bpRNA-CosMoS: a robust and efficient RNA structural comparison method using k-mer based cosine similarity.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40085007", "kind": "science-record", "revision": 2, "content_hash": "sha256:f2a88ec582615c5cbe436dae82c8c9ce551dd6057ad144a1a1e7067c22fa491e", "created_at": "2026-11-01T20:30:18Z", "updated_at": "2026-11-01T21:34:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "bpRNA-CosMoS: a robust and efficient RNA structural comparison method using k-mer based cosine similarity.", "doi": "10.1093/bioinformatics/btaf108", "pmid": "40085007", "authors": ["Brittany Lasher", "David A Hendrix"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: RNA secondary structure is often essential to function. Recent work has led to the development of high-throughput experimental probing methods for structure determination. Although structure is more conserved than primary sequence, much of the bioinformatics pipelines to connect RNA structure to function rely on nucleotide sequence alignments rather than structural similarity. There is a need to develop methods for secondary structure comparisons that are also fast and efficient to navigate the vast amounts of structural data. K-mer based similarity approaches are valued for their computational efficiency and have been applied for protein, DNA, and RNA primary sequences. However, these approaches have yet to be implemented for RNA secondary structure.\nRESULTS: Our method, bpRNA-CosMoS, fills this gap by using k-mers and length-weighted cosine similarity to compute similarity scores between RNA structures. bpRNA-CosMoS is built upon the bpRNA structure array, which represents the structural category of each nucleotide as a single-character structural code (e.g. hairpin=H, etc.). A structural comparison score is calculated through cosine similarity of the k-mer count vectors, generated from structure arrays. A major challenge with k-mer based methods is that they often ignore the length of the sequences being compared. We have overcome this with a length-weighted penalty that addresses cases of two RNAs of vastly different lengths. In addition, the use of \"fuzzy counting\" has added some optional flexibility to decrease the negative impact that small structural variations have on the similarity score. This results in a robust and efficient way to identify structural comparisons across large datasets.\nAVAILABILITY AND IMPLEMENTATION: The code and application guidelines of bpRNA-CosMoS are made available at github (https://github.com/BLasher113/bpRNA-CosMoS) and Zenodo (10.5281/zenodo.14715285).", "claims": [{"id": "claim-method", "statement": "Our method, bpRNA-CosMoS, fills this gap by using k-mers and length-weighted cosine similarity to compute similarity scores between RNA structures.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40085007", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Our method, bpRNA-CosMoS, fills this gap by using k-mers and length-weighted cosine similarity to compute similarity scores between RNA structures."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data underlying this article are available in Zenodo, at https://zenodo.org/records/14715285.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40085007", "locator": "sections[30] \"Data availability\" paragraph 2", "quote": "The data underlying this article are available in Zenodo, at https://zenodo.org/records/14715285."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "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:40085007"], "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:40085007", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf108", "sha256": "sha256:f1dd9d482e8a66c033f3723690d35c91aec36fdbf92a721e09a678390e2a7097", "bytes": 55390, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf108", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12017588", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "length-weighted cosine similarity, with an optional fuzzy-counting approach", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Our method, bpRNA-CosMoS, fills this gap by using k-mers and length-weighted cosine similarity to compute similarity scores between RNA structures."}}], "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (length-weighted cosine similarity, with an optional fuzzy-counting approach), 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 https://zenodo.org/records/14715285."], "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:40085007"], "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": "2026-11-01T19:48:41Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15051, "completion_tokens": 1540, "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:40085007", "type": "paper", "label": "pmid:40085007"}, {"id": "source:pmid:40085007", "type": "manuscript", "label": "PMID 40085007 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40085007", "type": "paper", "label": "pmid:40085007"}, {"id": "source:pmid:40085007", "type": "manuscript", "label": "PMID 40085007 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40085007", "type": "extraction", "used": ["source:pmid:40085007"], "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:40085007", "parent_hash": "sha256:6d3a4c4204ef256af64431dedb97dec29301ce1c8a7191720ea8be3b014ca8b3", "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"]}