Sarcomatoid-associated gene risk index for clear cell renal cell carcinoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36159988", "kind": "science-record", "revision": 3, "content_hash": "sha256:5471dfe5b65d99de581e8ba686a0581d784aabe152a55496c94f92cc2b73facb", "created_at": "2026-11-01T18:15:27Z", "updated_at": "2026-11-01T21:29:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Sarcomatoid-associated gene risk index for clear cell renal cell carcinoma.", "doi": "10.3389/fgene.2022.985641", "pmid": "36159988", "authors": ["You Zuo", "Shuai Fu", "Zhongwei Zhao", "Zeyan Li", "Yijian Wu", "Tienan Qi", "Jianguo Zheng", "Qinglong Du", "Zhonghua Xu", "Nengwang Yu"], "journal": "Frontiers in genetics", "year": 2022, "abstract": "Sarcomatoid renal cell carcinoma is a de-differentiated form of kidney cancer with an extremely poor prognosis. Genes associated with sarcomatoid differentiation may be closely related to the prognosis of renal cell carcinoma. The prognosis of renal cell carcinoma itself is extremely variable, and a new prognostic model is needed to stratify patients and guide treatment. Data on clear cell renal cell carcinoma with or without sarcomatoid differentiation were obtained from TCGA database, and a sarcomatoid-associated gene risk index (SAGRI) and column line graphs were constructed using sarcomatoid-associated genes. The predictive power of the SAGRI and column line graphs was validated using an internal validation set and an independent validation set (E-MTAB-1980). The SAGRI was constructed using four sarcoma-like differentiation-related genes, COL7A1, LCTL, NPR3, ZFHX4, and had a 1-year AUC value of 0.725 in the training set, 0.712 in the internal validation set, and 0.770 in the independent validation set for TCGA training cohort, with high model reliability. The molecular characteristics among the SAGRI subgroups were analyzed by multiple methods, and results suggested that the SAGRI-HIGH subgroup may benefit more from immunotherapy to improve prognosis. SAGRI satisfactorily predicted the prognosis of patients with clear cell renal cell carcinoma with or without sarcomatoid differentiation.", "claims": [{"id": "claim-method", "statement": "The propensity score matching (PSM) analysis in this study was implemented using the “MatchIt” package (version 4.3.2) in R.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36159988", "locator": "sections[4] \"Identification of genes associated with sarcoma-like differentiation\" paragraph 3", "quote": "The propensity score matching (PSM) analysis in this study was implemented using the “MatchIt” package (version 4.3.2) in R."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material further inquiries can be directed to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36159988", "locator": "sections[17] \"Data availability statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material further inquiries can be directed to the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "SAGRI satisfactorily predicted the prognosis of patients with clear cell renal cell carcinoma with or without sarcomatoid differentiation.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36159988", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "SAGRI satisfactorily predicted the prognosis of patients with clear cell renal cell carcinoma with or without sarcomatoid differentiation."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "SAGRI satisfactorily predicted the prognosis of patients with clear cell renal cell carcinoma with or without sarcomatoid differentiation.", "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:36159988"], "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-1980"], "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-1980"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36159988", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2022.985641", "sha256": "sha256:66b1ff493f1ad2262b2534024aedd7ad4ac2c391376e830628ee03b4f2e1426b", "bytes": 48424, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2022.985641", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9493111", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-1980", "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-1980", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-1980", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material further inquiries can be directed to the corresponding author.", "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": "2026-10-31T18:28:57Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:E-MTAB-1980 not downloaded", "asset:data:geo:E-MTAB-1980 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": null, "specific": null, "label": "Propensity score matching", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The propensity score matching (PSM) analysis in this study was implemented using the “MatchIt” package (version 4.3.2) in R."}}], "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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-1980"], "resolved_accessions": ["E-MTAB-1980"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material further inquiries can be directed to the corresponding author."], "basis": "The paper names E-MTAB-1980 in E-MTAB-1980 cohort and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:36159988", "data:geo:E-MTAB-1980"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-1980"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:06:57Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14329, "completion_tokens": 1237, "cached_tokens": 264}}, "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:36159988", "type": "paper", "label": "pmid:36159988"}, {"id": "source:pmid:36159988", "type": "manuscript", "label": "PMID 36159988 full text"}, {"id": "data:geo:E-MTAB-1980", "type": "dataset", "label": "GEO E-MTAB-1980"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36159988", "type": "paper", "label": "pmid:36159988"}, {"id": "source:pmid:36159988", "type": "manuscript", "label": "PMID 36159988 full text"}, {"id": "data:geo:E-MTAB-1980", "type": "dataset", "label": "GEO E-MTAB-1980"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36159988", "type": "extraction", "used": ["source:pmid:36159988"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-1980", "type": "accession_resolution", "used": ["data:geo:E-MTAB-1980"], "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:36159988", "parent_hash": "sha256:6bfe13e31b143cdccfa6cb87beaeb592886e89bd57d08fe971f87f7636c9e3ed", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:E-MTAB-1980 licence not read", "asset:data:geo:E-MTAB-1980 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]}