Integrative analysis of lactylation related genes in prostate cancer: unveiling heterogeneity through single-cell RNA-seq, bulk RNA-seq and machine learning.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40832598", "kind": "science-record", "revision": 2, "content_hash": "sha256:c3e9ab22bf4f2307bd74d51235a8a1a717d65eb24b34f91ce92ab5425c06bd54", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:46Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Integrative analysis of lactylation related genes in prostate cancer: unveiling heterogeneity through single-cell RNA-seq, bulk RNA-seq and machine learning.", "doi": "10.3389/fphar.2025.1634985", "pmid": "40832598", "authors": null, "journal": "Frontiers in pharmacology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 56.0, "unit": "prognostic lrgs", "tolerance": null, "source": "chars 1294-1420 of source sha256 dc78bd4a73aba8d28929bbca22f59d97d6284f88fd5ac1908448041be0f22b69"}, "evidence": [{"asset": "source:pmid:40832598", "locator": "chars 1294-1420 of source sha256 dc78bd4a73aba8d28929bbca22f59d97d6284f88fd5ac1908448041be0f22b69", "quote": "Bulk RNA-seq analysis identified 56 prognostic LRGs, classifying patients into two distinct clusters with divergent prognoses."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40832598"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40832598", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40832598' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40832598", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fphar.2025.1634985", "sha256": "sha256:dc78bd4a73aba8d28929bbca22f59d97d6284f88fd5ac1908448041be0f22b69", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fphar.2025.1634985", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40832598:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fa44fa7972248386423a648b48c339e0a04008eff5e155685f1a306c9cf84eed", "bytes": 1163, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#T1", "version": null, "note": "Primers of top ten LRGs.", "structure": {"pmcid": "PMC12358452", "section_index": 8, "section_title": "Collection of patient samples, RNA extraction, and quantitative real-time PCR", "row_count": 11, "column_count": 3}, "table": {"label": "TABLE 1", "caption": "Primers of top ten LRGs.", "rows": [["Gene symbol", "Primer F", "Primer R"], ["RBM17", "AGT​GGA​GAC​CAG​TGA​CTC​AAA", "CTG​GGG​CGA​GGA​CTG​TAC​T"], ["MTA1", "ACG​CAA​CCC​TGT​CAG​TCT​G", "GGG​CAG​GTC​CAC​CAT​TTC​C"], ["PRAM1", "GCA​GCC​TGA​GTT​GAG​TAC​CTT", "GGC​ACG​GAC​TTC​TTA​GGG​AG"], ["RACGAP1", "ATG​ATG​CTG​AAT​GTG​CGG​AAT", "CGC​CAA​CTG​GAT​AAA​TTG​GAC​TT"], ["VIM", "GAC​GCC​ATC​AAC​ACC​GAG​TT", "CTT​TGT​CGT​TGG​TTA​GCT​GGT"], ["MKI67", "ACG​CCT​GGT​TAC​TAT​CAA​AAG​G", "CAG​ACC​CAT​TTA​CTT​GTG​TTG​GA"], ["MNDA", "AAC​TGA​CAT​CGG​AAG​CAA​GAG", "CCT​GAT​TCG​GAG​TAA​ACG​AAG​TG"], ["CCNA2", "CGC​TGG​CGG​TAC​TGA​AGT​C", "GAG​GAA​CGG​TGA​CAT​GCT​CAT"], ["RBM10", "ATG​GAG​TAT​GAA​AGA​CGT​GGT​GG", "TCC​CGG​TAG​TCG​TGG​TCT​C"], ["KIF2C", "CTG​TTT​CCC​GGT​CTC​GCT​ATC", "AGA​AGC​TGT​AAG​AGT​TCT​GGG​T"]], "row_count": 11, "column_count": 3, "numeric_cells": 3, "header_rows": 1, "locator": "section[8]/table-wrap[1]#T1"}}], "gaps": ["asset:source:pmid:40832598 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40832598", "asset:table:pmid:40832598:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40832598"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "e63a21f345549ad709b852c5d211b9b609266ff768bf60ee9d2aa1c755026c90", "source_hash": "dc78bd4a73aba8d28929bbca22f59d97d6284f88fd5ac1908448041be0f22b69", "raw_response_sha256": "sha256:07ee0635e1f6f8fbafa945bcf4c834c218cdde6119c77ff23c9f486c9884f2b1", "raw_response_chars": 5662}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "1337d71bb11e336de1cc5e4871c4ba0197979aea4407a1e91f3dacccfb0a735a", "source_hash": "dc78bd4a73aba8d28929bbca22f59d97d6284f88fd5ac1908448041be0f22b69", "raw_response_sha256": "sha256:dc301b5c7218c778f27384fe607087f83a84e78bc4ab9618ab7fa69cc2c0c569", "raw_response_chars": 46327}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "abecbb5cea5182b424fc8c457ae3433eb7bdfab58631d5d4de937ff62bef1d74", "source_hash": "dc78bd4a73aba8d28929bbca22f59d97d6284f88fd5ac1908448041be0f22b69", "raw_response": "{\"parent_value\":56,\"unit\":\"prognostic LRGs\",\"evidence\":\"Bulk RNA-seq analysis identified 56 prognostic LRGs, classifying patients into two distinct clusters with divergent prognoses.\",\"target_result\":\"56 prognostic lactylation-related genes were identified.\",\"number_stated\":true}", "reading": {"parent_value": 56, "unit": "prognostic LRGs", "evidence": "Bulk RNA-seq analysis identified 56 prognostic LRGs, classifying patients into two distinct clusters with divergent prognoses.", "target_result": "56 prognostic lactylation-related genes were identified.", "number_stated": true, "source_locator": "chars 1294-1420 of source sha256 dc78bd4a73aba8d28929bbca22f59d97d6284f88fd5ac1908448041be0f22b69"}, "recorded_at": "2026-10-31T15:30:39.149312+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "21315b12d02949b5e8facd00d79d649e91ea04cc7b8e74333261c3b2dfa479ba", "source_hash": "dc78bd4a73aba8d28929bbca22f59d97d6284f88fd5ac1908448041be0f22b69", "raw_response": "<think>We need answer JSON only. Need identify single numerical result replication registered target headline numerical result paper states for main finding. Source has 56 prognostic LRGs likely headline numerical result. Other numbers software 4.4.1, top ten, 5%,2%, IC50, p etc. Main finding explicitly \"Bulk RNA-seq analysis identified 56 prognostic LRGs\". Need evidence exact contiguous quotation containing number, perhaps whole clause attribution. Unit must paper prints. What unit? \"56 prognostic LRGs\" - unit likely \"LRGs\" or \"prognostic LRGs\". Asked unit paper prints. Need parent_value number 56, unit perhaps \"prognostic LRGs\". Evidence exact quote maybe \"Bulk RNA-seq analysis identified 56 prognostic LRGs, classifying patients into two distinct clusters with divergent prognoses.\" This contains number and direct attribution. Headline number only in output target_result likely \"56 prognostic LRGs\". Need make sure no requirement headline number only means target_result value perhaps \"56 prognostic LRGs\". Evidence whole clause if target attached directly. Exact source wording. JSON valid.\n\nCould unit be \"LRGs\" because count. They say unit must be unit paper prints. It prints 56 prognostic LRGs, no \"%\" etc. Use \"prognostic LRGs\". parent_value 56. Evidence exact sentence. target_result \"56 prognostic LRGs\". number_stated true.\n\nNeed perhaps concern \"main finding\" could be prognostic model performance but no numerical AUC given. Thus 56 is clear headline result. Ensure source exact punctuation. Quote: \"Bulk RNA-seq analysis identified 56 prognostic LRGs, classifying patients into two distinct clusters with divergent prognoses.\" Good.\n\nReply JSON object only.</think>\n\n{\"parent_value\":56,\"unit\":\"prognostic LRGs\",\"evidence\":\"Bulk RNA-seq analysis identified 56 prognostic LRGs, classifying patients into two distinct clusters with divergent prognoses.\",\"target_result\":\"56 prognostic LRGs\",\"number_stated\":true}", "reading": {"parent_value": 56, "unit": "prognostic LRGs", "evidence": "Bulk RNA-seq analysis identified 56 prognostic LRGs, classifying patients into two distinct clusters with divergent prognoses.", "target_result": "56 prognostic LRGs", "number_stated": true, "source_locator": "chars 1294-1420 of source sha256 dc78bd4a73aba8d28929bbca22f59d97d6284f88fd5ac1908448041be0f22b69"}, "recorded_at": "2026-10-31T15:30:38.634540+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "56 prognostic lactylation-related genes were identified, and patients were classified into two clusters with divergent prognoses.", "minimax_alt": "56 prognostic lactylation-related genes (LRGs) were identified by bulk RNA-seq analysis.", "decisive": false}, "physical_methods": {"minimax": ["RT-qPCR validation of the mRNA expression levels of the ten signature genes in clinical prostate cancer and adjacent normal samples"], "minimax_alt": ["RT-qPCR on clinical samples to assess mRNA expression of the ten hub genes"], "decisive": false}, "analysis_methods": {"minimax": ["Single-cell RNA sequencing", "Bulk RNA sequencing", "ComBat batch-effect correction", "Unsupervised clustering", "Integrative machine learning for prognostic-signature development", "Univariate and multivariate Cox regression models", "Kaplan-Meier survival analysis", "Log-rank test", "ROC curve analysis and AUC calculation", "Spearman correlation analysis", "Chi-squared test", "Wilcoxon test", "FDR-corrected differential-expression analysis", "Functional enrichment analysis", "Tumor-microenvironment immune-cell infiltration analysis", "OncoPredict-based drug-sensitivity analysis", "Multi-omics analysis using SNV, CNV, methylation, and gene-expression data", "Student's t-test"], "minimax_alt": ["Single-cell RNA sequencing", "Bulk RNA sequencing", "ComBat batch-effect correction", "Unsupervised clustering", "Integrative machine-learning prognostic modeling", "Tumor microenvironment and functional pathway enrichment analyses", "OncoPredict chemosensitivity prediction", "Chi-squared test", "Wilcoxon test", "FDR-corrected differential-expression testing", "Kaplan-Meier survival analysis", "Log-rank test", "Univariate and multivariate Cox regression", "ROC curve analysis and AUC calculation", "Spearman correlation analysis", "GSCA multi-omics analysis", "Student's t-test for qRT-PCR results"], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "passed", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.passed"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:ee423c7785ed9e7a602be7d10f8eac2cd58528b3a96b36d655cda97c9ca965fd", "type": "sep_package", "label": "SEP v1 package for pmid:40832598"}], "activities": [{"id": "activity:conversion:pmid:40832598", "type": "conversion", "used": ["package:ee423c7785ed9e7a602be7d10f8eac2cd58528b3a96b36d655cda97c9ca965fd"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:40832598", "parent_hash": "sha256:45c88dcca16062d2fd9153a0471437f8738c3c3fc8cb2b2104616d21919b1bc0", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40832598 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.passed", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40832598' does not resolve to a declared asset", "targets"]}