GEInter: an R package for robust gene-environment interaction analysis.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33961050", "kind": "science-record", "revision": 3, "content_hash": "sha256:22d5d9957e54e3e831fa17d8925eb7e765ba2e30edbdff9514785bdf49ab46bc", "created_at": "2026-11-01T17:35:14Z", "updated_at": "2026-11-01T21:25:17Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "GEInter: an R package for robust gene-environment interaction analysis.", "doi": "10.1093/bioinformatics/btab318", "pmid": "33961050", "authors": ["Mengyun Wu", "Xing Qin", "Shuangge Ma"], "journal": "Bioinformatics (Oxford, England)", "year": 2021, "abstract": "SUMMARY: For understanding complex diseases, gene-environment (G-E) interactions have important implications beyond main G and E effects. Most of the existing analysis approaches and software packages cannot accommodate data contamination/long-tailed distribution. We develop GEInter, a comprehensive R package tailored to robust G-E interaction analysis. For both marginal and joint analysis, for data without and with missingness, for continuous and censored survival responses, it comprehensively conducts identification, estimation, visualization and prediction. It can fill an important gap in the existing literature and enjoy broad applicability.\nAVAILABILITY AND IMPLEMENTATION: TCGA data is analyzed as demonstrating examples. It is well known that such data is publicly available https://cran.r-project.org/web/packages/GEInter/.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-method", "statement": "We develop GEInter, a comprehensive R package tailored to robust G–E interaction analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33961050", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We develop GEInter, a comprehensive R package tailored to robust G–E interaction analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "TCGA data is analyzed as demonstrating examples. It is well known that such data is publicly available https://cran.r-project.org/web/packages/GEInter/", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33961050", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "TCGA data is analyzed as demonstrating examples. It is well known that such data is publicly available https://cran.r-project.org/web/packages/GEInter/"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "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:33961050"], "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:33961050", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btab318", "sha256": "sha256:f82191b135f6b3a25689f582c732831fb60a2ccc8690ae2957418a3ccd730ee9", "bytes": 869, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btab318", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8545291", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "GEInter", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We develop GEInter, a comprehensive R package tailored to robust G–E interaction analysis."}}], "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": "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 (GEInter), 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": ["TCGA data is analyzed as demonstrating examples. It is well known that such data is publicly available https://cran.r-project.org/web/packages/GEInter/"], "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:33961050"], "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": "2026-11-01T17:01:57Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 1788, "completion_tokens": 885, "cached_tokens": 256}}, "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:33961050", "type": "paper", "label": "pmid:33961050"}, {"id": "source:pmid:33961050", "type": "manuscript", "label": "PMID 33961050 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33961050", "type": "paper", "label": "pmid:33961050"}, {"id": "source:pmid:33961050", "type": "manuscript", "label": "PMID 33961050 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33961050", "type": "extraction", "used": ["source:pmid:33961050"], "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:33961050", "parent_hash": "sha256:29879e402d6949a146a59191531ba0f0dc9ba49839e142af463718d6347b574d", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}