E-ABIN: an explainable module for anomaly detection in biological networks.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41133270", "kind": "science-record", "revision": 3, "content_hash": "sha256:636de175ccd2205e6987df53e43c06c4f453700687c92114f14d1ca1fa68a938", "created_at": "2026-11-01T20:31:11Z", "updated_at": "2026-11-01T22:14:53Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "E-ABIN: an explainable module for anomaly detection in biological networks.", "doi": "10.1093/nargab/lqaf135", "pmid": "41133270", "authors": ["Ugo Lomoio", "Tommaso Mazza", "Pierangelo Veltri", "Pietro Hiram Guzzi"], "journal": "NAR genomics and bioinformatics", "year": 2025, "abstract": "The increasing availability of large-scale omics data calls for robust analytical frameworks capable of handling complex gene expression datasets while offering interpretable results. Recent advances in artificial intelligence have enabled the identification of aberrant molecular patterns distinguishing disease states from healthy controls. Coupled with improvements in model interpretability, these tools now support the identification of genes potentially driving disease phenotypes. However, current approaches to gene anomaly detection often remain limited to single datasets and lack accessible graphical interfaces. We introduce E-ABIN, a general-purpose, explainable framework for anomaly detection in biological networks. E-ABIN combines classical machine learning and graph-based deep learning techniques within a unified, user-friendly platform, enabling the detection and interpretation of anomalies from gene expression or methylation-derived networks. By integrating algorithms such as support vector machines, random forests, graph autoencoders, and graph adversarial attributed networks, E-ABIN ensures high predictive accuracy while maintaining interpretability. We demonstrate the utility of E-ABIN through case studies of bladder cancer and celiac disease, where it effectively uncovers biologically relevant anomalies and offers insights into disease mechanisms. E-ABIN is freely available on the Zenodo platform at https://doi.org/10.5281/zenodo.17062501.", "claims": [{"id": "claim-method", "statement": "Receiver Operating Characteristic (ROC) -area under curve (AUC) scores on the test set for all the datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41133270", "locator": "sections[7] \"Results\" paragraph 11", "quote": "Receiver Operating Characteristic (ROC) -area under curve (AUC) scores on the test set for all the datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41133270", "locator": "sections[14] \"Data availability\" paragraph 2", "quote": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Specifically, E-ABIN (LR) and Deep GONet achieve perfect scores (1.0) on GSE37817 and GSE21510 and deliver higher performance than Deep GONet on the other two datasets as well (0.73 versus 0.5909 for GSE11501 and 0.64 versus 0.5 for GSE6613).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41133270", "locator": "sections[8] \"Comparison with state-of-the-art tools\" paragraph 3", "quote": "Specifically, E-ABIN (LR) and Deep GONet achieve perfect scores (1.0) on GSE37817 and GSE21510 and deliver higher performance than Deep GONet on the other two datasets as well (0.73 versus 0.5909 for GSE11501 and 0.64 versus 0.5 for GSE6613)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Specifically, E-ABIN (LR) and Deep GONet achieve perfect scores (1.0) on GSE37817 and GSE21510 and deliver higher performance than Deep GONet on the other two datasets as well (0.73 versus 0.5909 for GSE11501 and 0.64 versus 0.5 for GSE6613).", "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:41133270"], "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": "complete", "blocked_on": null, "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": ["data:geo:GSE11501"], "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": ["data:geo:GSE11501"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41133270", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/nargab/lqaf135", "sha256": "sha256:a3c86e73fea9180d687d50618f10385c49980400b6f3149013a965f47d6eb1eb", "bytes": 34522, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/nargab/lqaf135", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12541387", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE11501", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE11501", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE11501", "version": null, "note": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM289470", "GSM289471", "GSM289472", "GSM289473", "GSM289474", "GSM289475", "GSM289476", "GSM289477", "GSM289478", "GSM289479", "GSM289480", "GSM289481", "GSM289482", "GSM289483", "GSM289484", "GSM289485", "GSM289486", "GSM289487", "GSM289488", "GSM289489", "GSM289490", "GSM289491", "GSM289492", "GSM289493", "GSM289494", "GSM289495", "GSM289496", "GSM289497", "GSM289498", "GSM289499", "GSM289500", "GSM289501", "GSM289502", "GSM289503", "GSM289504", "GSM289505", "GSM289506", "GSM289507", "GSM289508", "GSM289509", "GSM289510", "GSM289511", "GSM289512", "GSM289513", "GSM289514", "GSM289515", "GSM289516", "GSM289517", "GSM289518", "GSM289519", "GSM289520", "GSM289521", "GSM289522", "GSM289523", "GSM289524", "GSM289525", "GSM289526", "GSM289527", "GSM289528", "GSM289529", "GSM289530", "GSM289531", "GSM289532", "GSM289533", "GSM289534", "GSM289535", "GSM289536", "GSM289537", "GSM289538", "GSM289539", "GSM289540", "GSM289541", "GSM289542", "GSM289543", "GSM289544", "GSM289545", "GSM289546", "GSM289547", "GSM289548", "GSM289549", "GSM289550", "GSM289551", "GSM289552", "GSM289553", "GSM289554", "GSM289555", "GSM289556", "GSM289557", "GSM289558", "GSM289559", "GSM289560", "GSM289561", "GSM289562", "GSM289563", "GSM289564", "GSM289565", "GSM289566", "GSM289567", "GSM289568", "GSM289569", "GSM289570", "GSM289571", "GSM289572", "GSM289573", "GSM289574", "GSM289575", "GSM289576", "GSM289577", "GSM289578", "GSM289579", "GSM289580", "GSM289581", "GSM289582", "GSM289583", "GSM289584", "GSM289585", "GSM289586", "GSM289587", "GSM289588", "GSM289589", "GSM289590", "GSM289591", "GSM289592", "GSM289593", "GSM289594", "GSM289595", "GSM289596", "GSM289597", "GSM289598", "GSM289599", "GSM289600", "GSM289601"], "sample_count": 132, "group_sizes": null, "group_sizes_basis": null, "platform": "6104", "taxon": "Homo sapiens", "title": "Primary human leucocyte RNA expression of unrelated celiac disease cases and unrelated healthy controls.", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE21510", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE21510", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21510", "version": null, "note": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM537330", "GSM537331", "GSM537332", "GSM537333", "GSM537334", "GSM537335", "GSM537336", "GSM537337", "GSM537338", "GSM537339", "GSM537340", "GSM537341", "GSM537342", "GSM537343", "GSM537344", "GSM537345", "GSM537346", "GSM537347", "GSM537348", "GSM537349", "GSM537350", "GSM537351", "GSM537352", "GSM537353", "GSM537354", "GSM537355", "GSM537356", "GSM537357", "GSM537358", "GSM537359", "GSM537360", "GSM537361", "GSM537362", "GSM537363", "GSM537364", "GSM537365", "GSM537366", "GSM537367", "GSM537368", "GSM537369", "GSM537370", "GSM537371", "GSM537372", "GSM537373", "GSM537374", "GSM537375", "GSM537376", "GSM537377", "GSM537378", "GSM537379", "GSM537380", "GSM537381", "GSM537382", "GSM537383", "GSM537384", "GSM537385", "GSM537386", "GSM537387", "GSM537388", "GSM537389", "GSM537390", "GSM537391", "GSM537392", "GSM537393", "GSM537394", "GSM537395", "GSM537396", "GSM537397", "GSM537398", "GSM537399", "GSM537400", "GSM537401", "GSM537402", "GSM537403", "GSM537404", "GSM537405", "GSM537406", "GSM537407", "GSM537408", "GSM537409", "GSM537410", "GSM537411", "GSM537412", "GSM537413", "GSM537414", "GSM537415", "GSM537416", "GSM537417", "GSM537418", "GSM537419", "GSM537420", "GSM537421", "GSM537422", "GSM537423", "GSM537424", "GSM537425", "GSM537426", "GSM537427", "GSM537428", "GSM537429", "GSM537430", "GSM537431", "GSM537432", "GSM537433", "GSM549099", "GSM549100", "GSM549101", "GSM549102", "GSM549103", "GSM549104", "GSM549105", "GSM549106", "GSM549107", "GSM549108", "GSM549109", "GSM549110", "GSM549111", "GSM549112", "GSM549113", "GSM549114", "GSM549115", "GSM549116", "GSM549117", "GSM549118", "GSM549119", "GSM549120", "GSM549121", "GSM549122", "GSM549123", "GSM549124", "GSM549125", "GSM549126", "GSM549127", "GSM549128", "GSM549129", "GSM549130", "GSM549131", "GSM549132", "GSM549133", "GSM549134", "GSM549135", "GSM549136", "GSM549137", "GSM549138", "GSM549139", "GSM549140", "GSM549141", "GSM549142"], "sample_count": 148, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Clinical Significance of Osteoprotegerin Expression in Human Colorectal Cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE37817", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE37817", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37817", "version": null, "note": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM340538", "GSM340539", "GSM340541", "GSM340542", "GSM340544", "GSM340545", "GSM340642", "GSM340645", "GSM340651", "GSM340652", "GSM340662", "GSM340663", "GSM340666", "GSM340667", "GSM340682", "GSM340686", "GSM340698", "GSM340710", "GSM340711", "GSM340713", "GSM340717", "GSM340737", "GSM340740", "GSM340749", "GSM928410", "GSM928411", "GSM928412", "GSM928413", "GSM928414", "GSM928415", "GSM928416", "GSM928417", "GSM928418", "GSM928419", "GSM928420", "GSM928421", "GSM928422", "GSM928423", "GSM928424", "GSM928425", "GSM928426", "GSM928427", "GSM928428", "GSM928429", "GSM928430", "GSM928431", "GSM928432", "GSM928433"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "8490;6102", "taxon": "Homo sapiens", "title": "DNA methylation and expression profiling study for bladder cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE6613", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE6613", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6613", "version": null, "note": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Software and user guide are available at https://doi.org/10.5281/zenodo.17062501.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM153404", "GSM153405", "GSM153406", "GSM153407", "GSM153408", "GSM153409", "GSM153410", "GSM153411", "GSM153412", "GSM153413", "GSM153414", "GSM153415", "GSM153416", "GSM153417", "GSM153418", "GSM153419", "GSM153420", "GSM153421", "GSM153422", "GSM153423", "GSM153424", "GSM153425", "GSM153426", "GSM153427", "GSM153428", "GSM153429", "GSM153430", "GSM153431", "GSM153432", "GSM153433", "GSM153434", "GSM153435", "GSM153436", "GSM153437", "GSM153438", "GSM153439", "GSM153440", "GSM153441", "GSM153442", "GSM153443", "GSM153444", "GSM153445", "GSM153446", "GSM153447", "GSM153448", "GSM153449", "GSM153450", "GSM153451", "GSM153452", "GSM153453", "GSM153454", "GSM153455", "GSM153456", "GSM153457", "GSM153458", "GSM153459", "GSM153460", "GSM153461", "GSM153462", "GSM153463", "GSM153464", "GSM153465", "GSM153466", "GSM153467", "GSM153468", "GSM153469", "GSM153470", "GSM153471", "GSM153472", "GSM153473", "GSM153474", "GSM153475", "GSM153476", "GSM153477", "GSM153478", "GSM153479", "GSM153480", "GSM153481", "GSM153482", "GSM153483", "GSM153484", "GSM153485", "GSM153486", "GSM153487", "GSM153488", "GSM153489", "GSM153490", "GSM153491", "GSM153492", "GSM153493", "GSM153494", "GSM153495", "GSM153496", "GSM153497", "GSM153498", "GSM153499", "GSM153500", "GSM153501", "GSM153502", "GSM153503", "GSM153504", "GSM153505", "GSM153506", "GSM153507", "GSM153508"], "sample_count": 105, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Parkinson's disease vs. controls, whole blood", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE11501 not downloaded", "asset:data:geo:GSE11501 licence not read", "asset:data:geo:GSE21510 not downloaded", "asset:data:geo:GSE21510 licence not read", "asset:data:geo:GSE37817 not downloaded", "asset:data:geo:GSE37817 licence not read", "asset:data:geo:GSE6613 not downloaded", "asset:data:geo:GSE6613 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "PCA"}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "support vector machines"}}, {"id": "method-3", "family": null, "specific": null, "label": "Receiver Operating Characteristic (ROC) -area under curve (AUC)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Receiver Operating Characteristic (ROC) -area under curve (AUC) scores on the test set for all the datasets."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": "R1", "reachable": true, "accessions": ["GSE37817", "GSE11501", "GSE21510", "GSE6613"], "resolved_accessions": ["GSE37817", "GSE11501", "GSE21510", "GSE6613"], "statements": ["Software and user guide are available at https://doi.org/10.5281/zenodo.17062501."], "basis": "The paper names GSE37817, GSE11501, GSE21510, GSE6613 in GEO data repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:41133270", "data:geo:GSE11501"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE11501"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:03:55Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8342, "completion_tokens": 2476, "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:41133270", "type": "paper", "label": "pmid:41133270"}, {"id": "source:pmid:41133270", "type": "manuscript", "label": "PMID 41133270 full text"}, {"id": "data:geo:GSE11501", "type": "dataset", "label": "GEO GSE11501"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41133270", "type": "paper", "label": "pmid:41133270"}, {"id": "source:pmid:41133270", "type": "manuscript", "label": "PMID 41133270 full text"}, {"id": "data:geo:GSE11501", "type": "dataset", "label": "GEO GSE11501"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41133270", "type": "extraction", "used": ["source:pmid:41133270"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE11501", "type": "accession_resolution", "used": ["data:geo:GSE11501"], "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:41133270", "parent_hash": "sha256:a5b5b12799e2ffabd361f5aa94de63a1e1426d869d34f83eadaca5451d2f1143", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE11501 licence not read", "asset:data:geo:GSE11501 not downloaded", "asset:data:geo:GSE21510 licence not read", "asset:data:geo:GSE21510 not downloaded", "asset:data:geo:GSE37817 licence not read", "asset:data:geo:GSE37817 not downloaded", "asset:data:geo:GSE6613 licence not read", "asset:data:geo:GSE6613 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["PCA"], "order_basis": "analysis_only", "id": "assay:1"}]}