Integrative eQTL and Mendelian randomization analysis reveals key genes in colorectal cancer.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41252059", "kind": "science-record", "revision": 2, "content_hash": "sha256:a638b1624e91c5c5aa97c22004c518b4f1bcd2316cc85a3b76d09494d5854f5a", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:51Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Integrative eQTL and Mendelian randomization analysis reveals key genes in colorectal cancer.", "doi": "10.1007/s12672-025-03960-8", "pmid": "41252059", "authors": null, "journal": "Discover oncology", "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:41252059"], "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:41252059", "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:41252059' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41252059", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s12672-025-03960-8", "sha256": "sha256:2812b7050a9014c1b825cb76725593c317a836e00972da49919952a5cc93bf75", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s12672-025-03960-8", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41252059:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a84ef2c8d7cad0f23d0d6b9d94797cfc38742be3e24e74982cdca10cad11e20f", "bytes": 425, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "The information of the dataset source in this study", "structure": {"pmcid": "PMC12627289", "section_index": 3, "section_title": "Data sources", "row_count": 4, "column_count": 3}, "table": {"label": "Table 1", "caption": "The information of the dataset source in this study", "rows": [["ID", "Data type", "Contains"], ["TCGA-COAD", "RNA-seq database", "32 normal and 484 tumors"], ["GSE39582", "RNA-seq database", "19 normal and 443 tumors"], ["Finngen_R10_C3_COLORECTAL_EXALLC", "GWAS", "314,193 normal and 6847 tumors"]], "row_count": 4, "column_count": 3, "numeric_cells": 5, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:41252059:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:560ca5967e9e5509b7c619ca20330dc5df3da56d7e61c7dd6efa1638811dd47c", "bytes": 615, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab2", "version": null, "note": "The design primers information", "structure": {"pmcid": "PMC12627289", "section_index": 14, "section_title": "Quantitative real-time PCR (RT-PCR)", "row_count": 9, "column_count": 2}, "table": {"label": "Table 2", "caption": "The design primers information", "rows": [["Primer", "Sequence"], ["MCM6 forward", "5’-GAGGAACTGATTCGTCCTGAGA-3’"], ["MCM6 reverse", "5’-CAAGGCCCGACACAGGTAAG-3’"], ["RAB6B forward", "5’-TGTACGACAGCTTCGACAACA-3’"], ["RAB6B reverse", "5’-CTGCGGAACCTCTCCTGAC-3’"], ["CDC25B forward", "5’-ACGCACCTATCCCTGTCTC-3’"], ["CDC25B reverse", "5’-CTGGAAGCGTCTGATGGCAA-3’"], ["GAPDH forward", "5’-GGAGCGAGATCCCTCCAAAAT-3’"], ["GAPDH reverse", "5’-GGCTGTTGTCATACTTCTCATGG-3’"]], "row_count": 9, "column_count": 2, "numeric_cells": 10, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:41252059:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:71ed4987d9fe01e092a6c9502387e257560a908814616b4d1f80fc249cd09a5c", "bytes": 767, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#Tab3", "version": null, "note": "Sensitivity analyses of critical genes implicated in disease pathogenesis", "structure": {"pmcid": "PMC12627289", "section_index": 18, "section_title": "Mendelian randomization analysis", "row_count": 12, "column_count": 7}, "table": {"label": "Table 3", "caption": "Sensitivity analyses of critical genes implicated in disease pathogenesis", "rows": [["Exposure", "Outcome", "Method", "Heterogeneity", "Horizontal pleiotropy"], ["Q", "Q_p-value", "Egger intercept", "p-value"], ["CDC25B", "CRC", "MR Egger", "4.21", "0.24", "−0.01", "0.68"], ["IVW", "4.50", "0.34", "", ""], ["MCM6", "CRC", "MR Egger", "0.733", "0.69", "−0.03", "0.48"], ["IVW", "1.49", "0.68", "", ""], ["RAB6B", "CRC", "MR Egger", "9.51", "0.39", "0.01", "0.66"], ["IVW", "9.72", "0.47", "", ""], ["RPL13", "CRC", "MR Egger", "0.28", "0.60", "−0.02", "0.60"], ["IVW", "0.79", "0.67", "", ""], ["SPART", "CRC", "MR Egger", "2.33", "0.67", "0.01", "0.98"], ["IVW", "2.33", "0.80", "", ""]], "row_count": 12, "column_count": 7, "numeric_cells": 32, "header_rows": 2, "locator": "section[18]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:41252059:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ab8849adb6e69971aa4bacc5c87bb38a65ab27240531f0e0796499f2062f995e", "bytes": 393, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[2]#Tab4", "version": null, "note": "SMR analysis results", "structure": {"pmcid": "PMC12627289", "section_index": 18, "section_title": "Mendelian randomization analysis", "row_count": 6, "column_count": 4}, "table": {"label": "Table 4", "caption": "SMR analysis results", "rows": [["Gene", "topSNP", "p_HEIDI", "p_SMR_FDR"], ["MCM6", "rs6742283", "0.70", "0.01"], ["RAB6B", "rs2715633", "0.21", "0.02"], ["SPART", "rs35519395", "0.38", "0.03"], ["RPL13", "rs113847672", "0.07", "0.03"], ["CDC25B", "rs1010608", "0.19", "0.01"]], "row_count": 6, "column_count": 4, "numeric_cells": 17, "header_rows": 1, "locator": "section[18]/table-wrap[2]#Tab4"}}, {"id": "asset:table:pmid:41252059:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fb2c15eb87b99db4bbaa9600baf32a956e791b74041efc394231a2f3a815a315", "bytes": 1539, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#Tab5", "version": null, "note": "The GO analysis results", "structure": {"pmcid": "PMC12627289", "section_index": 20, "section_title": "Construction of PPI network and functional enrichment analysis", "row_count": 27, "column_count": 3}, "table": {"label": "Table 5", "caption": "The GO analysis results", "rows": [["ONTOLOGY", "ID", "Description"], ["BP", "GO:1,901,993", "regulation of meiotic cell cycle phase transition"], ["GO:0000727", "double-strand break repair via break-induced replication"], ["GO:0007144", "female meiosis I"], ["GO:0044771", "meiotic cell cycle phase transition"], ["GO:0030174", "regulation of DNA templated DNA replication initiation"], ["GO:1,902,969", "mitotic DNA replication"], ["GO:0006268", "DNA unwinding involved in DNA replication"], ["GO:0051446", "positive regulation of meiotic cell cycle"], ["GO:0010971", "positive regulation of G2/M transition of mitotic cell cycle"], ["GO:0034067", "protein localization to Golgi apparatus"], ["CC", "GO:0071162", "CMG complex"], ["GO:0031261", "DNA replication preinitiation complex"], ["GO:0005793", "endoplasmic reticulum-Golgi intermediate compartment"], ["GO:0000781", "chromosome, telomeric region"], ["GO:0000922", "spindle pole"], ["GO:0000228", "nuclear chromosome"], ["MF", "GO:0043138", "3’−5’ DNA helicase activity"], ["GO:0031489", "myosin V binding"], ["GO:0017116", "single-stranded DNA helicase activity"], ["GO:0003678", "DNA helicase activity"], ["GO:0017022", "myosin binding"], ["GO:0004725", "protein tyrosine phosphatase activity"], ["GO:0003697", "single-stranded DNA binding"], ["GO:0008094", "ATP-dependent activity, acting on DNA"], ["GO:0004386", "helicase activity"], ["GO:0004721", "phosphoprotein phosphatase activity"]], "row_count": 27, "column_count": 3, "numeric_cells": 27, "header_rows": 1, "locator": "section[20]/table-wrap[1]#Tab5"}}], "gaps": ["asset:source:pmid:41252059 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:41252059", "asset:table:pmid:41252059:1", "asset:table:pmid:41252059:2", "asset:table:pmid:41252059:3", "asset:table:pmid:41252059:4", "asset:table:pmid:41252059:5"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41252059"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [], "target_providers": [], "agreement": false, "disagreements": [], "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": [{"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}]}}, {"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", "review.machine_critique.providers"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:ad67179e9a81b8e22bdde39555d4b9840e6688ff97c5480a716cf44bf18154f6", "type": "sep_package", "label": "SEP v1 package for pmid:41252059"}], "activities": [{"id": "activity:conversion:pmid:41252059", "type": "conversion", "used": ["package:ad67179e9a81b8e22bdde39555d4b9840e6688ff97c5480a716cf44bf18154f6"], "agent": "agent:corpus-assay-engine"}], "agents": [{"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:41252059", "parent_hash": "sha256:a7c55546a682086c2ba35214e61961618a186001468d666cff4f262513f83189", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41252059 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers", "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:41252059' does not resolve to a declared asset", "targets"]}