RNA sequencing data of human prostate cancer cells treated with androgens.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31485472", "kind": "science-record", "revision": 8, "content_hash": "sha256:7b795783efca2ee3c3ffb2cb55ba4230e760a23acab47a39979ea803ac4ed4be", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T22:44:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "RNA sequencing data of human prostate cancer cells treated with androgens.", "doi": "10.1016/j.dib.2019.104372", "pmid": "31485472", "authors": ["Raghavendra Tejo Karthik Poluri", "Charles Joly Beauparlant", "Arnaud Droit", "Étienne Audet-Walsh"], "journal": "Data in brief", "year": 2019, "abstract": "Prostate cancer (PCa) is the most frequent cancer in North American men and PCa cells rely on the androgen receptor (AR) for growth and survival. To understand the effect of AR in cancer cells, we have treated LNCaP and LAPC4 cells, two immortalized human PCa cells in vitro, with the synthetic androgen R1881 and then performed RNA-seq analyses. High quality sequencing data have been analyzed using our bioinformatic pipeline which consists of FastQC for quality controls, Trimmomatic for trimming, and Kallisto for pseudoalignment to the transcriptome. Differentially expressed genes were identified using DESeq2 after adjustment for false-discovery rate (FDR q values < 0.05) and Relative Log Expression (RLE) normalization. Gene Set Enrichment Analysis (GSEA) was also performed to identify biological pathways significantly modulated by androgens. GSEA analyses identified the androgen signaling pathway, as well as several metabolic pathways, as significantly enriched following androgen stimulation. These analyses highlight the most significant metabolic pathways up-regulated following AR activation. Raw and processed RNA-seq data were deposited and made publicly available on the Gene Expression Omnibus (GEO; GSE128749). These data have been incorporated in a recent article describing the functions of AR as a master regulator of PCa cell metabolism. For more details about interpretation of these results, please refer to \"Functional genomics studies reveal the androgen receptor as a master regulator of cellular energy metabolism in prostate cancer\" by Gonthier et al. (doi: 10.1016/j.jsbmb.2019.04.016).", "claims": [{"id": "claim-method", "statement": "To study genes regulated by AR in PCa cells, differential expressed genes were identified using a FDR q value < 0.05 with DESeq2 [8].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31485472", "locator": "sections[8] \"Differential gene expression and GSEA analysis\" paragraph 2", "quote": "To study genes regulated by AR in PCa cells, differential expressed genes were identified using a FDR q value < 0.05 with DESeq2 [8]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Both raw and processed RNA-seq data were deposited on the Gene Expression Omnibus (GEO) and made publicly available (GSE128749). https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE128749", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31485472", "locator": "sections[1] \"table-wrap\" paragraph 1", "quote": "Both raw and processed RNA-seq data were deposited on the Gene Expression Omnibus (GEO) and made publicly available (GSE128749). https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE128749"}], "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:31485472"], "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:GSE128749"], "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:GSE128749"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31485472", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.104372", "sha256": "sha256:4a94bd995c92fd6cf648e5f15785d4a8642fca13989a8b5c8e31cfdbf24174e6", "bytes": 10666, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.104372", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6715830", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE128749", "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=GSE128749", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE128749", "version": null, "note": "Both raw and processed RNA-seq data were deposited on the Gene Expression Omnibus (GEO) and made publicly available (GSE128749). https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE128749", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Both raw and processed RNA-seq data were deposited on the Gene Expression Omnibus (GEO) and made publicly available (GSE128749). https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE128749", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3684385", "GSM3684386", "GSM3684387", "GSM3684388", "GSM3684389", "GSM3684391", "GSM3684392", "GSM3684393", "GSM3684394", "GSM3684395", "GSM3684396"], "sample_count": 11, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "RNA sequencing data of human prostate cancer cells treated with androgen", "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:31485472:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9141365078b1fbf98fd07eb0c37b80af3a6ab7b94f8c1a97c2995ff5131095dd", "bytes": 694, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#tbl1", "version": null, "note": "Number of reads for raw and trimmed sequences of PCa cells treated with androgens.", "structure": {"pmcid": "PMC6715830", "section_index": 7, "section_title": "RNA-seq analysis", "row_count": 12, "column_count": 4}, "table": {"label": "Table 1", "caption": "Number of reads for raw and trimmed sequences of PCa cells treated with androgens.", "rows": [["Cell lines", "Treatment", "Reads (Raw)", "Reads (after trimming)"], ["LNCaP", "Control #1", "9327182", "7694732"], ["Control #2", "11058265", "9014786"], ["Control #3", "10258931", "8909738"], ["R1881 #1", "7812714", "6616969"], ["R1881 #2", "9964804", "8508748"], ["R1881 #3", "10496859", "8965255"], ["LAPC4", "Control #1", "8744802", "7390781"], ["Control #2", "6528343", "5443146"], ["Control #3", "10146342", "8641030"], ["R1881 #1", "9384625", "7940193"], ["R1881 #2", "11134285", "9474978"]], "row_count": 12, "column_count": 4, "numeric_cells": 33, "header_rows": 1, "locator": "section[7]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:geo:GSE128749 not downloaded", "asset:data:geo:GSE128749 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To study genes regulated by AR in PCa cells, differential expressed genes were identified using a FDR q value < 0.05 with DESeq2 [8]."}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: deseq2."}, "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": ["GSE128749"], "resolved_accessions": ["GSE128749"], "statements": ["Both raw and processed RNA-seq data were deposited on the Gene Expression Omnibus (GEO) and made publicly available (GSE128749). https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE128749"], "basis": "The paper names GSE128749 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:31485472", "data:geo:GSE128749", "asset:table:pmid:31485472:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE128749"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:03Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 9579, "completion_tokens": 944, "cached_tokens": 777}}, "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:31485472", "type": "paper", "label": "pmid:31485472"}, {"id": "source:pmid:31485472", "type": "manuscript", "label": "PMID 31485472 full text"}, {"id": "data:geo:GSE128749", "type": "dataset", "label": "GEO GSE128749"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31485472", "type": "paper", "label": "pmid:31485472"}, {"id": "source:pmid:31485472", "type": "manuscript", "label": "PMID 31485472 full text"}, {"id": "data:geo:GSE128749", "type": "dataset", "label": "GEO GSE128749"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31485472", "type": "extraction", "used": ["source:pmid:31485472"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE128749", "type": "accession_resolution", "used": ["data:geo:GSE128749"], "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:31485472", "parent_hash": "sha256:d51b8920e6268dd0ea24bbdc0fef7633bda858def75fc365a11b1de86a247f4a", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE128749 licence not read", "asset:data:geo:GSE128749 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["RNA sequencing data of human prostate cancer cells treated", "synthetic androgen R1881 and then performed RNA-seq analyses. High quality sequencing data have", "d following AR activation. Raw and processed RNA-seq data were deposited and made publicly availa", "ing, and Kallisto for pseudoalignment to the transcriptome. Differentially expressed genes were identif"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To study genes regulated by AR in PCa cells, differential expressed genes were identified using a FDR q value < 0.05 with DESeq2 [8]."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}