Sequali: efficient and comprehensive quality control of short- and long-read sequencing data.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39927290", "kind": "science-record", "revision": 1, "content_hash": "sha256:170dea834aaf37ac99620c69030f3c82b04db96440e6e99f713c5d68ef1c410c", "created_at": "2026-11-01T20:30:11Z", "updated_at": "2026-11-01T20:30:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Sequali: efficient and comprehensive quality control of short- and long-read sequencing data.", "doi": "10.1093/bioadv/vbaf010", "pmid": "39927290", "authors": ["Ruben H P Vorderman"], "journal": "Bioinformatics advances", "year": 2025, "abstract": "Motivation: Quality control of sequencing data is the first step in many sequencing workflows. Short- and long-read sequencing technologies have many commonalities with regard to quality control. Several quality control programs exist; however, none possess a feature set that is adequate for both technologies. Quality control programs aimed at Oxford Nanopore Technologies sequencing lack vital features, such as adapter searching, overrepresented sequence analysis, and duplication analysis.\nResults: Sequali was developed to provide sequencing quality control for both short- and long-read sequencing technologies. It features adapter search, overrepresented sequence analysis, and duplication analysis and supports FASTQ and uBAM inputs. It is significantly faster than comparable sequencing quality control programs for both short- and long-read sequencing technologies.\nAvailability and Implementation: Sequali is an open-source Python application using C extensions and is freely available under the AGPL-3.0 license at https://github.com/rhpvorderman/sequali. The source code for each release is archived at zenodo: https://zenodo.org/doi/10.5281/zenodo.10822485.", "claims": [{"id": "claim-data-access", "statement": "Sequali is freely available under the AGPL-3.0 license. The source code and additional examples can be found at https://github.com/rhpvorderman/sequali. The source code for each release is archived at zenodo: https://zenodo.org/doi/10.5281/zenodo.10822485.\nBinary releases for Linux, Windows and macOS are available on PyPI (https://pypi.org/project/sequali/). Binary releases for Linux and macOS are available on Bioconda (https://bioconda.github.io/recipes/sequali/README.html). Installation can be via pip, conda or by using a container provided by the BioContainers project.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39927290", "locator": "sections[9] \"Data availability\" paragraphs 1-3", "quote": "Sequali is freely available under the AGPL-3.0 license. The source code and additional examples can be found at https://github.com/rhpvorderman/sequali. The source code for each release is archived at zenodo: https://zenodo.org/doi/10.5281/zenodo.10822485.\nBinary releases for Linux, Windows and macOS are available on PyPI (https://pypi.org/project/sequali/). Binary releases for Linux and macOS are available on Bioconda (https://bioconda.github.io/recipes/sequali/README.html). Installation can be via pip, conda or by using a container provided by the BioContainers project."}], "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:39927290"], "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:39927290", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioadv/vbaf010", "sha256": "sha256:6273756fa1e76a2811ed29a9a886b5357c66efc9703d6a602b08120777cabd35", "bytes": 12546, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioadv/vbaf010", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11802474", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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 (not named), 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": ["Sequali is freely available under the AGPL-3.0 license. The source code and additional examples can be found at https://github.com/rhpvorderman/sequali. The source code for each release is archived at zenodo: https://zenodo.org/doi/10.5281/zenodo.10822485.\nBinary releases for Linux, Windows and macOS are available on PyPI (https://pypi.org/project/sequali/). Binary releases for Linux and macOS are available on Bioconda (https://bioconda.github.io/recipes/sequali/README.html). Installation can be via pip, conda or by using a container provided by the BioContainers project."], "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:39927290"], "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": "2026-11-01T19:45:57Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 4504, "completion_tokens": 1726, "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:39927290", "type": "paper", "label": "pmid:39927290"}, {"id": "source:pmid:39927290", "type": "manuscript", "label": "PMID 39927290 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39927290", "type": "paper", "label": "pmid:39927290"}, {"id": "source:pmid:39927290", "type": "manuscript", "label": "PMID 39927290 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39927290", "type": "extraction", "used": ["source:pmid:39927290"], "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": null, "parent_hash": null, "fork_of": null, "generation": 0}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}