Morpheus: a fragment-based algorithm to predict fold-switching behaviour in proteins across proteomes.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41284920", "kind": "science-record", "revision": 4, "content_hash": "sha256:4fb6b288b0e23132df8b5840de7114fc28f67f0a367a8b7a40fde14369924a90", "created_at": "2026-11-01T20:31:19Z", "updated_at": "2026-11-01T22:57:30Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Morpheus: a fragment-based algorithm to predict fold-switching behaviour in proteins across proteomes.", "doi": "10.1093/bioinformatics/btaf635", "pmid": "41284920", "authors": ["Vijay Subramanian", "Rajeswari Appadurai", "Harikrishnan Venkatesh", "Ashok Sekhar", "Anand Srivastava"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: Functionally important 'fold-switching' proteins, which do not obey the classical folding dogma, are now thought to be widespread. Algorithms that can accurately annotate fold-switching proteins from sequence information can help uncover the true extent of the 'metamorphome'.\nRESULTS: Here, we present Morpheus, a fragment-based classification approach, that works by analysing the diversity of structures within a query protein sequence. Morpheus exhaustively curates and uses fragment structural data from the Protein Data Bank as well as the AlphaFold Protein Structure Database. We employed our algorithm on 57 different proteomes consisting of a total of 601 218 proteins and identified about 10% of these proteins with the ability to fold-switch. Additionally, we provide a web server for Morpheus to test for fold-switching propensities for user-defined sequences (http://mbu.iisc.ac.in/∼anand/morpheus). Besides screening for fold-switching behaviour in proteomes, our work will be useful in de novo design and engineering of such proteins through further experimentation.\nAVAILABILITY AND IMPLEMENTATION: All codes used for fragment-picking analysis and the proteome-level prediction data for the 57 proteomes are publicly available on Zenodo (https://zenodo.org/records/14837336). The algorithm is also hosted within the web server (http://mbu.iisc.ac.in/∼anand/morpheus).", "claims": [{"id": "claim-method", "statement": "The training data is randomly split according to a six-fold cross-validation scheme. Upon performing a six-fold cross-validation, an SVM model with a polynomial kernel of degree 2 is found to be the model that has the highest average validation accuracy while also maintaining a lower model complexity.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41284920", "locator": "sections[6] \"2.4 Prediction model\" paragraph 2", "quote": "The training data is randomly split according to a six-fold cross-validation scheme. Upon performing a six-fold cross-validation, an SVM model with a polynomial kernel of degree 2 is found to be the model that has the highest average validation accuracy while also maintaining a lower model complexity."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The code used for fragment-picking analysis is publicly available on Zenodo (https://zenodo.org/records/14837336). The Zenedo repository also contains the proteome-level prediction data for the 57 proteome. The algorithm is also hosted within the web server (http://mbu.iisc.ac.in/∼anand/morpheus).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41284920", "locator": "sections[18] \"Data availability\" paragraph 2", "quote": "The code used for fragment-picking analysis is publicly available on Zenodo (https://zenodo.org/records/14837336). The Zenedo repository also contains the proteome-level prediction data for the 57 proteome. The algorithm is also hosted within the web server (http://mbu.iisc.ac.in/∼anand/morpheus)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Morpheus was applied to 57 proteomes containing 601,218 proteins and identified approximately 10% as having the ability to fold-switch.", "kind": "quantitative", "target": {"value": 10.0, "unit": "per cent", "tolerance": null, "source": "We employed our algorithm on 57 different proteomes consisting of a total of 601 218 proteins and identified about 10% of these proteins with the ability to fold-switch."}, "evidence": [{"asset": "source:pmid:41284920", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We employed our algorithm on 57 different proteomes consisting of a total of 601 218 proteins and identified about 10% of these proteins with the ability to fold-switch."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Morpheus was applied to 57 proteomes containing 601,218 proteins and identified approximately 10% as having the ability to fold-switch.", "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:41284920"], "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:41284920", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf635", "sha256": "sha256:0f836b1e2ac13a4fbb3f29772fa88d6ce741dcc9976d7cfd4463d56aa1571036", "bytes": 35065, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf635", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12702140", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The training data is randomly split according to a six-fold cross-validation scheme. Upon performing a six-fold cross-validation, an SVM model with a polynomial kernel of degree 2 is found to be the model that has the highest average validation accuracy while also maintaining a lower model complexity."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cross_validate", "expected_value": 10.0, "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": []}, "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: support_vector_machine."}, "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 code used for fragment-picking analysis is publicly available on Zenodo (https://zenodo.org/records/14837336). The Zenedo repository also contains the proteome-level prediction data for the 57 proteome. The algorithm is also hosted within the web server (http://mbu.iisc.ac.in/∼anand/morpheus)."], "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:41284920"], "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": "2026-11-01T20:06:25Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9101, "completion_tokens": 1241, "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:41284920", "type": "paper", "label": "pmid:41284920"}, {"id": "source:pmid:41284920", "type": "manuscript", "label": "PMID 41284920 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41284920", "type": "paper", "label": "pmid:41284920"}, {"id": "source:pmid:41284920", "type": "manuscript", "label": "PMID 41284920 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41284920", "type": "extraction", "used": ["source:pmid:41284920"], "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:41284920", "parent_hash": "sha256:33d84abd4f54d6fc4444b641c4f54dd4a92eeac6e4f165e0dd6bc2e552b43455", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "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": 1.0, "evidence": ["The training data is randomly split according to a six-fold cross-validation scheme. Upon performing a six-fold cross-validation, an SVM model with a polynomial kernel of degree 2 is found to be the model that has the highest average validation accuracy while also maintaining a lower model complexity."], "order_basis": "analysis_only", "id": "assay:1"}]}