DeepAllo: allosteric site prediction using protein language model (pLM) with multitask learning.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40372465", "kind": "science-record", "revision": 3, "content_hash": "sha256:cda72f5f4f89905ae96905884964a6b46ee3d478e97caef1e85256f17c686eb1", "created_at": "2026-11-01T20:30:31Z", "updated_at": "2026-11-01T22:14:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "DeepAllo: allosteric site prediction using protein language model (pLM) with multitask learning.", "doi": "10.1093/bioinformatics/btaf294", "pmid": "40372465", "authors": ["Moaaz Khokhar", "Ozlem Keskin", "Attila Gursoy"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: Allostery, the process by which binding at one site perturbs a distant site, is being rendered as a key focus in the field of drug development with its substantial impact on protein function. The identification of allosteric pockets (sites) is a challenging task and several techniques have been developed, including Machine Learning to predict allosteric pockets that utilize both static and pocket features.\nRESULTS: Our work, DeepAllo, is the first study that combines fine-tuned protein language model (pLM) with FPocket features and shows an increase in prediction performance of allosteric sites over previous studies. The pLM model was fine-tuned on AlloSteric Database (ASD) in Multitask Learning setting and was further used as a feature extractor to train XGBoost and AutoML models. The best model predicts allosteric pockets with 89.66% F1 score and 90.5% of allosteric pockets in the top 3 positions, outperforming previous results. A case study has been performed on proteins with known allosteric pockets, which shows the proof of our approach. Moreover, an effort was made to explain the pLM by visualizing its attention mechanism among allosteric and non-allosteric residues.\nAVAILABILITY AND IMPLEMENTATION: The source code is available on GitHub (https://github.com/MoaazK/deepallo) and archived on Zenodo (DOI: 10.5281/zenodo.15255379). The trained model is hosted on Hugging Face (DOI: 10.57967/hf/5198). The dataset used for training and evaluation is archived on Zenodo (DOI: 10.5281/zenodo.15255437).", "claims": [{"id": "claim-method", "statement": "As the dataset is highly imbalanced, the performance was evaluated using F1 score mainly but also keeping in mind Precision and Recall.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40372465", "locator": "sections[9] \"3 Experimental evaluation\" paragraph 2", "quote": "As the dataset is highly imbalanced, the performance was evaluated using F1 score mainly but also keeping in mind Precision and Recall."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The source code is available on GitHub (https://github.com/MoaazK/deepallo). The trained model is hosted on Hugging Face (DOI: 10.57967/hf/5198). The dataset used for training and evaluation is archived on Zenodo (DOI: 10.5281/zenodo.15255437).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40372465", "locator": "sections[25] \"Data availability\" paragraph 2", "quote": "The source code is available on GitHub (https://github.com/MoaazK/deepallo). The trained model is hosted on Hugging Face (DOI: 10.57967/hf/5198). The dataset used for training and evaluation is archived on Zenodo (DOI: 10.5281/zenodo.15255437)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The best model predicts allosteric pockets with 89.66% F1 score and 90.5% of allosteric pockets in the top 3 positions, outperforming previous results.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40372465", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "The best model predicts allosteric pockets with 89.66% F1 score and 90.5% of allosteric pockets in the top 3 positions, outperforming previous results."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The best model predicts allosteric pockets with 89.66% F1 score and 90.5% of allosteric pockets in the top 3 positions, outperforming previous results.", "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:40372465"], "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:40372465", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf294", "sha256": "sha256:bfddf7d9d31e95ea76352920dbb4504f5f872056b137d894873cafc67e80f803", "bytes": 29622, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf294", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12145174", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "gradient_boosting", "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": "XGBoost"}}, {"id": "method-2", "family": null, "specific": null, "label": "F1 score", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "As the dataset is highly imbalanced, the performance was evaluated using F1 score mainly but also keeping in mind Precision and Recall."}}], "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": "R1", "expressible": true, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: gradient_boosting."}, "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 source code is available on GitHub (https://github.com/MoaazK/deepallo). The trained model is hosted on Hugging Face (DOI: 10.57967/hf/5198). The dataset used for training and evaluation is archived on Zenodo (DOI: 10.5281/zenodo.15255437)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:40372465"], "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": "2026-11-01T19:52:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9046, "completion_tokens": 1197, "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:40372465", "type": "paper", "label": "pmid:40372465"}, {"id": "source:pmid:40372465", "type": "manuscript", "label": "PMID 40372465 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40372465", "type": "paper", "label": "pmid:40372465"}, {"id": "source:pmid:40372465", "type": "manuscript", "label": "PMID 40372465 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40372465", "type": "extraction", "used": ["source:pmid:40372465"], "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:40372465", "parent_hash": "sha256:639fc95564eba410c97c777e6f0e9c02764c55314b26874261f5f00c9413d9f0", "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"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["XGBoost"], "order_basis": "analysis_only", "id": "assay:1"}]}