An Investigation about Gene Modules Associated with hDPSC Differentiation for Adolescents.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31089336", "kind": "science-record", "revision": 6, "content_hash": "sha256:f4ac9f7ccf6e2e401843ae80d992a0ec1a544765546bc72a6e362c228854fcdc", "created_at": "2026-11-01T15:40:45Z", "updated_at": "2026-11-01T21:22:12Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "An Investigation about Gene Modules Associated with hDPSC Differentiation for Adolescents.", "doi": "10.1155/2019/8913287", "pmid": "31089336", "authors": ["Wenjing Xu", "Jianqiang Li", "Juan Li", "Ji-Jiang Yang", "Qing Wang", "Bo Liu", "Weiliang Qiu"], "journal": "Stem cells international", "year": 2019, "abstract": "Dental pulp stem cells (DPSCs) have the property of self-renewal and multidirectional differentiation so that they have the potential for future regenerative therapy of various diseases. The latest breakthrough in the biology of stem cells and the development of regenerative biology provides an effective strategy for regenerative therapy. However, in the medium promoting differentiation during long-term passage, DPSCs would lose their differentiation capability. Some efforts have been made to find genes influencing human DPSC (hDPSC) differentiation based on hDPSCs isolated from adults. However, hDPSC differentiation is a very complex process, which involves multiple genes and multielement interactions. The purpose of this study is to detect sets of correlated genes (i.e., gene modules) that are associated to hDPSC differentiation at the crown-completed stage of the third molars, by using weighted gene coexpression network analysis (WGCNA). Based on the gene expression dataset GSE10444 from Gene Expression Omnibus (GEO), we identified two significant gene modules: yellow module (742 genes) and salmon module (9 genes). The WEB-based Gene SeT AnaLysis Toolkit showed that the 742 genes in the yellow module were enriched in 59 KEGG pathways (including Wnt signaling pathway), while the 9 genes in the salmon module were enriched in one KEGG pathway (neurotrophin signaling pathway). There were 660 (7) genes upregulated at P10 and 82 (2) genes downregulated at P10 in the yellow (salmon) module. Our results provide new insights into the differentiation capability of hDPSCs.", "claims": [{"id": "claim-method", "statement": "We applied WGCNA to the gene microarray dataset GSE10444 downloaded from GEO to investigate the effect of passage on the differentiation of human dental pulp stem cells (hDPSCs) and to construct gene coexpression modules.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31089336", "locator": "sections[9] \"3. Results and Discussion\" paragraph 2", "quote": "We applied WGCNA to the gene microarray dataset GSE10444 downloaded from GEO to investigate the effect of passage on the differentiation of human dental pulp stem cells (hDPSCs) and to construct gene coexpression modules."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The microarray data used to support the findings of this study have been deposited in the GEO repository. Please visit https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10444 (GEO accession number: GSE10444).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31089336", "locator": "sections[12] \"Data Availability\" paragraph 2", "quote": "The microarray data used to support the findings of this study have been deposited in the GEO repository. Please visit https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10444 (GEO accession number: GSE10444)."}], "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:31089336"], "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:GSE10444"], "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": {"n_components": "2: scatter plots of the top 2 principal components (pca plot)"}, "inputs": ["data:geo:GSE10444"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31089336", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2019/8913287", "sha256": "sha256:33d17b93db1347d5c8975a5dde90e52ff9fffb0195d4e2b2e97c128db92842e3", "bytes": 25500, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2019/8913287", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6476005", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10444", "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=GSE10444", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10444", "version": null, "note": "The microarray data used to support the findings of this study have been deposited in the GEO repository. Please visit https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10444 (GEO accession number: GSE10444).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data used to support the findings of this study have been deposited in the GEO repository. Please visit https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10444 (GEO accession number: GSE10444).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM265494", "GSM265495", "GSM265496", "GSM265497", "GSM265498", "GSM265499"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "gene expression levels in long-term cultures of human dental pulp 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:31089336:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2f17d382fd5b8dcc8e9813daa33107a881a10f1be0b9d8acc2d8956f266dbf5d", "bytes": 1270, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#tab1", "version": null, "note": "21 genes enriched in the Wnt signaling pathway in the yellow module.", "structure": {"pmcid": "PMC6476005", "section_index": 9, "section_title": "3. Results and Discussion", "row_count": 22, "column_count": 5}, "table": {"label": "Table 1", "caption": "21 genes enriched in the Wnt signaling pathway in the yellow module.", "rows": [["Index", "User ID", "Gene symbol", "Entrez Gene", "Ensembl"], ["1", "6423", "SFRP2", "6423", "ENSG00000145423"], ["2", "1454", "CSNK1E", "1454", "ENSG00000213923"], ["3", "144165", "PRICKLE1", "144165", "ENSG00000139174"], ["4", "57216", "VANGL2", "57216", "ENSG00000162738"], ["5", "5566", "PRKACA", "5566", "ENSG00000072062"], ["6", "10725", "NFAT5", "10725", "ENSG00000102908"], ["7", "23002", "DAAM1", "23002", "ENSG00000100592"], ["8", "6934", "TCF7L2", "6934", "ENSG00000148737"], ["9", "1387", "CREBBP", "1387", "ENSG00000005339"], ["10", "3725", "JUN", "3725", "ENSG00000177606"], ["11", "5529", "PPP2R5E", "5529", "ENSG00000154001"], ["12", "4087", "SMAD2", "4087", "ENSG00000175387"], ["13", "4775", "NFATC3", "4775", "ENSG00000072736"], ["14", "6424", "SFRP4", "6424", "ENSG00000106483"], ["15", "8312", "AXIN1", "8312", "ENSG00000103126"], ["16", "5534", "PPP3R1", "5534", "ENSG00000221823"], ["17", "6500", "SKP1", "6500", "ENSG00000113558"], ["18", "7473", "WNT3", "7473", "ENSG00000108379"], ["19", "1487", "CTBP1", "1487", "ENSG00000159692"], ["20", "818", "CAMK2G", "818", "ENSG00000148660"], ["21", "815", "CAMK2A", "815", "ENSG00000070808"]], "row_count": 22, "column_count": 5, "numeric_cells": 84, "header_rows": 1, "locator": "section[9]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:31089336:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9fcdbd4220c4753e60af8915f488a66f40b22481b5629f3bd88a4dcd872540c0", "bytes": 702, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#tab2", "version": null, "note": "Nine genes enriched in neurotrophic signaling pathways in salmon module.", "structure": {"pmcid": "PMC6476005", "section_index": 9, "section_title": "3. Results and Discussion", "row_count": 10, "column_count": 5}, "table": {"label": "Table 2", "caption": "Nine genes enriched in neurotrophic signaling pathways in salmon module.", "rows": [["Index", "User ID", "Gene symbol", "Entrez Gene", "Ensembl"], ["1", "817", "CAMK2D", "817", "ENSG00000145349"], ["2", "2889", "RAPGEF1", "2889", "ENSG00000107263"], ["3", "3654", "IRAK1", "3654", "ENSG00000184216"], ["4", "10782", "ZNF274", "10782", "ENSG00000171606"], ["5", "10971", "YWHAQ", "10971", "ENSG00000134308"], ["6", "397", "ARHGDIB", "397", "ENSG00000111348"], ["7", "3845", "KRAS", "3845", "ENSG00000133703"], ["8", "2549", "GAB1", "2549", "ENSG00000109458"], ["9", "27330", "RPS6KA6", "27330", "ENSG00000072133"]], "row_count": 10, "column_count": 5, "numeric_cells": 37, "header_rows": 1, "locator": "section[9]/table-wrap[2]#tab2"}}], "gaps": ["asset:data:geo:GSE10444 not downloaded", "asset:data:geo:GSE10444 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {"n_components": "2: scatter plots of the top 2 principal components (pca plot)"}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "pca"}}, {"id": "method-2", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}, {"id": "method-3", "family": null, "specific": null, "label": "Weighted gene coexpression network analysis (WGCNA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We applied WGCNA to the gene microarray dataset GSE10444 downloaded from GEO to investigate the effect of passage on the differentiation of human dental pulp stem cells (hDPSCs) and to construct gene coexpression modules."}}], "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": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": ["GSE10444"], "resolved_accessions": ["GSE10444"], "statements": ["The microarray data used to support the findings of this study have been deposited in the GEO repository. Please visit https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10444 (GEO accession number: GSE10444)."], "basis": "The paper names GSE10444 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": ["pca_fit"], "assets": ["source:pmid:31089336", "data:geo:GSE10444", "asset:table:pmid:31089336:1", "asset:table:pmid:31089336:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10444"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:41Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 20629, "completion_tokens": 1285, "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:31089336", "type": "paper", "label": "pmid:31089336"}, {"id": "source:pmid:31089336", "type": "manuscript", "label": "PMID 31089336 full text"}, {"id": "data:geo:GSE10444", "type": "dataset", "label": "GEO GSE10444"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31089336", "type": "paper", "label": "pmid:31089336"}, {"id": "source:pmid:31089336", "type": "manuscript", "label": "PMID 31089336 full text"}, {"id": "data:geo:GSE10444", "type": "dataset", "label": "GEO GSE10444"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31089336", "type": "extraction", "used": ["source:pmid:31089336"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10444", "type": "accession_resolution", "used": ["data:geo:GSE10444"], "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:31089336", "parent_hash": "sha256:dda2089d538031b487947657d0fe1286995d01d5f3abc6cf3a106ca10a7044b3", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE10444 licence not read", "asset:data:geo:GSE10444 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["pca"], "order_basis": "analysis_only", "id": "assay:1"}]}