Maftools: efficient and comprehensive analysis of somatic variants in cancer.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30341162", "kind": "science-record", "revision": 2, "content_hash": "sha256:0d309427415bb4772b07ced677466827aaee1374e985549b2aca3a1482c0e0ed", "created_at": "2026-11-01T15:40:38Z", "updated_at": "2026-11-01T18:49:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Maftools: efficient and comprehensive analysis of somatic variants in cancer.", "doi": "10.1101/gr.239244.118", "pmid": "30341162", "authors": ["Anand Mayakonda", "De-Chen Lin", "Yassen Assenov", "Christoph Plass", "H Phillip Koeffler"], "journal": "Genome research", "year": 2018, "abstract": "Numerous large-scale genomic studies of matched tumor-normal samples have established the somatic landscapes of most cancer types. However, the downstream analysis of data from somatic mutations entails a number of computational and statistical approaches, requiring usage of independent software and numerous tools. Here, we describe an R Bioconductor package, Maftools, which offers a multitude of analysis and visualization modules that are commonly used in cancer genomic studies, including driver gene identification, pathway, signature, enrichment, and association analyses. Maftools only requires somatic variants in Mutation Annotation Format (MAF) and is independent of larger alignment files. With the implementation of well-established statistical and computational methods, Maftools facilitates data-driven research and comparative analysis to discover novel results from publicly available data sets. In the present study, using three of the well-annotated cohorts from The Cancer Genome Atlas (TCGA), we describe the application of Maftools to reproduce known results. More importantly, we show that Maftools can also be used to uncover novel findings through integrative analysis.", "claims": [{"id": "claim-data-access", "statement": "All raw input data and reproducible R code used to generate the results are provided as Supplemental Data S1.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30341162", "locator": "sections[14] \"Data sets\" paragraph 2", "quote": "All raw input data and reproducible R code used to generate the results are provided as Supplemental Data S1."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "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:30341162"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30341162", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1101/gr.239244.118", "sha256": "sha256:0ed1f21d12a10ecfbf46c20af43b7d542520f0399e4882a0bef26b493262984d", "bytes": 54617, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1101/gr.239244.118", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6211645", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["All raw input data and reproducible R code used to generate the results are provided as Supplemental Data S1."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:30341162"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:37:14Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 39935, "completion_tokens": 2625, "cached_tokens": 776}}, "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:30341162", "type": "paper", "label": "pmid:30341162"}, {"id": "source:pmid:30341162", "type": "manuscript", "label": "PMID 30341162 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30341162", "type": "paper", "label": "pmid:30341162"}, {"id": "source:pmid:30341162", "type": "manuscript", "label": "PMID 30341162 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30341162", "type": "extraction", "used": ["source:pmid:30341162"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:30341162", "parent_hash": "sha256:ed14d76a5b4952f891fe656bdaef934e8a673237dd397e93d679ad5561395681", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}