Multistage attention-based extraction and fusion of protein sequence and structural features for protein function prediction.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40569190", "kind": "science-record", "revision": 3, "content_hash": "sha256:76703f9d33c6039ece842afd611862dc7272b0d2daa4a0ea4c16690eabcd37c1", "created_at": "2026-11-01T20:30:39Z", "updated_at": "2026-11-01T22:14:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Multistage attention-based extraction and fusion of protein sequence and structural features for protein function prediction.", "doi": "10.1093/bioinformatics/btaf374", "pmid": "40569190", "authors": ["Meiling Liu", "Shuangshuang Wang", "Zeyu Luo", "Guohua Wang", "Yuming Zhao"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: Protein function prediction is important for drug development and disease treatment. Recently, deep learning methods have leveraged protein sequence and structural information, achieving remarkable progress in the field of protein function prediction. However, existing methods ignore the complex multimodal interaction information between sequence and structural features. Since protein sequence and structural information reveal the functional characteristics of proteins from different perspectives, it is challenging to effectively fuse the information from these two modalities to portray protein functions more comprehensively. In addition, current methods have difficulty in effectively capturing long-range dependencies and global contextual information in protein sequences during feature extraction, thus limiting the ability of the model to recognize critical functional residues.\nRESULTS: In this study, we propose a novel framework termed Multi-stage Attention-based Extraction and Fusion model for GO prediction (MAEF-GO) based on a multistage attention mechanism to predict protein functions. MAEF-GO innovatively integrates the graph convolutional network and the graph attention network to extract protein structural features. To address the issue of modeling long-range dependencies within protein sequences, we introduce a frequency-domain attention mechanism capable of extracting global contextual relationships. Additionally, a cross-attention module is implemented to facilitate interactive fusion between protein sequence and structural modalities. Experimental evaluations demonstrate that MAEF-GO achieves superior performance compared to several state-of-the-art baseline models across standard benchmarks. Furthermore, analysis of the cross-attention weight distributions demonstrates MAEF-GO's interpretability. It can effectively identify critical functional residues of proteins.\nAVAILABILITY AND IMPLEMENTATION: The MAEF-GO source code can be found at https://github.com/nebstudio/MAEF-GO, an archived snapshot of the code used in this study is also available via Zenodo at https://doi.org/10.5281/zenodo.15422392.", "claims": [{"id": "claim-method", "statement": "In this study, we used CAFA (Radivojac et al. 2013) evaluation metrics Fmax, AUPR and Smin to measure the performance of different methods.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40569190", "locator": "sections[12] \"2.10 Evaluation metrics\" paragraph 2", "quote": "In this study, we used CAFA (Radivojac et al. 2013) evaluation metrics Fmax, AUPR and Smin to measure the performance of different methods."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The MAEF-GO source code and data can be found at https://github.com/nebstudio/MAEF-GO.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40569190", "locator": "sections[25] \"Data availability\" paragraph 2", "quote": "The MAEF-GO source code and data can be found at https://github.com/nebstudio/MAEF-GO."}], "state": "complete"}, {"id": "claim-target-result", "statement": "In the three prediction tasks of MF, BP, and CC, MAEF-GO achieved AUPR scores of 0.758, 0.438, 0.530; Fmax scores of 0.787, 0.652, 0.720; and Smin scores of 0.298, 0.461, 0.426, respectively.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40569190", "locator": "sections[14] \"3.1 The comparison of MAEF-GO and baseline models\" paragraph 2", "quote": "In the three prediction tasks of MF, BP, and CC, MAEF-GO achieved AUPR scores of 0.758, 0.438, 0.530; Fmax scores of 0.787, 0.652, 0.720; and Smin scores of 0.298, 0.461, 0.426, respectively."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "In the three prediction tasks of MF, BP, and CC, MAEF-GO achieved AUPR scores of 0.758, 0.438, 0.530; Fmax scores of 0.787, 0.652, 0.720; and Smin scores of 0.298, 0.461, 0.426, respectively.", "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:40569190"], "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:40569190", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf374", "sha256": "sha256:cd40e9772e29f2cd581a4cf1a95272c313145e9168bca85e8008315c3a500397", "bytes": 40630, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf374", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12289230", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "sequence_alignment", "specific": "blast", "label": "Sequence alignment / homology", "dsl_operations": ["sequence_align", "alignment_identity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["sequence_records"], "evidence": {"score": 0.8, "band": "high", "quote": "Blast"}}, {"id": "method-2", "family": null, "specific": null, "label": "CAFA evaluation metrics Fmax, AUPR and Smin", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "In this study, we used CAFA (Radivojac et al. 2013) evaluation metrics Fmax, AUPR and Smin to measure the performance of different methods."}}], "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": ["sequence_align", "alignment_identity"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: blast."}, "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 MAEF-GO source code and data can be found at https://github.com/nebstudio/MAEF-GO."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["sequence_align", "alignment_identity"], "assets": ["source:pmid:40569190"], "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": "2026-11-01T19:54:56Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10646, "completion_tokens": 2579, "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:40569190", "type": "paper", "label": "pmid:40569190"}, {"id": "source:pmid:40569190", "type": "manuscript", "label": "PMID 40569190 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40569190", "type": "paper", "label": "pmid:40569190"}, {"id": "source:pmid:40569190", "type": "manuscript", "label": "PMID 40569190 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40569190", "type": "extraction", "used": ["source:pmid:40569190"], "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:40569190", "parent_hash": "sha256:0751ac90926b5edd52e77709f0e75f0e36650c6eeee18e64e127eafc28bbd996", "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": "sequence_alignment", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["sequence_align", "alignment_identity"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Blast"], "order_basis": "analysis_only", "id": "assay:1"}]}