6 items
[28] array · 6 items
[29] array · 6 items
[30] array · 6 items
[9] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 10 items
[0] array · 5 items
[1] array · 5 items
[2] array · 5 items
[3] array · 5 items
[4] array · 5 items
[5] array · 5 items
[6] array · 5 items
[7] array · 5 items
[8] array · 5 items
[9] array · 5 items
[10] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 15 items
[0] array · 2 items
[1] array · 2 items
[2] array · 2 items
[3] array · 2 items
[4] array · 2 items
[5] array · 2 items
[6] array · 2 items
[7] array · 2 items
[8] array · 2 items
[9] array · 2 items
[10] array · 2 items
[11] array · 2 items
[12] array · 2 items
[13] array · 2 items
[14] array · 2 items
[11] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 3 items
[0] array · 6 items
[1] array · 6 items
[2] array · 6 items
gaps array · 8 items
analysis object · 4 fields
methods array · 3 items
[0] object · 10 fields
dsl_operations array · 1 item
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 1 item
[1] object · 10 fields
dsl_operations array · 3 items
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 1 item
[2] object · 10 fields
dsl_operations array · 0 items
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 0 items
targets array · 0 items
gaps array · 1 item
capability object · 3 fields
requirements array · 1 item
[0] object · 6 fields
assay_families array · 9 items
gaps array · 0 items
readiness object · 8 fields
axes object · 3 fields
method object · 5 fields
required_operations array · 1 item
missing_operations array · 0 items
capability object · 4 fields
data object · 6 fields
accessions array · 4 items
resolved_accessions array · 4 items
statements array · 1 item
can_run object · 3 fields
dsl_operations array · 1 item
assets array · 9 items
steps array · 1 item
must_build object · 5 fields
dsl_operations array · 0 items
converters array · 0 items
readers array · 0 items
capabilities array · 0 items
data_gaps array · 1 item
gaps array · 0 items
review object · 5 fields
machine_critique object · 5 fields
reader object · 5 fields
evidence_check object · 2 fields
usage object · 3 fields
stages array · 1 item
[0] object · 4 fields
gaps array · 3 items
provenance object · 7 fields
entities array · 3 items
activities array · 3 items
[0] object · 4 fields
used array · 3 items
[0] object · 3 fields
[1] object · 3 fields
[2] object · 3 fields
[1] object · 4 fields
agents array · 2 items
lineage object · 4 fields
gaps array · 13 items
assays array · 1 item
[0] object · 11 fields
required_operations array · 1 item
source_hashes object · 1 field
evidence array · 1 item
Complete file
{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33193601", "kind": "science-record", "revision": 5, "content_hash": "sha256:952c81221682cfa64ef24af5a2e8ea6b6e88f7d1fc7ffaa52a0fcc5a83775300", "created_at": "2026-11-01T15:41:16Z", "updated_at": "2026-11-01T22:02:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Potential Core Genes Associated With the Progression of Stomach Adenocarcinoma Using Bioinformatic Analysis.", "doi": "10.3389/fgene.2020.517362", "pmid": "33193601", "authors": ["Biao Yang", "Meijing Zhang", "Tianhang Luo"], "journal": "Frontiers in genetics", "year": 2020, "abstract": "PURPOSE: Stomach adenocarcinoma (STAD) is one of the most frequently diagnosed cancer in the world with both high mortality and high metastatic capacity. Therefore, the present study aimed to investigate novel therapeutic targets and prognostic biomarkers that can be used for STAD treatment.\nMATERIALS AND METHODS: We acquired four original gene chip profiles, namely GSE13911, GSE19826, GSE54129, and GSE65801 from the Gene Expression Omnibus (GEO). The datasets included a total of 114 STAD tissues and 110 adjacent normal tissues. The GEO2R online tool and Venn diagram software were used to discriminate differentially expressed genes (DEGs). Gene ontology (GO) and Kyoto Encyclopedia of Gene and Genome (KEGG) enriched pathways were also performed for annotation and visualization with DEGs. The STRING online database was used to identify the functional interactions of DEGs. Subsequently, we selected the most significant DEGs to construct the protein-protein interaction (PPI) network and to reveal the core genes involved. Finally, the Kaplan-Meier Plotter online database and Gene Expression Profiling Interactive Analysis (GEPIA) were used to analyze the prognostic information of the core DEGs.\nRESULTS: A total of 114 DEGs (35 upregulated and 79 downregulated) were identified, which were abnormally expressed in the GEO datasets. GO analysis demonstrated that the majority of the upregulated DEGs were significantly enriched in collagen trimer, cell adhesion, and identical protein binding. The downregulated DEGs were involved in extracellular space, digestion, and inward rectifier potassium channel activity. Signaling pathway analysis indicated that upregulated DEGs were mainly enriched in receptor interaction, whereas downregulated DEGs were involved in gastric acid secretion. A total of 80 DEGs were screened into the PPI network complex, and one of the most important modules with a high degree was detected. Furthermore, 10 core genes were identified, namely COL1A1, COL1A2, FN1, COL5A2, BGN, COL6A3, COL12A1, THBS2, CDH11, and SERPINH1. Finally, the results of the prognostic information further demonstrated that all 10 core genes exhibited significantly higher expression in STAD tissues compared with that noted in normal tissues.\nCONCLUSION: The multiple molecular mechanisms of these novel core genes in STAD are worthy of further investigation and may reveal novel therapeutic targets and biomarkers for STAD treatment.", "claims": [{"id": "claim-method", "statement": "Following screening of the data with GEO2R online tools with the cut-off criterion of adjusted P < 0.05 and |log2FC| > 1.5, 1,294, 899, 2,419, and 1,734 DEGs were screened from the four expression profile data, respectively.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33193601", "locator": "sections[9] \"Identification of DEGs in STAD\" paragraph 2", "quote": "Following screening of the data with GEO2R online tools with the cut-off criterion of adjusted P < 0.05 and |log2FC| > 1.5, 1,294, 899, 2,419, and 1,734 DEGs were screened from the four expression profile data, respectively."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33193601", "locator": "sections[15] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801."}], "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:33193601"], "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:GSE13911"], "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:GSE13911"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33193601", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2020.517362", "sha256": "sha256:3a965300d6e247f620ec6699589756aa5c4bc312946f4666456c0b895061fec0", "bytes": 38661, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2020.517362", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7642829", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE13911", "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=GSE13911", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13911", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM350411", "GSM350412", "GSM350413", "GSM350414", "GSM350415", "GSM350416", "GSM350417", "GSM350418", "GSM350419", "GSM350420", "GSM350421", "GSM350422", "GSM350423", "GSM350424", "GSM350425", "GSM350426", "GSM350427", "GSM350428", "GSM350429", "GSM350430", "GSM350431", "GSM350432", "GSM350433", "GSM350434", "GSM350435", "GSM350436", "GSM350437", "GSM350438", "GSM350439", "GSM350440", "GSM350441", "GSM350442", "GSM350443", "GSM350444", "GSM350445", "GSM350446", "GSM350447", "GSM350448", "GSM350449", "GSM350450", "GSM350451", "GSM350452", "GSM350453", "GSM350454", "GSM350455", "GSM350456", "GSM350457", "GSM350458", "GSM350459", "GSM350460", "GSM350461", "GSM350462", "GSM350463", "GSM350464", "GSM350465", "GSM350466", "GSM350467", "GSM350468", "GSM350469", "GSM350470", "GSM350471", "GSM350472", "GSM350473", "GSM350474", "GSM350475", "GSM350476", "GSM350477", "GSM350478", "GSM350479"], "sample_count": 69, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from primary gastric tumors (MSI and MSS) and adjacent normal samples", "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:GSE19826", "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=GSE19826", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19826", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM495051", "GSM495052", "GSM495053", "GSM495054", "GSM495055", "GSM495056", "GSM495057", "GSM495058", "GSM495059", "GSM495060", "GSM495061", "GSM495062", "GSM495063", "GSM495064", "GSM495065", "GSM495066", "GSM495067", "GSM495068", "GSM495069", "GSM495070", "GSM495071", "GSM495072", "GSM495073", "GSM495074", "GSM495075", "GSM495076", "GSM495077"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from gastric 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:GSE54129", "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=GSE54129", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE54129", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1308392", "GSM1308393", "GSM1308394", "GSM1308395", "GSM1308396", "GSM1308397", "GSM1308398", "GSM1308399", "GSM1308400", "GSM1308401", "GSM1308402", "GSM1308403", "GSM1308404", "GSM1308405", "GSM1308406", "GSM1308407", "GSM1308408", "GSM1308409", "GSM1308410", "GSM1308411", "GSM1308412", "GSM1308413", "GSM1308414", "GSM1308415", "GSM1308416", "GSM1308417", "GSM1308418", "GSM1308419", "GSM1308420", "GSM1308421", "GSM1308422", "GSM1308423", "GSM1308424", "GSM1308425", "GSM1308426", "GSM1308427", "GSM1308428", "GSM1308429", "GSM1308430", "GSM1308431", "GSM1308432", "GSM1308433", "GSM1308434", "GSM1308435", "GSM1308436", "GSM1308437", "GSM1308438", "GSM1308439", "GSM1308440", "GSM1308441", "GSM1308442", "GSM1308443", "GSM1308444", "GSM1308445", "GSM1308446", "GSM1308447", "GSM1308448", "GSM1308449", "GSM1308450", "GSM1308451", "GSM1308452", "GSM1308453", "GSM1308454", "GSM1308455", "GSM1308456", "GSM1308457", "GSM1308458", "GSM1308459", "GSM1308460", "GSM1308461", "GSM1308462", "GSM1308463", "GSM1308464", "GSM1308465", "GSM1308466", "GSM1308467", "GSM1308468", "GSM1308469", "GSM1308470", "GSM1308471", "GSM1308472", "GSM1308473", "GSM1308474", "GSM1308475", "GSM1308476", "GSM1308477", "GSM1308478", "GSM1308479", "GSM1308480", "GSM1308481", "GSM1308482", "GSM1308483", "GSM1308484", "GSM1308485", "GSM1308486", "GSM1308487", "GSM1308488", "GSM1308489", "GSM1308490", "GSM1308491", "GSM1308492", "GSM1308493", "GSM1308494", "GSM1308495", "GSM1308496", "GSM1308497", "GSM1308498", "GSM1308499", "GSM1308500", "GSM1308501", "GSM1308502", "GSM1308503", "GSM1308504", "GSM1308505", "GSM1308506", "GSM1308507", "GSM1308508", "GSM1308509", "GSM1308510", "GSM1308511", "GSM1308512", "GSM1308513", "GSM1308514", "GSM1308515", "GSM1308516", "GSM1308517", "GSM1308518", "GSM1308519", "GSM1308520", "GSM1308521", "GSM1308522", "GSM1308523"], "sample_count": 132, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Global gene expression analysis of gastric cancer by oligonucleotide microarrays", "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:GSE65801", "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=GSE65801", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65801", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1606492", "GSM1606493", "GSM1606494", "GSM1606495", "GSM1606496", "GSM1606497", "GSM1606498", "GSM1606499", "GSM1606500", "GSM1606501", "GSM1606502", "GSM1606503", "GSM1606504", "GSM1606505", "GSM1606506", "GSM1606507", "GSM1606508", "GSM1606509", "GSM1606510", "GSM1606511", "GSM1606512", "GSM1606513", "GSM1606514", "GSM1606515", "GSM1606516", "GSM1606517", "GSM1606518", "GSM1606519", "GSM1606520", "GSM1606521", "GSM1606522", "GSM1606523", "GSM1606524", "GSM1606525", "GSM1606526", "GSM1606527", "GSM1606528", "GSM1606529", "GSM1606530", "GSM1606531", "GSM1606532", "GSM1606533", "GSM1606534", "GSM1606535", "GSM1606536", "GSM1606537", "GSM1606538", "GSM1606539", "GSM1606540", "GSM1606541", "GSM1606542", "GSM1606543", "GSM1606544", "GSM1606545", "GSM1606546", "GSM1606547", "GSM1606548", "GSM1606549", "GSM1606550", "GSM1606551", "GSM1606552", "GSM1606553", "GSM1606554", "GSM1606555"], "sample_count": 64, "group_sizes": null, "group_sizes_basis": null, "platform": "14550", "taxon": "Homo sapiens", "title": "Characterization of differentially expressed genes involved in pathways associated with gastric cancer", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33193601:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e537eefe01b3118bc2135029426643311f2b2a0e8ae2aaef219394d755afe5b7", "bytes": 479, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T6", "version": null, "note": "Re-analysis of 10 selected genes via the KEGG pathway enrichment.", "structure": {"pmcid": "PMC7642829", "section_index": 7, "section_title": "Core Gene Analysis", "row_count": 3, "column_count": 6}, "table": {"label": "TABLE 6", "caption": "Re-analysis of 10 selected genes via the KEGG pathway enrichment.", "rows": [["Pathway ID", "Term", "Count", "P-value", "Genes", "FDR"], ["XU04512", "ECM-receptor interaction", "6", "1.12E-09", "COL6A3, COL1A2, COL1 Al, THBS2, COL5A2, FN1", "4.28E-07"], ["xtrO4510", "Focal adhesion", "6", "1.19E-07", "COL6A3, COL1A2, COL1 Al, THBS2, COL5A2, FN1", "4.53E-05"]], "row_count": 3, "column_count": 6, "numeric_cells": 8, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T6"}}, {"id": "asset:table:pmid:33193601:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:141ea9c13ff6ed5510529f03b5dbad6f4cbac2920504f8bf40a0ac16ff4cd68d", "bytes": 400, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T1", "version": null, "note": "The detailed information of the four GEO datasets.", "structure": {"pmcid": "PMC7642829", "section_index": 9, "section_title": "Identification of DEGs in STAD", "row_count": 5, "column_count": 5}, "table": {"label": "TABLE 1", "caption": "The detailed information of the four GEO datasets.", "rows": [["ID", "Tissue", "Platform", "Normal", "Tumor"], ["GSE13911", "STAD", "GPL570", "31", "38"], ["GSE19826", "STAD", "GPL571", "15", "12"], ["GSE54129", "STAD", "GPL572", "21", "111"], ["GSE65801", "STAD", "GPL14550", "32", "32"]], "row_count": 5, "column_count": 5, "numeric_cells": 16, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33193601:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2a2811f7b3bd69b2e6509b7cb88b8b273e9ca470afb3ae991a11f0028dff9ae6", "bytes": 1428, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#T2", "version": null, "note": "All 114 commonly differentially expressed genes (DEGs) were detected from four profile datasets, including 79 downregulated genes and 35 upregulated genes in the STAD tissues compared to normal STAD tissues.", "structure": {"pmcid": "PMC7642829", "section_index": 9, "section_title": "Identification of DEGs in STAD", "row_count": 13, "column_count": 11}, "table": {"label": "TABLE 2", "caption": "All 114 commonly differentially expressed genes (DEGs) were detected from four profile datasets, including 79 downregulated genes and 35 upregulated genes in the STAD tissues compared to normal STAD tissues.", "rows": [["DEGs", "Gene names"], ["Uprcgulated", "ADAM 12", "IGF2BP3", "COL1A1", "FNDC1", "CST1", "FN1", "PRRX1", "COL5A2", "HOXA10", "SPP1"], ["", "SFRP4", "CDH11", "BGN", "COL8A1", "ASPN", "SERPINH1", "FAP", "INHBA", "FSCN1", "BMP1"], ["", "THBS2", "NID2", "MFAP2", "WISP1", "Sum", "RARRES1", "COL6A3", "CLDN1", "COL10A1", "PMEPA1"], ["", "CTHRC1", "EPHB2", "COL1A2", "COL12A1", "SPOCK1", "", "", "", "", ""], ["Downregulated", "LDHD", "MAL", "ADH7", "ZBTB7C", "LIPF", "B4GALNT3 FM05", "roc", "TMED6", "SULT1B1", ""], ["", "FBP2", "CAPN9", "VSIG1", "CWH43", "PDIA2", "CYP2C18", "CA2", "B3GNT6", "SCNN1G", "CLDN18"], ["", "AKR1B10", "PKIB", "CA9", "SCGB2A1", "LOC400043 ALDH3A1", "GATA5", "KCNE2", "PSAPL1", "FBXL13", ""], ["", "PTPRZ1", "ESRRG", "GCNT2", "TMPRSS2", "ARHGEF37 FUT9", "ATP4B", "SOSTDC1", "KLKU", "GKN2", ""], ["", "ATP4A", "AKR7A3", "SSI", "CXCL17", "CAPN13", "RDH12", "SLC26A9", "ENPP6", "PSCA", "BEX5"], ["", "UGT2B15", "CPA2", "TFF2", "SPINK2", "TCN1", "C16orf89", "VSTM2A", "RORC", "KCNJ16", "HYAL1"], ["", "KIAA1324", "RAB27B", "SCNN1B", "LYPD6B", "HOMER2", "GIF", "SSTR1", "MUC5AC", "KCNJ15", "TFF1"], ["", "GKN1", "DPCR1", "HPGD", "CNTN3", "MUC6", "ALDH1A1", "ACER2", "VSIG2", "ASCL1", ""]], "row_count": 13, "column_count": 11, "numeric_cells": 23, "header_rows": 1, "locator": "section[9]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:33193601:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9a7d2ec506ae39394ff39d311d97aab8f61ceff084f087766d393d8f7ae940f7", "bytes": 3210, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T3", "version": null, "note": "Gene ontology analysis of differentially expressed genes in STAD.", "structure": {"pmcid": "PMC7642829", "section_index": 10, "section_title": "DEGs, GO, and KEGG Pathway Analysis in STAD", "row_count": 31, "column_count": 6}, "table": {"label": "TABLE 3", "caption": "Gene ontology analysis of differentially expressed genes in STAD.", "rows": [["Expression", "Category", "Term", "Count", "P-value", "FDR"], ["Upregulated", "GOTERM_BP_DIRECT", "GO:0007155∼cell adhesion", "7", "8.38E-07", "0.001059856"], ["", "GOTERM_BP_DIRECT", "GO:0035987∼endodermal cell differentiation", "4", "1.68E-05", "0.021196552"], ["", "GOTERM_BP_DIRECT", "GO:0030199∼collagen fibril organization", "4", "2.35E-05", "0.029671995"], ["", "GOTERM_BP_DIRECT", "GO:0071230∼cellular response to amino acid stimulus", "3", "0.003303913", "4.09798155"], ["", "GOTERM_BP_DIRECT", "GO:()001501-skeletal system development", "3", "0.004586779", "5.647054851"], ["", "GOTERM_CC_DIRECT", "GO:0005581-collagen trimer", "7", "1.31E-09", "135E-06"], ["", "GOTERM_CC_DIRECT", "GO:0005578∼proteinaceous extracellular matrix", "8", "5.16E-08", "5.29E-05"], ["", "GOTERM_CC_DIRECT", "GO:0005615∼extracellular space", "12", "1.21E-06", "0.001236783"], ["", "GOTERM_CC_DIRECT", "GO:0070062∼extrdcellular exosome", "12", "0.002224851", "2.258522618"], ["", "GOTERM_CC_DIRECT", "GO:0005576∼extracellular region", "6", "0.00306613", "3.100466564"], ["", "GOTERM_MF_DIRECT", "GO:0042802∼identical protein binding", "4", "0.002087486", "1.983628784"], ["", "GOTERM_MF_DIRECT", "GO:0005201-extracellular matrix structural constituent", "3", "0.002236986", "2.124328943"], ["", "GOTERM_MF_DIRECT", "GO:0005515∼protein binding", "4", "0.003812268", "3.59592875"], ["", "GOTERM_MF_DIRECT", "GO:0005509∼calcium ion binding", "6", "0.003982864", "3.75410086"], ["", "GOTERM_MF_DIRECT", "GO:0048407∼platelet-derived growth factor binding", "2", "0.005716885", "5.348701785"], ["Downregulated", "GOTERM_BP_DIRECT", "GO:0007586∼digestion", "8", "6.67E-09", "9.09E-06"], ["", "GOTERM_BP_DIRECT", "GO:0006081∼cellular aldehyde metabolic process", "4", "1.07E-05", "0.014571778"], ["", "GOTERM_BP_DIRECT", "GO:0006805∼xenobiotic metabolic process", "6", "1.69E-05", "0.023039718"], ["", "GOTERM_BP_DIRECT", "GO:(X)55114∼oxidation-reduction process", "12", "2.71 E-05", "0.036936867"], ["", "GOTERM_BP_DIRECT", "GO:0010107∼potassium ion import", "4", "2.02E-04", "0.27485333"], ["", "GOTERM_CC_DIRECT", "GO:0005615∼extracellular space", "20", "1.49E-06", "0.001568694"], ["", "GOTERM_CC_DIRECT", "GO:0016324∼apical plasma membrane", "6", "0.006968923", "7.094816498"], ["", "GOTERM_CC_DIRECT", "GO:0070062∼extracellular exosome", "21", "0.008418185", "8.511744286"], ["", "GOTERM_CC_DIRECT", "GO:0031225∼anchored component of membrane", "4", "0.011341676", "11.31066102"], ["", "GOTERM_CC_DIRECT", "GO:0005764∼lysosome", "5", "0.014100077", "13.88022987"], ["", "GOTERM_MF_DIRECT", "GO:0005242∼inward rectifier potassium channel activity", "3", "0.002416557", "2.873134203"], ["", "GOTERM_MF_DIRECT", "GO:0018479∼benzaldehyde dehydrogenase (NAD +) activity", "2", "0.007332264", "8.48537793"], ["", "GOTERM_MF_DIRECT", "GO:0008900∼hydrogen:potassium-exchanging ATPase activity", "2", "0.010978534", "12.45446088"], ["", "GOTERM_MF_DIRECT", "GO:0001758∼retinal dehydrogenase activity", "2", "0.025432302", "26.68434583"], ["", "GOTERM_MF_DIRECT", "GO:0015280∼ligand-gated sodium channel activity", "2", "0.029013148", "29.86504406"]], "row_count": 31, "column_count": 6, "numeric_cells": 120, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:33193601:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3fee3bc633d252152ba5c9535b567234e94d4141c049808bb111fb6ce2d90d13", "bytes": 1210, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#T4", "version": null, "note": "KEGG pathway analysis of differentially expressed genes in STAD.", "structure": {"pmcid": "PMC7642829", "section_index": 10, "section_title": "DEGs, GO, and KEGG Pathway Analysis in STAD", "row_count": 10, "column_count": 5}, "table": {"label": "TABLE 4", "caption": "KEGG pathway analysis of differentially expressed genes in STAD.", "rows": [["Pathwav ID", "Description", "Count", "P-value", "Genes"], ["hsa04971", "Gastric acid secretion", "7", "2.00E-05", "KCNJ16, KCNJ15, ATP4A, ATP4B, KCNE2, CA2, and SST"], ["hsa04512", "ECM-receptor interaction", "7", "5.46E-05", "COL6A3, COL1A2, COL1 Al, THBS2, COL5A2, SPP1, and FN1"], ["hsa04974", "Protein digestion and absorption", "7", "5.83E-05", "COL6A3, COL1A2, CPA2, COL12A1, COL1A1, COL5A2, and COL10A1"], ["hsa00830", "Retinol metabolism", "5", "0.001520866", "ALDH1A1, RDH12, CYP2C18, ADH7, and UGT2B15"], ["hsa04510", "Focal adhesion", "7", "0.005227439", "COL6A3, COL1A2, COL1 Al, THBS2, COL5A2, SPP1, and FN1"], ["hsa00982", "Drug metabolism – cytochrome P450", "4", "0.016001409", "FM05, ADH7, UGT2B15, and ALDH3A1"], ["hsa04966", "Collecting duct acid secretion", "3", "0.018727092", "ATP4A, ATP4B, and CA2"], ["hsa00980", "Metabolism of xenobiotics by cytochrome P450", "4", "0.020028855", "AKR7A3, ADH7, UGT2B15, and ALDH3A1"], ["hsa05204", "Chemical carcinogenesis", "4", "0.024566639", "CYP2C18, ADH7.UGT2B15, and ALDH3A1"]], "row_count": 10, "column_count": 5, "numeric_cells": 35, "header_rows": 1, "locator": "section[10]/table-wrap[2]#T4"}}, {"id": "asset:table:pmid:33193601:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b538bc617b2106714dbb2a34a100fd41b642eadd203ad4cb80758a456a9d9e16", "bytes": 482, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T5", "version": null, "note": "The central node genes in the PPI network were identified based on the filtering degree ≥10.", "structure": {"pmcid": "PMC7642829", "section_index": 11, "section_title": "DEG PPI and Modular Analysis", "row_count": 15, "column_count": 2}, "table": {"label": "TABLE 5", "caption": "The central node genes in the PPI network were identified based on the filtering degree ≥10.", "rows": [["Node gene", "Degree"], ["COL1A1", "24"], ["COL1A2", "21"], ["FN1", "20"], ["COL5A2", "18"], ["BGN", "16"], ["COL6A3", "16"], ["COL12A1", "15"], ["THBS2", "15"], ["CDH11", "12"], ["SERPINH1", "11"], ["COL10A1", "11"], ["TFF2", "11"], ["ASPN", "11"], ["MUC5AC", "10"]], "row_count": 15, "column_count": 2, "numeric_cells": 17, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T5"}}, {"id": "asset:table:pmid:33193601:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e537eefe01b3118bc2135029426643311f2b2a0e8ae2aaef219394d755afe5b7", "bytes": 479, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T6", "version": null, "note": "Re-analysis of 10 selected genes via the KEGG pathway enrichment.", "structure": {"pmcid": "PMC7642829", "section_index": 12, "section_title": "Core Gene Analysis", "row_count": 3, "column_count": 6}, "table": {"label": "TABLE 6", "caption": "Re-analysis of 10 selected genes via the KEGG pathway enrichment.", "rows": [["Pathway ID", "Term", "Count", "P-value", "Genes", "FDR"], ["XU04512", "ECM-receptor interaction", "6", "1.12E-09", "COL6A3, COL1A2, COL1 Al, THBS2, COL5A2, FN1", "4.28E-07"], ["xtrO4510", "Focal adhesion", "6", "1.19E-07", "COL6A3, COL1A2, COL1 Al, THBS2, COL5A2, FN1", "4.53E-05"]], "row_count": 3, "column_count": 6, "numeric_cells": 8, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T6"}}], "gaps": ["asset:data:geo:GSE13911 not downloaded", "asset:data:geo:GSE13911 licence not read", "asset:data:geo:GSE19826 not downloaded", "asset:data:geo:GSE19826 licence not read", "asset:data:geo:GSE54129 not downloaded", "asset:data:geo:GSE54129 licence not read", "asset:data:geo:GSE65801 not downloaded", "asset:data:geo:GSE65801 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-2", "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-3", "family": null, "specific": null, "label": "GEO2R differential-expression screening using adjusted P-value and log2 fold-change criteria", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Following screening of the data with GEO2R online tools with the cut-off criterion of adjusted P < 0.05 and |log2FC| > 1.5, 1,294, 899, 2,419, and 1,734 DEGs were screened from the four expression profile data, respectively."}}], "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE13911", "GSE19826", "GSE54129", "GSE65801"], "resolved_accessions": ["GSE13911", "GSE19826", "GSE54129", "GSE65801"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: GEO database (https://www.ncbi.nlm.nih.gov/geo), accession numbers: GSE13911, GSE19826, GSE54129, and GSE65801."], "basis": "The paper names GSE13911, GSE19826, GSE54129, GSE65801 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:33193601", "data:geo:GSE13911", "asset:table:pmid:33193601:1", "asset:table:pmid:33193601:2", "asset:table:pmid:33193601:3", "asset:table:pmid:33193601:4", "asset:table:pmid:33193601:5", "asset:table:pmid:33193601:6", "asset:table:pmid:33193601:7"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13911"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:07Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 32224, "completion_tokens": 1855, "cached_tokens": 792}}, "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:33193601", "type": "paper", "label": "pmid:33193601"}, {"id": "source:pmid:33193601", "type": "manuscript", "label": "PMID 33193601 full text"}, {"id": "data:geo:GSE13911", "type": "dataset", "label": "GEO GSE13911"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33193601", "type": "paper", "label": "pmid:33193601"}, {"id": "source:pmid:33193601", "type": "manuscript", "label": "PMID 33193601 full text"}, {"id": "data:geo:GSE13911", "type": "dataset", "label": "GEO GSE13911"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33193601", "type": "extraction", "used": ["source:pmid:33193601"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13911", "type": "accession_resolution", "used": ["data:geo:GSE13911"], "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:33193601", "parent_hash": "sha256:d789ecc571573a38ec2596e1f0324f7daa06f3c96484926a049ca1ddd2f280b6", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE13911 licence not read", "asset:data:geo:GSE13911 not downloaded", "asset:data:geo:GSE19826 licence not read", "asset:data:geo:GSE19826 not downloaded", "asset:data:geo:GSE54129 licence not read", "asset:data:geo:GSE54129 not downloaded", "asset:data:geo:GSE65801 licence not read", "asset:data:geo:GSE65801 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]}