Dataset of differentially expressed genes from SOX9 over-expressing NT2/D1 cells.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27656672", "kind": "science-record", "revision": 6, "content_hash": "sha256:a09690693bd23a87b15f3133a35d619788e931c67b97bc96390f16012885e089", "created_at": "2026-11-01T15:40:20Z", "updated_at": "2026-11-01T21:20:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset of differentially expressed genes from SOX9 over-expressing NT2/D1 cells.", "doi": "10.1016/j.dib.2016.08.047", "pmid": "27656672", "authors": ["Louisa Ludbrook", "Dimuthu Alankarage", "Stefan Bagheri-Fam", "Vincent Harley"], "journal": "Data in brief", "year": 2016, "abstract": "The data presents the genes that are differentially up-regulated or down-regulated in response to SOX9 in a human Sertoli-like cell line, NT2/D1. The dataset includes genes that may be implicated in gonad development and are further explored in our associated article, \"SOX9 Regulates Expression of the Male Fertility Gene Ets Variant Factor 5 (ETV5) during Mammalian Sex Development\" (D. lankarage, R. Lavery, T. Svingen, S. Kelly, L.M. Ludbrook, S. Bagheri-Fam, et al., 2016) [1]. The necessity of SOX9 for male sex development is evident in instances where SOX9 is lost, as in 46, XY DSD where patients are sex reversed or in mouse knock-out models, where mice lacking Sox9 are sex reversed. Despite the crucial nature of this transcriptional activator, downstream target genes of SOX9 remain largely undiscovered. Here, we have utilized NT2/D1 cells to transiently over-express SOX9 and performed microarray analysis of the RNA. Microarray data are available in the ArrayExpress database (www.ebi.ac.uk/arrayexpress) under accession number E-MTAB-3378.", "claims": [{"id": "claim-method", "statement": "Gene ontology analysis of the differentially expressed genes was performed using PANTHER Overrepresentation Test and adjusted for multiple testing by Bonferroni correction (GO Ontology database Released 2016-06-22).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27656672", "locator": "sections[8] \"Data annotation\" paragraph 2", "quote": "Gene ontology analysis of the differentially expressed genes was performed using PANTHER Overrepresentation Test and adjusted for multiple testing by Bonferroni correction (GO Ontology database Released 2016-06-22)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Microarray data are available in the ArrayExpress database (www.ebi.ac.uk/arrayexpress) under accession number E-MTAB-3378.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27656672", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Microarray data are available in the ArrayExpress database (www.ebi.ac.uk/arrayexpress) under accession number E-MTAB-3378."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper used the PANTHER Overrepresentation Test with Bonferroni correction for GO analysis, and the source microarray data are available through ArrayExpress under accession E-MTAB-3378.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:27656672", "locator": "sections[8] \"Data annotation\" paragraph 2", "quote": "Gene ontology analysis of the differentially expressed genes was performed using PANTHER Overrepresentation Test and adjusted for multiple testing by Bonferroni correction (GO Ontology database Released 2016-06-22)."}, {"asset": "source:pmid:27656672", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Microarray data are available in the ArrayExpress database (www.ebi.ac.uk/arrayexpress) under accession number E-MTAB-3378."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper used the PANTHER Overrepresentation Test with Bonferroni correction for GO analysis, and the source microarray data are available through ArrayExpress under accession E-MTAB-3378.", "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:27656672"], "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:E-MTAB-3378"], "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:E-MTAB-3378"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27656672", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2016.08.047", "sha256": "sha256:c406951a4e81adc93b2d6791c776c9090057db00c68d5a0fea3811aeff34e005", "bytes": 7045, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2016.08.047", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5021785", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-3378", "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=E-MTAB-3378", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-3378", "version": null, "note": "Microarray data are available in the ArrayExpress database (www.ebi.ac.uk/arrayexpress) under accession number E-MTAB-3378.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray data are available in the ArrayExpress database (www.ebi.ac.uk/arrayexpress) under accession number E-MTAB-3378.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:28:58Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:27656672:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:335afb69187a09c57c589fd53ed00f02aa89fd6c4f0eb324e3b166be6429a8f3", "bytes": 1201, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#t0005", "version": null, "note": "The most affected GO terms from Biological Processes in up-regulated genes and their fold enrichment in SOX9 over-expressing NT2/D1 cells (adjusted p-value≤0.05).", "structure": {"pmcid": "PMC5021785", "section_index": 5, "section_title": "Data", "row_count": 13, "column_count": 4}, "table": {"label": "Table 1", "caption": "The most affected GO terms from Biological Processes in up-regulated genes and their fold enrichment in SOX9 over-expressing NT2/D1 cells (adjusted p-value≤0.05).", "rows": [["Up-regulated genes", "Total #", "Fold enrichment"], ["GO number", "GO terms", "", ""], ["GO:0036498", "IRE1-mediated unfolded protein response", "15", "4.62"], ["GO:0030705", "Cytoskeleton-dependent intracellular transport", "21", "4.07"], ["GO:0000236", "Mitotic prometaphase", "23", "4.01"], ["GO:0002433", "Immune response-regulating cell surface receptor signaling pathway involved in phagocytosis", "19", "3.86"], ["GO:0038096", "Fc-gamma receptor signaling pathway involved in phagocytosis", "19", "3.86"], ["GO:0002431", "Fc receptor mediated stimulatory signaling pathway", "19", "3.77"], ["GO:0038094", "Fc-gamma receptor signaling pathway", "19", "3.68"], ["GO:0010970", "Establishment of localization by movement along microtubule", "20", "3.52"], ["GO:0016241", "Regulation of macroautophagy", "23", "3.45"], ["GO:0000819", "Sister chromatid segregation", "34", "3.33"], ["GO:0016925", "Protein sumoylation", "22", "3.3"]], "row_count": 13, "column_count": 4, "numeric_cells": 33, "header_rows": 2, "locator": "section[5]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:27656672:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:152e8310dc4a17456e4d5465fb0093b4dbb5d96a28011f8887b710dc3b0ffd54", "bytes": 1178, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[2]#t0010", "version": null, "note": "The most affected GO terms from Biological Processes in down-regulated genes and their fold enrichment in SOX9 over-expressing NT2/D1 cells (adjusted p-value≤0.05).", "structure": {"pmcid": "PMC5021785", "section_index": 5, "section_title": "Data", "row_count": 13, "column_count": 4}, "table": {"label": "Table 2", "caption": "The most affected GO terms from Biological Processes in down-regulated genes and their fold enrichment in SOX9 over-expressing NT2/D1 cells (adjusted p-value≤0.05).", "rows": [["Down-regulated genes", "Total #", "Fold enrichment"], ["GO number", "GO terms", "", ""], ["GO:0070125", "Mitochondrial translational elongation", "56", "12.12"], ["GO:0070126", "Mitochondrial translational termination", "55", "11.62"], ["GO:0001682", "tRNA 5′-leader removal", "7", "11.56"], ["GO:0016074", "snoRNA metabolic process", "7", "11.56"], ["GO:0006415", "Translational termination", "56", "11.06"], ["GO:0032543", "Mitochondrial translation", "59", "10.12"], ["GO:0006414", "Translational elongation", "62", "9.01"], ["GO:0042776", "Mitochondrial ATP synthesis coupled proton transport", "9", "8.61"], ["GO:0043624", "Cellular protein complex disassembly", "57", "8.49"], ["GO:0000291", "Nuclear-transcribed mRNA catabolic process, exonucleolytic", "12", "7.03"], ["GO:0043928", "Exonucleolytic nuclear-transcribed mRNA catabolic process involved in deadenylation-dependent decay", "11", "6.89"]], "row_count": 13, "column_count": 4, "numeric_cells": 34, "header_rows": 2, "locator": "section[5]/table-wrap[2]#t0010"}}], "gaps": ["asset:data:geo:E-MTAB-3378 not downloaded", "asset:data:geo:E-MTAB-3378 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "PANTHER Overrepresentation Test, adjusted for multiple testing using Bonferroni correction", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Gene ontology analysis of the differentially expressed genes was performed using PANTHER Overrepresentation Test and adjusted for multiple testing by Bonferroni correction (GO Ontology database Released 2016-06-22)."}}], "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (PANTHER Overrepresentation Test, adjusted for multiple testing using Bonferroni correction), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["E-MTAB-3378"], "resolved_accessions": ["E-MTAB-3378"], "statements": ["Microarray data are available in the ArrayExpress database (www.ebi.ac.uk/arrayexpress) under accession number E-MTAB-3378."], "basis": "The paper names E-MTAB-3378 in ArrayExpress and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:27656672", "data:geo:E-MTAB-3378", "asset:table:pmid:27656672:1", "asset:table:pmid:27656672:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-3378"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:24Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 18704, "completion_tokens": 2976, "cached_tokens": 2104}}, "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:27656672", "type": "paper", "label": "pmid:27656672"}, {"id": "source:pmid:27656672", "type": "manuscript", "label": "PMID 27656672 full text"}, {"id": "data:geo:E-MTAB-3378", "type": "dataset", "label": "GEO E-MTAB-3378"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27656672", "type": "paper", "label": "pmid:27656672"}, {"id": "source:pmid:27656672", "type": "manuscript", "label": "PMID 27656672 full text"}, {"id": "data:geo:E-MTAB-3378", "type": "dataset", "label": "GEO E-MTAB-3378"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27656672", "type": "extraction", "used": ["source:pmid:27656672"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-3378", "type": "accession_resolution", "used": ["data:geo:E-MTAB-3378"], "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:27656672", "parent_hash": "sha256:98155dbee49759d750e1cb11b3f254a00022d7ad1f39be311122e05eaf27b46f", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:E-MTAB-3378 licence not read", "asset:data:geo:E-MTAB-3378 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["XY DSD where patients are sex reversed or in mouse knock-out models, where mice lacking Sox9 ar"], "order_basis": "paper_text_order:666", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["transiently over-express SOX9 and performed microarray analysis of the RNA. Microarray data are ava", "nd performed microarray analysis of the RNA. Microarray data are available in the ArrayExpress datab", "ferentially expressed gene list derived from microarray of SOX9 over-expressing NT2/D1 cells compare"], "order_basis": "paper_text_order:939", "id": "assay:2"}]}