Development of a MVI associated HCC prognostic model through single cell transcriptomic analysis and 101 machine learning algorithms.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40055377", "kind": "science-record", "revision": 2, "content_hash": "sha256:33fa4e7199dcbc79837afdd426c6461cda8d4498a2ec98b3734adcca9385daf1", "created_at": "2026-11-01T20:30:16Z", "updated_at": "2026-11-01T21:34:52Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Development of a MVI associated HCC prognostic model through single cell transcriptomic analysis and 101 machine learning algorithms.", "doi": "10.1038/s41598-025-91475-1", "pmid": "40055377", "authors": ["Jiayi Zhang", "Zheng Zhang", "Chenqing Yang", "Qingguang Liu", "Tao Song"], "journal": "Scientific reports", "year": 2025, "abstract": "Hepatocellular carcinoma (HCC) is an exceedingly aggressive form of cancer that often carries a poor prognosis, especially when it is complicated by the presence of microvascular invasion (MVI). Identifying patients at high risk of MVI is crucial for personalized treatment strategies. Utilizing the single-cell RNA-sequencing dataset (GSE242889) of HCC, we identified malignant cell subtypes associated with microvascular invasion (MVI), in conjunction with the TCGA dataset, selected a set of MVI-related genes (MRGs). We developed an optimal prognostic model comprising 11 genes (NOP16, YIPF1, HMMR, NDC80, DYNLL1, CDC34, NLN, KHDRBS3, MED8, SLC35G2, RAB3B) based on MVI-related signature genes by integrating single-cell transcriptomic analysis with 101 machine learning algorithms. This model is meticulously crafted to forecast the prognosis of individuals afflicted with hepatocellular carcinoma (HCC). Additionally, we affirmed the predictive precision and superiority of our model through a meta-analysis against existing HCC models. Furthermore, we explored the differences between high- and low-risk groups through mutation and immune infiltration analyses. Lastly, we investigated immunotherapy responses and drug sensitivities between risk groups, providing novel therapeutic insights for liver cancer.", "claims": [{"id": "claim-method", "statement": "Based on the optimal algorithm determined to be Stepcox(forward) + RSF, we constructed our model.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40055377", "locator": "sections[19] \"Construction, validation, and evaluation of the prognostic model\" paragraph 3", "quote": "Based on the optimal algorithm determined to be Stepcox(forward) + RSF, we constructed our model."}], "state": "complete"}, {"id": "claim-data-access", "statement": "We accessed a comprehensive RNA-sequencing dataset, clinical information and somatic mutation data from the TCGA-LIHC, which obtained directly from the TCGA data repository.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40055377", "locator": "sections[13] \"Data sources\" paragraph 2", "quote": "We accessed a comprehensive RNA-sequencing dataset, clinical information and somatic mutation data from the TCGA-LIHC, which obtained directly from the TCGA data repository."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The optimal Stepcox(forward) + RSF prognostic model achieved an average C-index of 0.835 in the TCGA-LIHC training set and ICGC external validation set.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40055377", "locator": "sections[5] \"Construction, validation, and evaluation of the prognostic model\" paragraph 2", "quote": "The optimal model, Stepcox(forward) + RSF, demonstrated an average C-index of 0.835 (Fig. 3A)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The optimal Stepcox(forward) + RSF prognostic model achieved an average C-index of 0.835 in the TCGA-LIHC training set and ICGC external validation set.", "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:40055377"], "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:GSE242889"], "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:GSE242889"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40055377", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-91475-1", "sha256": "sha256:b0d15602a8f327b3bae3f0cf6b3dc0f079b6a18574ed0fa4d44e46ddabe0ace9", "bytes": 54216, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-91475-1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11889200", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE242889", "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=GSE242889", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE242889", "version": null, "note": "We accessed a comprehensive RNA-sequencing dataset, clinical information and somatic mutation data from the TCGA-LIHC, which obtained directly from the TCGA data repository.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We accessed a comprehensive RNA-sequencing dataset, clinical information and somatic mutation data from the TCGA-LIHC, which obtained directly from the TCGA data repository.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM7774394", "GSM7774395", "GSM7774396", "GSM7774397", "GSM7774398", "GSM7774399", "GSM7774400", "GSM7774401", "GSM7774402", "GSM7774403"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Single-cell dissection of the multicellular ecosystem and molecular feature sunderlying microvascular invasion in hepatocellular carcinoma", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE242889 not downloaded", "asset:data:geo:GSE242889 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-2", "family": null, "specific": null, "label": "Stepwise Cox forward selection combined with Random Survival Forest (Stepcox(forward) + RSF), evaluated using Leave-One-Out Cross-Validation", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Based on the optimal algorithm determined to be Stepcox(forward) + RSF, we constructed our model."}}], "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": ["pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pathway_enrichment."}, "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": ["GSE242889"], "resolved_accessions": ["GSE242889"], "statements": ["We accessed a comprehensive RNA-sequencing dataset, clinical information and somatic mutation data from the TCGA-LIHC, which obtained directly from the TCGA data repository."], "basis": "The paper names GSE242889 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": ["pathway_enrich"], "assets": ["source:pmid:40055377", "data:geo:GSE242889"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE242889"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:47:53Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 14630, "completion_tokens": 1463, "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:40055377", "type": "paper", "label": "pmid:40055377"}, {"id": "source:pmid:40055377", "type": "manuscript", "label": "PMID 40055377 full text"}, {"id": "data:geo:GSE242889", "type": "dataset", "label": "GEO GSE242889"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40055377", "type": "paper", "label": "pmid:40055377"}, {"id": "source:pmid:40055377", "type": "manuscript", "label": "PMID 40055377 full text"}, {"id": "data:geo:GSE242889", "type": "dataset", "label": "GEO GSE242889"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40055377", "type": "extraction", "used": ["source:pmid:40055377"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE242889", "type": "accession_resolution", "used": ["data:geo:GSE242889"], "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:40055377", "parent_hash": "sha256:212d289805663c7456c997465179a70c44e14529e8a64e101ac1d4e4ecc10c13", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE242889 licence not read", "asset:data:geo:GSE242889 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["data.The quality control parameters for the scRNA-seq data were stringent and included the followi", "owing filters: Quality control standards for scRNA-seq data included the following criteria: (1) nC"], "order_basis": "paper_text_order:7138", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["pathway enrichment"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}