Construction and validation of a post-translational modification-related signature to predict the effect of immune therapies in gastric cancer.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40697523", "kind": "science-record", "revision": 2, "content_hash": "sha256:d9b0ae61c97e4f4406d06f2ee5e11932ac324828674ed9ff87cd688f04e8211c", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T14:01:44Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Construction and validation of a post-translational modification-related signature to predict the effect of immune therapies in gastric cancer.", "doi": "10.1016/j.bbrep.2025.102146", "pmid": "40697523", "authors": null, "journal": "Biochemistry and biophysics reports", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "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:40697523"], "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:40697523", "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:40697523' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40697523", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.bbrep.2025.102146", "sha256": "sha256:5db69180381dd4f2008cb2ad8401cdc51fa222a64ee41156d9abbec1a86bfd86", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.bbrep.2025.102146", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40697523:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:751d7114d8387a6adcc1a4708841c09e3eddebd62589c96c403402516a983cfc", "bytes": 628, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tbl1", "version": null, "note": "Primer sequences of the 6 PRGs for qPCR.", "structure": {"pmcid": "PMC12281070", "section_index": 12, "section_title": "Quantitative real-time PCR", "row_count": 13, "column_count": 2}, "table": {"label": "Table 1", "caption": "Primer sequences of the 6 PRGs for qPCR.", "rows": [["Gene", "Sequence (5′–3′)"], ["CUL4A", "F: GCTTGTGTGGAGAAACAGCTATT"], ["R: AAGTCTTGATGTACTCGCTCCAG"], ["KLHL13", "F: ACACGCATCTTTACCAGCAATAC"], ["R: ACCTGTGAACATAGCCTTGAAGT"], ["VHL", "F: CTCCCAGGTCATCTTCTGCAATC"], ["R: GCTTGTTCCTGTCTTTGCATCTG"], ["INCENP", "F: CAGAGTGCCAGGAGGAAGC"], ["R: TCCATGCGCAGGGGAGT"], ["SMC1A", "F: GTATGGACAAGGTGGAGGATGAA"], ["R: CCAGCTCATCCATGTCACCTTTA"], ["RNF144A", "F: TCCATGCGCAGGGGAGT"], ["R: TCTCTAAGATGGCATCACCCT"]], "row_count": 13, "column_count": 2, "numeric_cells": 3, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:40697523:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e384ba46d9efd46c3470311f14f159154e3cff53b29b7f81c9e83601aaa33521", "bytes": 401, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#tbl2", "version": null, "note": "The calculated coefficient of the 6 PRGs.", "structure": {"pmcid": "PMC12281070", "section_index": 17, "section_title": "The PTMs-related prognostic signature: development and validation", "row_count": 7, "column_count": 2}, "table": {"label": "Table 2", "caption": "The calculated coefficient of the 6 PRGs.", "rows": [["Gene", "Coef"], ["CUL4A", "−0.0970192684136801"], ["KLHL13", "0.214780697024463"], ["VHL", "−0.278691818924363"], ["INCENP", "−0.182976184112747"], ["SMC1A", "−0.147765018610833"], ["RNF144A", "0.305558009064573"]], "row_count": 7, "column_count": 2, "numeric_cells": 8, "header_rows": 1, "locator": "section[17]/table-wrap[1]#tbl2"}}], "gaps": ["asset:source:pmid:40697523 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:40697523", "asset:table:pmid:40697523:1", "asset:table:pmid:40697523:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40697523"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "36c9c393c2a94c508844e6d2710e72a0054c5fa5b6a0fb45e75f0ddabb217fe6", "source_hash": "5db69180381dd4f2008cb2ad8401cdc51fa222a64ee41156d9abbec1a86bfd86", "raw_response_sha256": "sha256:dbf74a29812b03d932edc3905e528579cd76fbd9eb75bcfe13849d1a8ef4b1e0", "raw_response_chars": 4687}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "239e33d095e77b80fe87561484c82667b5272cbab381f0f1ea2619f27fdc2480", "source_hash": "5db69180381dd4f2008cb2ad8401cdc51fa222a64ee41156d9abbec1a86bfd86", "raw_response_sha256": "sha256:667db519dce92e29f680b0b267a89271053f0e29df17b4b1e793f2b00805f386", "raw_response_chars": 80705}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "d487032f9ec6c091f777b3b41180c68012dba7f71b4e6db4a75c8fce2c81a0aa", "source_hash": "5db69180381dd4f2008cb2ad8401cdc51fa222a64ee41156d9abbec1a86bfd86", "raw_response": "{\"parent_value\":0.001,\"unit\":\"p\",\"evidence\":\"This signature stratifies patients into high- and low-risk groups with significantly different OS outcomes (p < 0.001).\",\"target_result\":\"p < 0.001\",\"number_stated\":true}", "reading": {"parent_value": 0.001, "unit": "p", "evidence": "This signature stratifies patients into high- and low-risk groups with significantly different OS outcomes (p < 0.001).", "target_result": "p < 0.001", "number_stated": true, "source_locator": "chars 1070-1189 of source sha256 5db69180381dd4f2008cb2ad8401cdc51fa222a64ee41156d9abbec1a86bfd86"}, "recorded_at": "2026-10-31T15:23:24.758073+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "534e2380a015351ac049fbd2084cc92cd76f0e1e5ef7471981f59015c076e9f4", "source_hash": "5db69180381dd4f2008cb2ad8401cdc51fa222a64ee41156d9abbec1a86bfd86", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline for registered target main finding. Source abstract says signature consisting of six prognostic PRGs; high/low OS significantly different p&lt;0.001. \"headline numerical result the paper states for its main finding\" likely six prognostic PRGs? Need parse wording. User asks \"find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated...\" Registered target = headline numerical result paper states for main finding. Main finding signature consisting of six prognostic PRGs. Number is six, unit perhaps \"prognostic PRGs\" or \"genes\"? Evidence exact contiguous quote containing number and attribution whole clause. Could also be p &lt; 0.001, but \"headline numerical result\" could be six genes. Need determine intended benchmark style. They often ask identify numerical result attached target. Here main finding likely \"PTM-related prognostic signature consisting of six prognostic PRGs\". Replication must reproduce number six. Unit paper prints? It prints \"six prognostic PRGs\" perhaps unit \"prognostic PRGs\". parent_value numeric 6. Evidence exact quote entire sentence perhaps. Target_result should state. number_stated true.\n\nCould p &lt;0.001 be headline numerical result? The wording \"single numerical result\" and target generic. Paper title/main finding. The abstract explicitly reports developed signature \"consisting of six prognostic PRGs\". That's a headline number. Another numerical p value. Which one is \"headline numerical result the paper states for its main finding\"? likely count of genes. Need perhaps evidence exact contiguous sentence:\n\"Using LASSO and Cox regression analyses, we developed a PTM-related prognostic signature consisting of six prognostic PRGs in the TCGA-STAD cohort, and we validated this signature in the independent GSE62254 dataset.\"\nUnit: \"prognostic PRGs\". Target_result: \"The PTM-related prognostic signature consists of six prognostic PRGs.\" They ask \"headline number only\" likely parent_value 6. Unit must printed unit. \"six prognostic PRGs\" yes. Evidence perhaps exact clause. No issue.\n\nBut let's deeply inspect possible expectation from source. User's target phrasing likely generated to ask a specific number without explicitly naming target, requiring extraction. \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\". There are several numerical results: three molecular subtypes; six PRGs; p&lt;0.001; OS outcomes; TMB etc. \"headline numerical result\" likely six because main model signature. Need choose.\n\nCould \"number stated\" as false because no explicit headline numerical result? Yet likely not. They say if no number for registered target. There is six in abstract. Replication of signature has to reproduce six genes. So yes.\n\nUnit exact printed unit perhaps \"prognostic PRGs\" rather than \"genes\". The source sentence: \"signature consisting of six prognostic PRGs\". Unit could be \"prognostic PRGs\". They insist unit must be unit paper prints. Better use \"prognostic PRGs\". parent_value 6.\n\nEvidence exact contiguous quotation, no shorten. We can quote full sentence. Should evidence contain \"six\" spelled word, not numeric digit. They want number value paper states; parent numeric. Exact quote contains number. Fine. Could quote just clause \"we developed...\" but attribution. Full sentence safest.\n\ntarget_result perhaps \"The PTM-related prognostic signature consists of six prognostic PRGs.\" Yet \"headline number only\" perhaps they want target_result to describe number. Schema mandates string. We can say \"6 prognostic PRGs\". Is that reporting headline number only. likely. Need JSON valid no markdown.</think>\n\n{\"parent_value\":6,\"unit\":\"prognostic PRGs\",\"evidence\":\"Using LASSO and Cox regression analyses, we developed a PTM-related prognostic signature consisting of six prognostic PRGs in the TCGA-STAD cohort, and we validated this signature in the independent GSE62254 dataset.\",\"target_result\":\"6 prognostic PRGs\",\"number_stated\":true}", "reading": {"parent_value": 6, "unit": "prognostic PRGs", "evidence": "Using LASSO and Cox regression analyses, we developed a PTM-related prognostic signature consisting of six prognostic PRGs in the TCGA-STAD cohort, and we validated this signature in the independent GSE62254 dataset.", "target_result": "6 prognostic PRGs", "number_stated": true, "source_locator": "chars 758-974 of source sha256 5db69180381dd4f2008cb2ad8401cdc51fa222a64ee41156d9abbec1a86bfd86"}, "recorded_at": "2026-10-31T15:23:07.234015+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A six-gene PTM-related prognostic signature stratified gastric cancer patients into high- and low-risk groups with significantly different overall survival outcomes (p < 0.001).", "minimax_alt": "This signature stratifies patients into high- and low-risk groups with significantly different OS outcomes (p < 0.001).", "decisive": false}, "analysis_methods": {"minimax": ["LASSO regression", "Cox regression", "clustering analysis", "Kaplan-Meier survival analysis", "Spearman correlation analysis", "Gene Ontology enrichment analysis", "Kyoto Encyclopedia of Genes and Genomes enrichment analysis", "Gene Set Enrichment Analysis"], "minimax_alt": ["LASSO", "Cox regression", "clustering analysis", "Gene Ontology (GO) analysis", "Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis", "Gene Set Enrichment Analysis (GSEA)", "Spearman test", "WilcoxTest", "Kaplan-Meier (KM) survival analysis", "stratified survival analysis"], "decisive": false}, "statistical_method": {"minimax": "LASSO and Cox regression analyses", "minimax_alt": "", "decisive": true}, "parent_value": {"minimax": 0.001, "minimax_alt": 6, "decisive": true}, "unit": {"minimax": "p", "minimax_alt": "prognostic PRGs", "decisive": true}}, "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": "blocked", "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.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:41ad2feaf23b0dc85811420943d65fcbc9254a73e56f01896a16314593662802", "type": "sep_package", "label": "SEP v1 package for pmid:40697523"}], "activities": [{"id": "activity:conversion:pmid:40697523", "type": "conversion", "used": ["package:41ad2feaf23b0dc85811420943d65fcbc9254a73e56f01896a16314593662802"], "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:40697523", "parent_hash": "sha256:051e82636679b54937cde336f5ccfaf1bb6140b451bb13e61bf9d50e8c06356b", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40697523 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "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:40697523' does not resolve to a declared asset", "targets"]}