Identification of marker genes and cell subtypes in castration-resistant prostate cancer cells.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33442423", "kind": "science-record", "revision": 6, "content_hash": "sha256:0172fd9732b8ac5ada6378f0f10cb9f8f132a446df5a0c105d46f1003d55fd8a", "created_at": "2026-11-01T15:41:22Z", "updated_at": "2026-11-01T21:24:30Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of marker genes and cell subtypes in castration-resistant prostate cancer cells.", "doi": "10.7150/jca.49409", "pmid": "33442423", "authors": ["Xiao-Dan Lin", "Ning Lin", "Ting-Ting Lin", "Yu-Peng Wu", "Peng Huang", "Zhi-Bin Ke", "Yun-Zhi Lin", "Shao-Hao Chen", "Qing-Shui Zheng", "Yong Wei", "Xue-Yi Xue", "Rong-Jin Lin", "Ning Xu"], "journal": "Journal of Cancer", "year": 2021, "abstract": "The diverse tumor cell populations may be the critical roles in relapse and resistance to treatment in prostate cancer patients. This study aimed to identify new marker genes and cell subtypes among castration-resistant prostate cancer (CRPC) cells. We downloaded single-cell RNA seq profiles (GSE67980) from the Gene Expression Omnibus (GEO) database. Principal component (PC) analysis and t-Distributed Stochastic Neighbor Embedding (TSNE) analysis were performed to identify marker genes. CRPC cells were clustered and annotated. GO and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses among marker genes were performed. A total of 1500 genes with larger standardized variance were obtained. The top 20 genes were demonstrated in each identified 20 PCs. PC with P-value < 0.05 was selected, including PC1, PC7, PC8, and PC14. The TSNE analysis classified cells as two clusters. The top 6 genes in cluster 0 included HBB, CCL5, SLITRK4, GZMB, BBIP1, and PF4V1. Plus, the top 6 genes in cluster 1 included MLEC, CCT8, CCT3, EPCAM, TMPRSS2, EIF4G2. The GO analysis revealed that these marker genes were mainly enriched in RNA catabolic process, translational initiation, mitochondrial inner membrane, cytosolic part, ribosome, cell adhesion molecule binding, cadherin binding, and structural constituent of ribosome. The KEGG analysis showed that these marker genes mainly enriched in metabolism associated pathways, including carbon metabolism, cysteine and methionine metabolism, propanoate metabolism, pyruvate metabolism, and citrate cycle pathways. To conclude, our results provide essential insights into the spectrum of cellular heterogeneity within human CRPC cells. These marker genes, GO terms and pathways may be critical in the development and progression of human CRPC.", "claims": [{"id": "claim-method", "statement": "t-Distributed Stochastic Neighbor Embedding (TSNE) analysis was performed after PCA.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33442423", "locator": "sections[5] \"TSNE analysis and identification of Marker genes\" paragraph 2", "quote": "t-Distributed Stochastic Neighbor Embedding (TSNE) analysis was performed after PCA."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during the present study was downloaded from the Gene Expression Omnibus (GEO) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33442423", "locator": "sections[15] \"ack\" paragraph 1", "quote": "All data generated or analyzed during the present study was downloaded from the Gene Expression Omnibus (GEO) 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:33442423"], "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:GSE67980"], "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:GSE67980"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33442423", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/jca.49409", "sha256": "sha256:b17e5f4764e6a0a58e912728d86d1f56088c4a304e5b2d55a568a7dbe95f368c", "bytes": 18187, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/jca.49409", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7797644", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE67980", "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=GSE67980", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE67980", "version": null, "note": "All data generated or analyzed during the present study was downloaded from the Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from the Gene Expression Omnibus (GEO) database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1660073", "GSM1660074", "GSM1660075", "GSM1660076", "GSM1660077", "GSM1660078", "GSM1660079", "GSM1660080", "GSM1660081", "GSM1660082", "GSM1660083", "GSM1660084", "GSM1660085", "GSM1660086", "GSM1660087", "GSM1660088", "GSM1660089", "GSM1660090", "GSM1660091", "GSM1660092", "GSM1660093", "GSM1660094", "GSM1660095", "GSM1660096", "GSM1660097", "GSM1660098", "GSM1660099", "GSM1660100", "GSM1660101", "GSM1660102", "GSM1660103", "GSM1660104", "GSM1660105", "GSM1660106", "GSM1660107", "GSM1660108", "GSM1660109", "GSM1660110", "GSM1660111", "GSM1660112", "GSM1660113", "GSM1660114", "GSM1660115", "GSM1660116", "GSM1660117", "GSM1660118", "GSM1660119", "GSM1660120", "GSM1660121", "GSM1660122", "GSM1660123", "GSM1660124", "GSM1660125", "GSM1660126", "GSM1660127", "GSM1660128", "GSM1660129", "GSM1660130", "GSM1660131", "GSM1660132", "GSM1660133", "GSM1660134", "GSM1660135", "GSM1660136", "GSM1660137", "GSM1660138", "GSM1660139", "GSM1660140", "GSM1660141", "GSM1660142", "GSM1660143", "GSM1660144", "GSM1660145", "GSM1660146", "GSM1660147", "GSM1660148", "GSM1660149", "GSM1660150", "GSM1660151", "GSM1660152", "GSM1660153", "GSM1660154", "GSM1660155", "GSM1660156", "GSM1660157", "GSM1660158", "GSM1660159", "GSM1660160", "GSM1660161", "GSM1660162", "GSM1660163", "GSM1660164", "GSM1660165", "GSM1660166", "GSM1660167", "GSM1660168", "GSM1660169", "GSM1660170", "GSM1660171", "GSM1660172", "GSM1660173", "GSM1660174", "GSM1660175", "GSM1660176", "GSM1660177", "GSM1660178", "GSM1660179", "GSM1660180", "GSM1660181", "GSM1660182", "GSM1660183", "GSM1660184", "GSM1660185", "GSM1660186", "GSM1660187", "GSM1660188", "GSM1660189", "GSM1660190", "GSM1660191", "GSM1660192", "GSM1660193", "GSM1660194", "GSM1660195", "GSM1660196", "GSM1660197", "GSM1660198", "GSM1660199", "GSM1660200", "GSM1660201", "GSM1660202", "GSM1660203", "GSM1660204", "GSM1660205", "GSM1660206", "GSM1660207", "GSM1660208", "GSM1660209", "GSM1660210", "GSM1660211", "GSM1660212", "GSM1660213", "GSM1660214", "GSM1660215", "GSM1660216", "GSM1660217", "GSM1660218", "GSM1660219", "GSM1660220", "GSM1660221", "GSM1660222", "GSM1660223", "GSM1660224", "GSM1660225", "GSM1660226", "GSM1660227", "GSM1660228", "GSM1660229", "GSM1660230", "GSM1660231", "GSM1660232", "GSM1660233", "GSM1660234", "GSM1660235", "GSM1660236", "GSM1660237", "GSM1660238", "GSM1660239", "GSM1660240", "GSM1660241"], "sample_count": 169, "group_sizes": null, "group_sizes_basis": null, "platform": "16288", "taxon": "Homo sapiens", "title": "RNA-Seq of Single Prostate CTCs Implicates Non-Canonical Wnt Signaling in Antiandrogen Resistance", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE67980 not downloaded", "asset:data:geo:GSE67980 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": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "PCA"}}, {"id": "method-2", "family": null, "specific": null, "label": "t-Distributed Stochastic Neighbor Embedding (TSNE) analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "t-Distributed Stochastic Neighbor Embedding (TSNE) analysis was performed after PCA."}}], "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": ["GSE67980"], "resolved_accessions": ["GSE67980"], "statements": ["All data generated or analyzed during the present study was downloaded from the Gene Expression Omnibus (GEO) database."], "basis": "The paper names GSE67980 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:33442423", "data:geo:GSE67980"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE67980"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:02Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 13944, "completion_tokens": 743, "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:33442423", "type": "paper", "label": "pmid:33442423"}, {"id": "source:pmid:33442423", "type": "manuscript", "label": "PMID 33442423 full text"}, {"id": "data:geo:GSE67980", "type": "dataset", "label": "GEO GSE67980"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33442423", "type": "paper", "label": "pmid:33442423"}, {"id": "source:pmid:33442423", "type": "manuscript", "label": "PMID 33442423 full text"}, {"id": "data:geo:GSE67980", "type": "dataset", "label": "GEO GSE67980"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33442423", "type": "extraction", "used": ["source:pmid:33442423"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE67980", "type": "accession_resolution", "used": ["data:geo:GSE67980"], "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:33442423", "parent_hash": "sha256:e7f7eebca9b4af522030af0a4d8c8823d7679ecf74d95f2c809eb238878fa494", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE67980 licence not read", "asset:data:geo:GSE67980 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"}]}