AdDeam: a fast and scalable tool for estimating and clustering reference-level damage profiles.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40674584", "kind": "science-record", "revision": 2, "content_hash": "sha256:bcf2497916cd691235d86857d5a302d9a4ce1db0fbf486a9086f59672ead9092", "created_at": "2026-11-01T20:30:46Z", "updated_at": "2026-11-01T21:35:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "AdDeam: a fast and scalable tool for estimating and clustering reference-level damage profiles.", "doi": "10.1093/bioinformatics/btaf407", "pmid": "40674584", "authors": ["Louis Kraft", "Thorfinn Sand Korneliussen", "Peter Wad Sackett", "Gabriel Renaud"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: DNA damage patterns, such as increased frequencies of C→T and G→A substitutions at fragment ends, are widely used in ancient DNA studies to assess authenticity and detect contamination. In metagenomic studies, fragments can be mapped against multiple references or de novo assembled contigs to identify those likely to be ancient. Generating and comparing damage profiles, however, can be both tedious and time-consuming. Although tools exist for estimating damage in single reference genomes and metagenomic datasets, none efficiently cluster damage patterns.\nRESULTS: To address this methodological gap, we developed AdDeam, a tool that combines rapid damage estimation with clustering for streamlined analyses and easy identification of potential contaminants or outliers. Our tool takes aligned ancient DNA (aDNA) fragments from various samples or contigs as input, computes damage patterns, clusters them, and outputs representative damage profiles per cluster, a probability of each sample pertaining to a cluster, as well as a Principal Component Analysis of the damage patterns for each sample for fast visualisation. We evaluated AdDeam on both simulated and empirical datasets. AdDeam effectively distinguishes different damage levels, such as uracil-DNA glycosylase-treated samples, sample-specific damages from specimens of different time periods, and can also distinguish between contigs containing modern or ancient fragments, providing a clear framework for aDNA authentication and facilitating large-scale analyses.\nAVAILABILITY AND IMPLEMENTATION: AdDeam is publicly available at https://github.com/LouisPwr/AdDeam and can also be installed via Bioconda. It is implemented in Python and C++. All analysis scripts and datasets are available at https://github.com/LouisPwr/AdDeamAnalysis and on Zenodo under: 10.5281/zenodo.15052427.", "claims": [{"id": "claim-method", "statement": "This matrix serves as input for clustering the damage patterns using a GMM algorithm implemented using scikit-learn (Pedregosa et al. 2011).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40674584", "locator": "sections[8] \"2.2 Stage 2: clustering of damage profiles into k clusters\" paragraph 4", "quote": "This matrix serves as input for clustering the damage patterns using a GMM algorithm implemented using scikit-learn (Pedregosa et al. 2011)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All analysis scripts and datasets are available at https://github.com/LouisPwr/AdDeamAnalysis and on Zenodo under: 10.5281/zenodo.15052427.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40674584", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "All analysis scripts and datasets are available at https://github.com/LouisPwr/AdDeamAnalysis and on Zenodo under: 10.5281/zenodo.15052427."}], "state": "complete"}, {"id": "claim-target-result", "statement": "AdDeam effectively distinguishes different damage levels, such as uracil-DNA glycosylase-treated samples, sample-specific damages from specimens of different time periods, and can also distinguish between contigs containing modern or ancient fragments, providing a clear framework for aDNA authentication and facilitating large-scale analyses.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40674584", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "AdDeam effectively distinguishes different damage levels, such as uracil-DNA glycosylase-treated samples, sample-specific damages from specimens of different time periods, and can also distinguish between contigs containing modern or ancient fragments, providing a clear framework for aDNA authentication and facilitating large-scale analyses."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "AdDeam effectively distinguishes different damage levels, such as uracil-DNA glycosylase-treated samples, sample-specific damages from specimens of different time periods, and can also distinguish between contigs containing modern or ancient fragments, providing a clear framework for aDNA authentication and facilitating large-scale analyses.", "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:40674584"], "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:40674584", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf407", "sha256": "sha256:6fb523530c5e07072ebe8ce5c71718c25d054bd743fb2b382c3f4a9368127661", "bytes": 50602, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf407", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12317744", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Principal Component Analysis"}}, {"id": "method-2", "family": null, "specific": null, "label": "Gaussian Mixture Model (GMM) clustering algorithm implemented using scikit-learn", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "This matrix serves as input for clustering the damage patterns using a GMM algorithm implemented using scikit-learn (Pedregosa et al. 2011)."}}], "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": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": ["All analysis scripts and datasets are available at https://github.com/LouisPwr/AdDeamAnalysis and on Zenodo under: 10.5281/zenodo.15052427."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:40674584"], "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": "2026-11-01T19:57:14Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13521, "completion_tokens": 1310, "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:40674584", "type": "paper", "label": "pmid:40674584"}, {"id": "source:pmid:40674584", "type": "manuscript", "label": "PMID 40674584 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40674584", "type": "paper", "label": "pmid:40674584"}, {"id": "source:pmid:40674584", "type": "manuscript", "label": "PMID 40674584 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40674584", "type": "extraction", "used": ["source:pmid:40674584"], "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:40674584", "parent_hash": "sha256:18781c3ce0d83ae0745e0a146cf5a88e8fef40d89d33cf0f1d115a9dc1fc0d00", "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"], "assays": [{"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Principal Component Analysis"], "order_basis": "analysis_only", "id": "assay:1"}]}