ODNA: identification of organellar DNA by machine learning.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37195463", "kind": "science-record", "revision": 2, "content_hash": "sha256:9e181ee3810dcda4b89754ec119f857613a3e5595922ee12882aee6caf8d94b0", "created_at": "2026-11-01T19:01:53Z", "updated_at": "2026-11-01T21:30:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "ODNA: identification of organellar DNA by machine learning.", "doi": "10.1093/bioinformatics/btad326", "pmid": "37195463", "authors": ["Roman Martin", "Minh Kien Nguyen", "Nick Lowack", "Dominik Heider"], "journal": "Bioinformatics (Oxford, England)", "year": 2023, "abstract": "MOTIVATION: Identifying organellar DNA, such as mitochondrial or plastid sequences, inside a whole genome assembly, remains challenging and requires biological background knowledge. To address this, we developed ODNA based on genome annotation and machine learning to fulfill.\nRESULTS: ODNA is a software that classifies organellar DNA sequences within a genome assembly by machine learning based on a predefined genome annotation workflow. We trained our model with 829 769 DNA sequences from 405 genome assemblies and achieved high predictive performance (e.g. matthew's correlation coefficient of 0.61 for mitochondria and 0.73 for chloroplasts) on independent validation data, thus outperforming existing approaches significantly.\nAVAILABILITY AND IMPLEMENTATION: Our software ODNA is freely accessible as a web service at https://odna.mathematik.uni-marburg.de and can also be run in a docker container. The source code can be found at https://gitlab.com/mosga/odna and the processed data at Zenodo (DOI: 10.5281/zenodo.7506483).", "claims": [{"id": "claim-method", "statement": "We used a stratified training-to-test ratio of 1:5 for the 10-fold cross-validation (CV) with various ML models provided by scikit-learn, including Linear Classifiers, Random Forests, k-nearest neighbors, and AdaBoost.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37195463", "locator": "sections[3] \"2.1 Machine learning\" paragraph 2", "quote": "We used a stratified training-to-test ratio of 1:5 for the 10-fold cross-validation (CV) with various ML models provided by scikit-learn, including Linear Classifiers, Random Forests, k-nearest neighbors, and AdaBoost."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The source code can be found at https://gitlab.com/mosga/odna and the processed data at Zenodo (DOI: 10.5281/zenodo.7506483).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37195463", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "The source code can be found at https://gitlab.com/mosga/odna and the processed data at Zenodo (DOI: 10.5281/zenodo.7506483)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "ODNA outperforms MitoFinder in identifying mitochondrial sequences, with an MCC of 0.61 versus 0.37.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37195463", "locator": "sections[5] \"3 Results\" paragraph 3", "quote": "A comparison between MitoFinder and ODNA reveals that ODNA outperforms MitoFinder with an MCC of 0.61 versus 0.37 in identifying the mitochondrial sequence on our validation data."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "ODNA outperforms MitoFinder in identifying mitochondrial sequences, with an MCC of 0.61 versus 0.37.", "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:37195463"], "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:37195463", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btad326", "sha256": "sha256:fee737f455977cce687417aa1c2806e0d79cd4dc8b9fc9f5138c7ca7a48f65fe", "bytes": 11617, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btad326", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10229373", "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": "10-fold cross-validation (CV)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used a stratified training-to-test ratio of 1:5 for the 10-fold cross-validation (CV) with various ML models provided by scikit-learn, including Linear Classifiers, Random Forests, k-nearest neighbors, and AdaBoost."}}], "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 (10-fold cross-validation (CV)), 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 source code can be found at https://gitlab.com/mosga/odna and the processed data at Zenodo (DOI: 10.5281/zenodo.7506483)."], "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:37195463"], "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": "2026-11-01T18:40:38Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 4608, "completion_tokens": 1940, "cached_tokens": 128}}, "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:37195463", "type": "paper", "label": "pmid:37195463"}, {"id": "source:pmid:37195463", "type": "manuscript", "label": "PMID 37195463 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37195463", "type": "paper", "label": "pmid:37195463"}, {"id": "source:pmid:37195463", "type": "manuscript", "label": "PMID 37195463 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37195463", "type": "extraction", "used": ["source:pmid:37195463"], "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:37195463", "parent_hash": "sha256:8398951817fdb905952b0f7933948fad29ae83c2797432af2beb398f25f7f4b2", "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"]}