Identification of key genes of human bone marrow stromal cells adipogenesis at an early stage.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32742785", "kind": "science-record", "revision": 7, "content_hash": "sha256:425e884d35e98302358c3210ac8fae9bfcc6f4fb487f6074cdd681f300b41acd", "created_at": "2026-11-01T15:41:06Z", "updated_at": "2026-11-01T22:01:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key genes of human bone marrow stromal cells adipogenesis at an early stage.", "doi": "10.7717/peerj.9484", "pmid": "32742785", "authors": ["Pengyu Chen", "Mingrui Song", "Yutian Wang", "Songyun Deng", "Weisheng Hong", "Xianrong Zhang", "Bin Yu"], "journal": "PeerJ", "year": 2020, "abstract": "BACKGROUND: Bone marrow adipocyte (BMA), closely associated with bone degeneration, shares common progenitors with osteoblastic lineage. However, the intrinsic mechanism of cells fate commitment between BMA and osteogenic lineage remains unclear.\nMETHODS: Gene Expression Omnibus (GEO) dataset GSE107789 publicly available was downloaded and analyzed. Differentially expressed genes (DEGs) were analyzed using GEO2R. Functional and pathway enrichment analyses of Gene Ontology and Kyoto Encyclopedia of Genes and Genomes were conducted by The Database for Annotation, Visualization and Integrated Discovery and Gene set enrichment analysis software. Protein-protein interactions (PPI) network was obtained using STRING database, visualized and clustered by Cytoscape software. Transcriptional levels of key genes were verified by real-time quantitative PCR in vitro in Bone marrow stromal cells (BMSCs) undergoing adipogenic differentiation at day 7 and in vivo in ovariectomized mice model.\nRESULTS: A total of 2,869 DEGs, including 1,357 up-regulated and 1,512 down-regulated ones, were screened out from transcriptional profile of human BMSCs undergoing adipogenic induction at day 7 vs. day 0. Functional and pathway enrichment analysis, combined with modules analysis of PPI network, highlighted ACSL1, sphingosine 1-phosphate receptors 3 (S1PR3), ZBTB16 and glypican 3 as key genes up-regulated at the early stage of BMSCs adipogenic differentiation. Furthermore, up-regulated mRNA expression levels of ACSL1, S1PR3 and ZBTB16 were confirmed both in vitro and in vivo.\nCONCLUSION: ACSL1, S1PR3 and ZBTB16 may play crucial roles in early regulation of BMSCs adipogenic differentiation.", "claims": [{"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:\nThe raw data are available in the Supplemental Files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32742785", "locator": "sections[33] \"Data Availability Statement\" paragraphs 1-3", "quote": "The following information was supplied regarding data availability:\nThe raw data are available in the Supplemental Files."}], "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:32742785"], "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:GSE107789"], "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:GSE107789"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32742785", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.9484", "sha256": "sha256:8798093f4548ce536d734e571dd02d234bd6c4608b814f63525ebc88c51d8112", "bytes": 44212, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.9484", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7380279", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE107789", "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=GSE107789", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE107789", "version": null, "note": "The following information was supplied regarding data availability:\nThe raw data are available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe raw data are available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2879318", "GSM2879319", "GSM2879320", "GSM2879321", "GSM2879322", "GSM2879323"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "14550", "taxon": "Homo sapiens", "title": "Gene expression during adipocytic differentiation of human bone marrow stromal stem 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:32742785:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:389c973c98bef9bbbd6f05dfcb59883b9eca30ec54ee83298cd0ae85d437820e", "bytes": 691, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#table-1", "version": null, "note": "Primer sequences for qRT-PCR.", "structure": {"pmcid": "PMC7380279", "section_index": 10, "section_title": "RNA isolation and real-time quantitative PCR analysis", "row_count": 9, "column_count": 3}, "table": {"label": "Table 1", "caption": "Primer sequences for qRT-PCR.", "rows": [["Gene symbol", "Forward primers", "Reverse primers"], ["GAPDH", "TGTCGTGGAGTCTACTGGTG", "GCATTGCTGACAATCTTGAG"], ["S1PR3", "TTATGTCCGGCAGGAAGACG", "ATCATGGTCAGGTGTCGCTC"], ["ACSL1", "TGCCAGAGCTGATTGACATTC", "GGCATACCAGAAGGTGGTGAG"], ["ZBTB16", "CTGGGACTTTGTGCGATGTG", "CGGTGGAAGAGGATCTCAAACA"], ["GPC3", "CAGCCCGGACTCAAATGGG", "GCCGTGCTGTTAGTTGGTATTTT"], ["ADIPOQ", "GTTCCCAATGTACCCATTCGC", "TGTTGCAGTAGAACTTGCCAG"], ["CEBPA", "TTCGGGTCGCTGGATCTCTA", "TCAAGGAGAAACCACCACGG"], ["PPARG", "TCGCTGATGCACTGCCTATG", "GAGAGGTCCACAGAGCTGATT"]], "row_count": 9, "column_count": 3, "numeric_cells": 1, "header_rows": 1, "locator": "section[10]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:32742785:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c03cda3f100befbd35c50c0ea8c0e1ac7662bebb6322913e1bf7507118500d8e", "bytes": 1285, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#table-2", "version": null, "note": "Pathways enriched in adipogenic induced BMSCs by GSEA analysis.", "structure": {"pmcid": "PMC7380279", "section_index": 16, "section_title": "GSEA enrichment analysis", "row_count": 21, "column_count": 4}, "table": {"label": "Table 2", "caption": "Pathways enriched in adipogenic induced BMSCs by GSEA analysis.", "rows": [["NAME", "NES", "NOM p-value", "FDR q-value"], ["Ribosome", "2.77", "0", "0"], ["Drug metabolism cytochrome p450", "2.01", "0", "0.003"], ["Metabolism of xenobiotics by cytochrome p450", "2", "0", "0.002"], ["Nitrogen metabolism", "1.85", "0", "0.012"], ["Arachidonic acid metabolism", "1.8", "0", "0.02"], ["Glycolysis gluconeogenesis", "1.78", "0", "0.022"], ["Steroid hormone biosynthesis", "1.73", "0", "0.025"], ["PPAR signaling pathway", "1.69", "0", "0.032"], ["Fatty acid metabolism", "1.66", "0", "0.036"], ["Linoleic acid metabolism", "1.65", "0", "0.035"], ["Olfactory transduction", "1.38", "0", "0.146"], ["Sulfur metabolism", "1.77", "0.002", "0.021"], ["Renin angiotensin system", "1.9", "0.002", "0.007"], ["ECM receptor interaction", "1.62", "0.003", "0.04"], ["Lysosome", "1.61", "0.003", "0.039"], ["Cytokine cytokine receptor interaction", "1.44", "0.003", "0.115"], ["Complement and coagulation cascades", "1.66", "0.005", "0.035"], ["Adipocytokine signaling pathway", "1.61", "0.005", "0.039"], ["Glycosaminoglycan biosynthesis chondroitin sulfate", "1.7", "0.007", "0.031"], ["Glutathione metabolism", "1.62", "0.009", "0.041"]], "row_count": 21, "column_count": 4, "numeric_cells": 62, "header_rows": 1, "locator": "section[16]/table-wrap[1]#table-2"}}, {"id": "asset:table:pmid:32742785:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f909cea4baf2bc578e1c6d8c9e027a0c54194e615dda010205273b3f45cb9e65", "bytes": 947, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#table-3", "version": null, "note": "Top five hub proteins in each top three module.", "structure": {"pmcid": "PMC7380279", "section_index": 17, "section_title": "PPI network analysis: hub proteins and PPI module", "row_count": 16, "column_count": 6}, "table": {"label": "Table 3", "caption": "Top five hub proteins in each top three module.", "rows": [["Cluster", "Name", "Degree", "Betweenness centrality", "Closeness centrality", "Log2 (Fold change)"], ["Module 1", "CDK1", "253", "0.022", "0.428", "−2.344"], ["CCNA2", "227", "0.011", "0.421", "−2.726"], ["CCNB1", "226", "0.016", "0.423", "−3.126"], ["AURKA", "216", "0.014", "0.412", "−3.33"], ["AURKB", "215", "0.007", "0.403", "−3.583"], ["Module 2", "CXCL8", "115", "0.017", "0.409", "5.541"], ["CXCL12", "95", "0.009", "0.385", "2.184"], ["DNMT1", "87", "0.009", "0.393", "−2.166"], ["AGT", "83", "0.011", "0.375", "7.155"], ["HIST1H2BK", "80", "0.003", "0.36", "2.13"], ["Module 3", "IL6", "203", "0.086", "0.445", "−2.289"], ["BMP4", "88", "0.015", "0.393", "−3.008"], ["APOB", "79", "0.014", "0.378", "4.305"], ["SPP1", "75", "0.007", "0.397", "5.079"], ["HIST1H4A", "73", "0.004", "0.369", "−2.533"]], "row_count": 16, "column_count": 6, "numeric_cells": 64, "header_rows": 1, "locator": "section[17]/table-wrap[1]#table-3"}}], "gaps": ["asset:data:geo:GSE107789 not downloaded", "asset:data:geo:GSE107789 licence not read"]}, "analysis": {"state": "complete", "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": "PPI"}}, {"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"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["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": ["GSE107789"], "resolved_accessions": ["GSE107789"], "statements": ["The following information was supplied regarding data availability:\nThe raw data are available in the Supplemental Files."], "basis": "The paper names GSE107789 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:32742785", "data:geo:GSE107789", "asset:table:pmid:32742785:1", "asset:table:pmid:32742785:2", "asset:table:pmid:32742785:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE107789"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:07:19Z", "independence": "single_reader"}, "evidence_check": {"method": "absent", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 36060, "completion_tokens": 1455, "cached_tokens": 785}}, "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:32742785", "type": "paper", "label": "pmid:32742785"}, {"id": "source:pmid:32742785", "type": "manuscript", "label": "PMID 32742785 full text"}, {"id": "data:geo:GSE107789", "type": "dataset", "label": "GEO GSE107789"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32742785", "type": "paper", "label": "pmid:32742785"}, {"id": "source:pmid:32742785", "type": "manuscript", "label": "PMID 32742785 full text"}, {"id": "data:geo:GSE107789", "type": "dataset", "label": "GEO GSE107789"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32742785", "type": "extraction", "used": ["source:pmid:32742785"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE107789", "type": "accession_resolution", "used": ["data:geo:GSE107789"], "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:32742785", "parent_hash": "sha256:7b1a441c252f07d3e9780088056680cf27e734f050e62ffebb88238f5a4c40d5", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE107789 licence not read", "asset:data:geo:GSE107789 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ptional levels of key genes were verified by real-time quantitative PCR in vitro in Bone marrow stromal cells (BMSCs"], "order_basis": "paper_text_order:880", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["oing adipogenic differentiation at day 7 and in vivo in ovariectomized mice model. RESULTS: A tot", "and ZBTB16 were confirmed both in vitro and in vivo. CONCLUSION: ACSL1, S1PR3 and ZBTB16 may pla", "d transcripts. Experimental animals C57BL/6J mice were provided by the Experimental Animal Center a", "guidelines of Animal Care and Use Committee. Mice were raised under specific pathogen-free conditio"], "order_basis": "paper_text_order:1004", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["e cell counts and total cell counts of BMSCs cultured in growth medium or adipogenic induction medium"], "order_basis": "paper_text_order:4963", "id": "assay:3"}, {"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": ["PPI"], "order_basis": "consumes_earlier_output", "id": "assay:4"}]}