A risk model of gene signatures for predicting platinum response and survival in ovarian cancer.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35361267", "kind": "science-record", "revision": 5, "content_hash": "sha256:df1445e9c085352b62212fe5b2478f5ed35d00eac7180a7e8bcedb11bbc9b7e0", "created_at": "2026-11-01T18:14:10Z", "updated_at": "2026-11-01T22:48:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A risk model of gene signatures for predicting platinum response and survival in ovarian cancer.", "doi": "10.1186/s13048-022-00969-3", "pmid": "35361267", "authors": ["Siyu Chen", "Yong Wu", "Simin Wang", "Jiangchun Wu", "Xiaohua Wu", "Zhong Zheng"], "journal": "Journal of ovarian research", "year": 2022, "abstract": "BACKGROUND: Ovarian cancer (OC) is the deadliest tumor in the female reproductive tract. And increased resistance to platinum-based chemotherapy represents the major obstacle in the treatment of OC currently. Robust and accurate gene expression models are crucial tools in distinguishing platinum therapy response and evaluating the prognosis of OC patients.\nMETHODS: In this study, 230 samples from The Cancer Genome Atlas (TCGA) OV dataset were subjected to mRNA expression profiling, single nucleotide polymorphism (SNP), and copy number variation (CNV) analysis comprehensively to screen out the differentially expressed genes (DEGs). An SVM classifier and a prognostic model were constructed using the Random Forest algorithm and LASSO Cox regression model respectively via R. The Gene Expression Omnibus (GEO) database was applied as the validation set.\nRESULTS: Forty-eight differentially expressed genes (DEGs) were figured out through integrated analysis of gene expression, single nucleotide polymorphism (SNP), and copy number variation (CNV) data. A 10-gene classifier was constructed which could discriminate platinum-sensitive samples precisely with an AUC of 0.971 in the training set and of 0.926 in the GEO dataset (GSE638855). In addition, 8 optimal genes were further selected to construct the prognostic risk model whose predictions were consistent with the actual survival outcomes in the training cohort (p = 9.613e-05) and validated in GSE638855 (p = 0.04862). PNLDC1, SLC5A1, and SYNM were then identified as hub genes that were associated with both platinum response status and prognosis, which was further validated by the Fudan University Shanghai cancer center (FUSCC) cohort.\nCONCLUSION: These findings reveal a specific risk model that could serve as effective biomarkers to identify patients' platinum response status and predict survival outcomes for OC patients. PNLDC1, SLC5A1, and SYNM are the hub genes that may serve as potential biomarkers in OC treatment.", "claims": [{"id": "claim-method", "statement": "An SVM classifier and a prognostic model were constructed using the Random Forest algorithm and LASSO Cox regression model respectively via R.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35361267", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "An SVM classifier and a prognostic model were constructed using the Random Forest algorithm and LASSO Cox regression model respectively via R."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed in this study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35361267", "locator": "sections[33] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analyzed in this study are available from the corresponding author on reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study developed a 10-gene SVM classifier with AUCs of 0.971 in the training set and 0.926 in the GEO validation set, and an 8-gene prognostic model whose predictions were associated with actual survival in both cohorts.", "kind": "quantitative", "target": {"value": 0.971, "unit": "auc", "tolerance": null, "source": "A 10-gene classifier was constructed which could discriminate platinum-sensitive samples precisely with an AUC of 0.971 in the training set and of 0.926 in the GEO dataset (GSE638855)."}, "evidence": [{"asset": "source:pmid:35361267", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "A 10-gene classifier was constructed which could discriminate platinum-sensitive samples precisely with an AUC of 0.971 in the training set and of 0.926 in the GEO dataset (GSE638855)."}, {"asset": "source:pmid:35361267", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "In addition, 8 optimal genes were further selected to construct the prognostic risk model whose predictions were consistent with the actual survival outcomes in the training cohort (p = 9.613e-05) and validated in GSE638855 (p = 0.04862)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study developed a 10-gene SVM classifier with AUCs of 0.971 in the training set and 0.926 in the GEO validation set, and an 8-gene prognostic model whose predictions were associated with actual survival in both cohorts.", "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:35361267"], "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:GSE63885"], "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:GSE63885"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35361267", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s13048-022-00969-3", "sha256": "sha256:6e3c3e037bcb5122ddee155a90a261407649b11b2ac134f4a841ad94558352b5", "bytes": 52964, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s13048-022-00969-3", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8973612", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE63885", "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=GSE63885", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63885", "version": null, "note": "The datasets used and/or analyzed in this study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed in this study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1559299", "GSM1559300", "GSM1559301", "GSM1559302", "GSM1559303", "GSM1559304", "GSM1559305", "GSM1559306", "GSM1559307", "GSM1559308", "GSM1559309", "GSM1559310", "GSM1559311", "GSM1559312", "GSM1559313", "GSM1559314", "GSM1559315", "GSM1559316", "GSM1559317", "GSM1559318", "GSM1559319", "GSM1559320", "GSM1559321", "GSM1559322", "GSM1559323", "GSM1559324", "GSM1559325", "GSM1559326", "GSM1559327", "GSM1559328", "GSM1559329", "GSM1559330", "GSM1559331", "GSM1559332", "GSM1559333", "GSM1559334", "GSM1559335", "GSM1559336", "GSM1559337", "GSM1559338", "GSM1559339", "GSM1559340", "GSM1559341", "GSM1559342", "GSM1559343", "GSM1559344", "GSM1559345", "GSM1559346", "GSM1559347", "GSM1559348", "GSM1559349", "GSM1559350", "GSM1559351", "GSM1559352", "GSM1559353", "GSM1559354", "GSM1559355", "GSM1559356", "GSM1559357", "GSM1559358", "GSM1559359", "GSM1559360", "GSM1559361", "GSM1559362", "GSM1559363", "GSM1559364", "GSM1559365", "GSM1559366", "GSM1559367", "GSM1559368", "GSM1559369", "GSM1559370", "GSM1559371", "GSM1559372", "GSM1559373", "GSM1559374", "GSM1559375", "GSM1559376", "GSM1559377", "GSM1559378", "GSM1559379", "GSM1559380", "GSM1559381", "GSM1559382", "GSM1559383", "GSM1559384", "GSM1559385", "GSM1559386", "GSM1559387", "GSM1559388", "GSM1559389", "GSM1559390", "GSM1559391", "GSM1559392", "GSM1559393", "GSM1559394", "GSM1559395", "GSM1559396", "GSM1559397", "GSM1559398", "GSM1559399"], "sample_count": 101, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling in ovarian cancer", "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:GSE63885 not downloaded", "asset:data:geo:GSE63885 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "An SVM classifier and a prognostic model were constructed using the Random Forest algorithm and LASSO Cox regression model respectively via R."}}, {"id": "method-2", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Random Forest"}}, {"id": "method-3", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "SVM"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 0.971, "unit": "auc", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE63885"], "resolved_accessions": ["GSE63885"], "statements": ["The datasets used and/or analyzed in this study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE63885 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": ["cox_ph"], "assets": ["source:pmid:35361267", "data:geo:GSE63885"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE63885"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:40:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15370, "completion_tokens": 1980, "cached_tokens": 128}}, "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:35361267", "type": "paper", "label": "pmid:35361267"}, {"id": "source:pmid:35361267", "type": "manuscript", "label": "PMID 35361267 full text"}, {"id": "data:geo:GSE63885", "type": "dataset", "label": "GEO GSE63885"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35361267", "type": "paper", "label": "pmid:35361267"}, {"id": "source:pmid:35361267", "type": "manuscript", "label": "PMID 35361267 full text"}, {"id": "data:geo:GSE63885", "type": "dataset", "label": "GEO GSE63885"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35361267", "type": "extraction", "used": ["source:pmid:35361267"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE63885", "type": "accession_resolution", "used": ["data:geo:GSE63885"], "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:35361267", "parent_hash": "sha256:4a1e1e67b11beda456a781f4cead0fe89093f6e4c15916f2c2bb738a05476c56", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE63885 licence not read", "asset:data:geo:GSE63885 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["An SVM classifier and a prognostic model were constructed using the Random Forest algorithm and LASSO Cox regression model respectively via R."], "order_basis": "analysis_only", "id": "assay:1"}]}