ADMET-AI: a machine learning ADMET platform for evaluation of large-scale chemical libraries.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38913862", "kind": "science-record", "revision": 2, "content_hash": "sha256:2464d513f0ddbb07acb3105a6aa33afcd33dddd9705a9ab1485399c3d7826fbd", "created_at": "2026-11-01T20:28:59Z", "updated_at": "2026-11-01T21:33:20Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "ADMET-AI: a machine learning ADMET platform for evaluation of large-scale chemical libraries.", "doi": "10.1093/bioinformatics/btae416", "pmid": "38913862", "authors": ["Kyle Swanson", "Parker Walther", "Jeremy Leitz", "Souhrid Mukherjee", "Joseph C Wu", "Rabindra V Shivnaraine", "James Zou"], "journal": "Bioinformatics (Oxford, England)", "year": 2024, "abstract": "MOTIVATION: The emergence of large chemical repositories and combinatorial chemical spaces, coupled with high-throughput docking and generative AI, have greatly expanded the chemical diversity of small molecules for drug discovery. Selecting compounds for experimental validation requires filtering these molecules based on favourable druglike properties, such as Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET).\nRESULTS: We developed ADMET-AI, a machine learning platform that provides fast and accurate ADMET predictions both as a website and as a Python package. ADMET-AI has the highest average rank on the TDC ADMET Leaderboard, and it is currently the fastest web-based ADMET predictor, with a 45% reduction in time compared to the next fastest public ADMET web server. ADMET-AI can also be run locally with predictions for one million molecules taking just 3.1 h.\nAVAILABILITY AND IMPLEMENTATION: The ADMET-AI platform is freely available both as a web server at admet.ai.greenstonebio.com and as an open-source Python package for local batch prediction at github.com/swansonk14/admet_ai (also archived on Zenodo at doi.org/10.5281/zenodo.10372930). All data and models are archived on Zenodo at doi.org/10.5281/zenodo.10372418.", "claims": [{"id": "claim-method", "statement": "Each server was used to make ADMET predictions for 1, 10, 100, or 1000 molecules from the DrugBank reference (Supplementary Table S3), and the median of three trials was recorded.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38913862", "locator": "sections[10] \"3.4 Comparison to alternatives: speed\" paragraph 3", "quote": "Each server was used to make ADMET predictions for 1, 10, 100, or 1000 molecules from the DrugBank reference (Supplementary Table S3), and the median of three trials was recorded."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data underlying this article are available in Zenodo, at doi.org/10.5281/zenodo.10372418. Data was originally obtained from the Therapeutics Data Commons (v0.4.1) and DrugBank (v5.1.10) and then further processed for this study.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38913862", "locator": "sections[17] \"Data availability\" paragraph 2", "quote": "The data underlying this article are available in Zenodo, at doi.org/10.5281/zenodo.10372418. Data was originally obtained from the Therapeutics Data Commons (v0.4.1) and DrugBank (v5.1.10) and then further processed for this study."}], "state": "complete"}, {"id": "claim-target-result", "statement": "ADMET-AI is the fastest publicly available web server for any number of molecules, with a 45% reduction in time over the next best server for 1000 molecules.", "kind": "quantitative", "target": {"value": 45.0, "unit": "per cent", "tolerance": null, "source": "ADMET-AI is the fastest publicly available web server for any number of molecules, with a 45% reduction in time over the next best server for 1000 molecules (Fig. 1C, left panel)."}, "evidence": [{"asset": "source:pmid:38913862", "locator": "sections[10] \"3.4 Comparison to alternatives: speed\" paragraph 3", "quote": "ADMET-AI is the fastest publicly available web server for any number of molecules, with a 45% reduction in time over the next best server for 1000 molecules (Fig. 1C, left panel)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "ADMET-AI is the fastest publicly available web server for any number of molecules, with a 45% reduction in time over the next best server for 1000 molecules.", "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:38913862"], "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:38913862", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btae416", "sha256": "sha256:d38bec57d2ca393229f55451c370048c19911342ff4468e146a82a1e6833d2fe", "bytes": 18126, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btae416", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11226862", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Median of three trials", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Each server was used to make ADMET predictions for 1, 10, 100, or 1000 molecules from the DrugBank reference (Supplementary Table S3), and the median of three trials was recorded."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": null, "expected_value": 45.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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 (Median of three trials), 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 doi.org/10.5281/zenodo.10372418. Data was originally obtained from the Therapeutics Data Commons (v0.4.1) and DrugBank (v5.1.10) and then further processed for this study."], "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:38913862"], "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": "2026-11-01T19:22:09Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6104, "completion_tokens": 1448, "cached_tokens": 264}}, "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:38913862", "type": "paper", "label": "pmid:38913862"}, {"id": "source:pmid:38913862", "type": "manuscript", "label": "PMID 38913862 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38913862", "type": "paper", "label": "pmid:38913862"}, {"id": "source:pmid:38913862", "type": "manuscript", "label": "PMID 38913862 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38913862", "type": "extraction", "used": ["source:pmid:38913862"], "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:38913862", "parent_hash": "sha256:34b618ddcc1f29f7af93f90da70352d35c133f0d10a16cdf25000f0801eb95c4", "fork_of": null, "generation": 1}, "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"]}