EDTox: an R Shiny application to predict the endocrine disruption potential of compounds.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35134136", "kind": "science-record", "revision": 3, "content_hash": "sha256:d3656933b45ea156c1661a26b5682ae0422e20d706d9401e4a492bdf95bfe5c0", "created_at": "2026-11-01T17:36:53Z", "updated_at": "2026-11-01T21:27:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "EDTox: an R Shiny application to predict the endocrine disruption potential of compounds.", "doi": "10.1093/bioinformatics/btac045", "pmid": "35134136", "authors": ["Amirhossein Sakhteman", "Arindam Ghosh", "Vittorio Fortino"], "journal": "Bioinformatics (Oxford, England)", "year": 2022, "abstract": "PURPOSE: Endocrine disruptors are a rising concern due to the wide array of health issues that it can cause. Although there are tools for mode of action (MoA)-based prediction of endocrine disruption (e.g. QSAR Toolbox and iSafeRat), none of them is based on toxicogenomics data. Here, we present EDTox, an R Shiny application enabling users to explore and use a computational method that we have recently published to identify and prioritize endocrine disrupting (ED) chemicals based on toxicogenomic data. The EDTox pipeline utilizes previously trained toxicogenomic-driven classifiers to make predictions on new untested compounds by using their molecular initiating events. Furthermore, the proposed R Shiny app allows users to extend the prediction systems by training and adding new classifiers based on new available toxicogenomic data. This functionality helps users to explore the ED potential of chemicals in new, untested exposure scenarios.\nAVAILABILITY AND IMPLEMENTATION: This tool is available as web application (www.edtox.fi) and stand-alone software on GitHub and Zenodo (https://doi.org/10.5281/zenodo.5817093).\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-method", "statement": "The EDTox pipeline for training the classifier utilizes general linear models (GLMs).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35134136", "locator": "sections[1] \"1 Introduction\" paragraph 7", "quote": "The EDTox pipeline for training the classifier utilizes general linear models (GLMs)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data underlying this article are available in Zenodo at https://doi.org/10.5281/zenodo.5817093, and can be accessed with 10.5281/zenodo.5817093.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35134136", "locator": "sections[7] \"Data Availability\" paragraph 2", "quote": "The data underlying this article are available in Zenodo at https://doi.org/10.5281/zenodo.5817093, and can be accessed with 10.5281/zenodo.5817093."}], "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:35134136"], "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:35134136", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btac045", "sha256": "sha256:e2b5be0eebe34e136dc0dd2a19dd951d5b019f096e32267e806384b51cd80387", "bytes": 13835, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btac045", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8963299", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "general linear models (GLMs)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The EDTox pipeline for training the classifier utilizes general linear models (GLMs)."}}], "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 (general linear models (GLMs)), 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": ["The data underlying this article are available in Zenodo at https://doi.org/10.5281/zenodo.5817093, and can be accessed with 10.5281/zenodo.5817093."], "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:35134136"], "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": "2026-11-01T17:33:21Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 4840, "completion_tokens": 1229, "cached_tokens": 128}}, "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:35134136", "type": "paper", "label": "pmid:35134136"}, {"id": "source:pmid:35134136", "type": "manuscript", "label": "PMID 35134136 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35134136", "type": "paper", "label": "pmid:35134136"}, {"id": "source:pmid:35134136", "type": "manuscript", "label": "PMID 35134136 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35134136", "type": "extraction", "used": ["source:pmid:35134136"], "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:35134136", "parent_hash": "sha256:010a378a60c1aebd4fb03afb26bc47b11a90b1283509bbdcb1924d22e800197f", "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"]}