Bioinformatic analysis reveals hub genes and pathways that promote melanoma metastasis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32894090", "kind": "science-record", "revision": 7, "content_hash": "sha256:e9ec78d31ce0e8736ae0a4c595753298e3289b48c2b7106b69271519f872bff0", "created_at": "2026-11-01T15:41:09Z", "updated_at": "2026-11-01T22:02:08Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatic analysis reveals hub genes and pathways that promote melanoma metastasis.", "doi": "10.1186/s12885-020-07372-5", "pmid": "32894090", "authors": ["Wenxing Su", "Yi Guan", "Biao Huang", "Juanjuan Wang", "Yuqian Wei", "Ying Zhao", "Qingqing Jiao", "Jiang Ji", "Daojiang Yu", "Longjiang Xu"], "journal": "BMC cancer", "year": 2020, "abstract": "BACKGROUND: Melanoma has the highest mortality rate of all skin tumors, and metastases are the major cause of death from it. The molecular mechanism leading to melanoma metastasis is currently unclear.\nMETHODS: With the goal of revealing the underlying mechanism, three data sets with accession numbers GSE8401, GSE46517 and GSE7956 were downloaded from the Gene Expression Omnibus (GEO) database. After identifying the differentially expressed gene (DEG) of primary melanoma and metastatic melanoma, three kinds of analyses were performed, namely functional annotation, protein-protein interaction (PPI) network and module construction, and co-expression and drug-gene interaction prediction analysis.\nRESULTS: A total of 41 up-regulated genes and 79 down-regulated genes was selected for subsequent analyses. Results of pathway enrichment analysis showed that extracellular matrix organization and proteoglycans in cancer are closely related to melanoma metastasis. In addition, seven pivotal genes were identified from PPI network, including CXCL8, THBS1, COL3A1, TIMP3, KIT, DCN, and IGFBP5, which have all been verified in the TCGA database and clinical specimens, but only CXCL8, THBS1 and KIT had significant differences in expression.\nCONCLUSIONS: To conclude, CXCL8, THBS1 and KIT may be the hub genes in the metastasis of melanoma and thus may be regarded as therapeutic targets in the future.", "claims": [{"id": "claim-method", "statement": "The adjusted P-value (adj. P-value) using Benjamini and Hochberg false discovery rate were applied to discover statistically significant genes while false-positive results corrected.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32894090", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "The adjusted P-value (adj. P-value) using Benjamini and Hochberg false discovery rate were applied to discover statistically significant genes while false-positive results corrected."}], "state": "complete"}, {"id": "claim-data-access", "statement": "In this study, mRNA microarray datasets were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo) and TCGA (https://tcga-data.nci.nih.gov/tcga/) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32894090", "locator": "sections[23] \"notes\" paragraph 1", "quote": "In this study, mRNA microarray datasets were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo) and TCGA (https://tcga-data.nci.nih.gov/tcga/) database."}], "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:32894090"], "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:GSE46517"], "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:GSE46517"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32894090", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12885-020-07372-5", "sha256": "sha256:08105b2519bddcf879eea4ec164b5ee538a5b15e6aff1ac7b4b8b0c281690a63", "bytes": 27686, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12885-020-07372-5", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7487637", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE46517", "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=GSE46517", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE46517", "version": null, "note": "In this study, mRNA microarray datasets were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo) and TCGA (https://tcga-data.nci.nih.gov/tcga/) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "In this study, mRNA microarray datasets were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo) and TCGA (https://tcga-data.nci.nih.gov/tcga/) database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1131566", "GSM1131567", "GSM1131568", "GSM1131569", "GSM1131570", "GSM1131571", "GSM1131572", "GSM1131573", "GSM1131574", "GSM1131575", "GSM1131576", "GSM1131577", "GSM1131578", "GSM1131579", "GSM1131580", "GSM1131581", "GSM1131582", "GSM1131583", "GSM1131584", "GSM1131585", "GSM1131586", "GSM1131587", "GSM1131588", "GSM1131589", "GSM1131590", "GSM1131591", "GSM1131592", "GSM1131593", "GSM1131594", "GSM1131595", "GSM1131596", "GSM1131597", "GSM1131598", "GSM1131599", "GSM1131600", "GSM1131601", "GSM1131602", "GSM1131603", "GSM1131604", "GSM1131605", "GSM1131606", "GSM1131607", "GSM1131608", "GSM1131609", "GSM1131610", "GSM1131611", "GSM1131612", "GSM1131613", "GSM1131614", "GSM1131615", "GSM1131616", "GSM1131617", "GSM1131618", "GSM1131619", "GSM1131620", "GSM1131621", "GSM1131622", "GSM1131623", "GSM1131624", "GSM1131625", "GSM1131626", "GSM1131627", "GSM1131628", "GSM1131629", "GSM1131630", "GSM1131631", "GSM1131632", "GSM1131633", "GSM1131634", "GSM1131635", "GSM1131636", "GSM1131637", "GSM1131638", "GSM1131639", "GSM1131640", "GSM1131641", "GSM1131642", "GSM1131643", "GSM1131644", "GSM1131645", "GSM1131646", "GSM1131647", "GSM1131648", "GSM1131649", "GSM1131650", "GSM1131651", "GSM1131652", "GSM1131653", "GSM1131654", "GSM1131655", "GSM1131656", "GSM1131657", "GSM1131658", "GSM1131659", "GSM1131660", "GSM1131661", "GSM1131662", "GSM1131663", "GSM1131664", "GSM1131665", "GSM1131666", "GSM1131667", "GSM1131668", "GSM1131669", "GSM1131670", "GSM1131671", "GSM1131672", "GSM1131673", "GSM1131674", "GSM1131675", "GSM1131676", "GSM1131677", "GSM1131678", "GSM1131679", "GSM1131680", "GSM1131681", "GSM1131682", "GSM1131683", "GSM1131684", "GSM1131685", "GSM1131686"], "sample_count": 121, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Human melanoma samples comparing nevi and primary and metastatic melanoma", "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:GSE7956", "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=GSE7956", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7956", "version": null, "note": "In this study, mRNA microarray datasets were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo) and TCGA (https://tcga-data.nci.nih.gov/tcga/) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "In this study, mRNA microarray datasets were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo) and TCGA (https://tcga-data.nci.nih.gov/tcga/) database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM195320", "GSM195321", "GSM195322", "GSM195323", "GSM195324", "GSM195325", "GSM195326", "GSM195327", "GSM195328", "GSM195329", "GSM195330", "GSM195331", "GSM195332", "GSM195333", "GSM195334", "GSM195335", "GSM195336", "GSM195337", "GSM195338", "GSM195339", "GSM195340", "GSM195341", "GSM195342", "GSM195343", "GSM195344", "GSM195345", "GSM195346", "GSM195347", "GSM195348", "GSM195349", "GSM195350", "GSM195351", "GSM195352", "GSM195353", "GSM195354", "GSM195355", "GSM195356", "GSM195357", "GSM195358"], "sample_count": 39, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene Signature for Aggression of Melanoma Metastases - Melanoma Metastasis (LeiFidler)", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE8401", "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=GSE8401", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE8401", "version": null, "note": "In this study, mRNA microarray datasets were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo) and TCGA (https://tcga-data.nci.nih.gov/tcga/) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "In this study, mRNA microarray datasets were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo) and TCGA (https://tcga-data.nci.nih.gov/tcga/) database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM207929", "GSM207930", "GSM207931", "GSM207932", "GSM207933", "GSM207934", "GSM207935", "GSM207936", "GSM207937", "GSM207938", "GSM207939", "GSM207940", "GSM207941", "GSM207942", "GSM207943", "GSM207944", "GSM207945", "GSM207946", "GSM207947", "GSM207948", "GSM207949", "GSM207950", "GSM207951", "GSM207952", "GSM207953", "GSM207954", "GSM207955", "GSM207956", "GSM207957", "GSM207958", "GSM207959", "GSM207960", "GSM207961", "GSM207962", "GSM207963", "GSM207964", "GSM207965", "GSM207966", "GSM207967", "GSM207968", "GSM207969", "GSM207970", "GSM207971", "GSM207972", "GSM207973", "GSM207974", "GSM207975", "GSM207976", "GSM207977", "GSM207978", "GSM207979", "GSM207980", "GSM207981", "GSM207982", "GSM207983", "GSM207984", "GSM207985", "GSM207986", "GSM207987", "GSM207988", "GSM207989", "GSM207990", "GSM207991", "GSM207992", "GSM207993", "GSM207994", "GSM207995", "GSM207996", "GSM207997", "GSM207998", "GSM207999", "GSM208000", "GSM208001", "GSM208002", "GSM208003", "GSM208004", "GSM208005", "GSM208006", "GSM208007", "GSM208008", "GSM208009", "GSM208010", "GSM208011"], "sample_count": 83, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene Signature for Aggression of Melanoma Metastases - Melanoma Metastasis ", "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:32894090:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:411fe9389eb8d9cbd1cfa918b15e6bf8d418b9f801866efb5759af5c62db6b32", "bytes": 1528, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab1", "version": null, "note": "Details of seven hub genes", "structure": {"pmcid": "PMC7487637", "section_index": 13, "section_title": "PPI network construction and hub genes selection and analysis", "row_count": 8, "column_count": 4}, "table": {"label": "Table 1", "caption": "Details of seven hub genes", "rows": [["Gene symbols", "Degrees", "Full names", "Gene function"], ["CXCL8", "17", "C-X-C motif chemokine ligand 8", "This chemokine is a potent angiogenic factor."], ["THBS1", "13", "thrombospondin 1", "This protein has been shown to play roles in platelet aggregation, angiogenesis, and tumorigenesis."], ["COL3A1", "12", "collagen type III alpha 1 chain", "Mutations in this gene are associated with Ehlers-Danlos syndrome types IV, and with aortic and arterial aneurysms."], ["TIMP3", "11", "TIMP metallopeptidase inhibitor 3", "The proteins encoded by this gene family are inhibitors of the matrix metalloproteinases, a group of peptidases involved in degradation of the extracellular matrix (ECM)."], ["KIT", "11", "KIT proto-oncogene receptor tyrosine kinase", "Mutations in this gene are associated with gastrointestinal stromal tumors, mast cell disease, acute myelogenous lukemia and piebaldism."], ["DCN", "10", "decorin", "Binding of this protein to multiple cell surface receptors mediates its role in tumor suppression, including a stimulatory effect on autophagy and inflammation and an inhibitory effect on angiogenesis and tumorigenesis."], ["IGFBP5", "10", "insulin like growth factor binding protein 5", "IGF-binding proteins prolong the half-life of the IGFs and have been shown to either inhibit or stimulate the growth promoting effects of the IGFs on cell culture."]], "row_count": 8, "column_count": 4, "numeric_cells": 12, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab1"}}], "gaps": ["asset:data:geo:GSE46517 not downloaded", "asset:data:geo:GSE46517 licence not read", "asset:data:geo:GSE7956 not downloaded", "asset:data:geo:GSE7956 licence not read", "asset:data:geo:GSE8401 not downloaded", "asset:data:geo:GSE8401 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": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "Benjamini–Hochberg false discovery rate adjustment", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The adjusted P-value (adj. P-value) using Benjamini and Hochberg false discovery rate were applied to discover statistically significant genes while false-positive results corrected."}}], "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": ["GSE8401", "GSE46517", "GSE7956"], "resolved_accessions": ["GSE8401", "GSE46517", "GSE7956"], "statements": ["In this study, mRNA microarray datasets were downloaded from the GEO (http://www.ncbi.nlm.nih.gov/geo) and TCGA (https://tcga-data.nci.nih.gov/tcga/) database."], "basis": "The paper names GSE8401, GSE46517, GSE7956 in Gene Expression Omnibus (GEO) 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:32894090", "data:geo:GSE46517", "asset:table:pmid:32894090:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE46517"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:22:19Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 20673, "completion_tokens": 1539, "cached_tokens": 528}}, "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:32894090", "type": "paper", "label": "pmid:32894090"}, {"id": "source:pmid:32894090", "type": "manuscript", "label": "PMID 32894090 full text"}, {"id": "data:geo:GSE46517", "type": "dataset", "label": "GEO GSE46517"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32894090", "type": "paper", "label": "pmid:32894090"}, {"id": "source:pmid:32894090", "type": "manuscript", "label": "PMID 32894090 full text"}, {"id": "data:geo:GSE46517", "type": "dataset", "label": "GEO GSE46517"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32894090", "type": "extraction", "used": ["source:pmid:32894090"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE46517", "type": "accession_resolution", "used": ["data:geo:GSE46517"], "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:32894090", "parent_hash": "sha256:28202532e76a41c8fb916b4c61b248d643de54ffca5a26d10d46f459f9172bf8", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE46517 licence not read", "asset:data:geo:GSE46517 not downloaded", "asset:data:geo:GSE7956 licence not read", "asset:data:geo:GSE7956 not downloaded", "asset:data:geo:GSE8401 licence not read", "asset:data:geo:GSE8401 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": "analysis_only", "id": "assay:1"}]}