MoGAAAP: a modular Snakemake workflow for automated genome assembly and annotation with quality assessment.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41585413", "kind": "science-record", "revision": 1, "content_hash": "sha256:a589af4347ab810417be0c599b2bf93f7b8221fb14fa1f9803f99dc355502ce0", "created_at": "2026-11-01T20:31:33Z", "updated_at": "2026-11-01T20:31:33Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "MoGAAAP: a modular Snakemake workflow for automated genome assembly and annotation with quality assessment.", "doi": "10.1093/nargab/lqag008", "pmid": "41585413", "authors": ["Dirk-Jan M van Workum", "Kuntal K Dey", "Alexander Kozik", "Dean O Lavelle", "Dick de Ridder", "M Eric Schranz", "Richard W Michelmore", "Sandra Smit"], "journal": "NAR genomics and bioinformatics", "year": 2026, "abstract": "With the current speed of sequencing, there is a desire for standardized and automated genome assembly and annotation to produce high-quality genomes as input for comparative (pan)genomics. Therefore, we created a convenience pipeline using existing tools that creates annotated genome assemblies from HiFi (and optionally ultra-long ONT and/or Hi-C) reads for a set of related individuals as well as a related reference genome. Our pipeline is species-agnostic and generates an extensive quality assessment report that can be used for manual filtering and refinement of the assembly and annotation. It includes statistics for individual completeness and contamination assessments as well as a concise pangenome view. The pipeline is implemented in Snakemake and available with a GPLv3 licence at GitHub under github.com/dirkjanvw/MoGAAAP, at Zenodo under doi.org/10.5281/zenodo.14833021, and can be installed through Bioconda.", "claims": [{"id": "claim-data-access", "statement": "The novel L. serriola genome, which is described as a use case in the Supplementary data, has been published at NCBI GenBank (GCA_051521515.1). Underlying HiFi and ONT sequencing data has been published under BioProject PRJNA412928. HTML reports created by MoGAAAP for the use cases described in the Supplementary data are available through data. 4TU (DOI: 10.4121/4b39da65-2eef-4e05-8583-25f8850cf932).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41585413", "locator": "sections[22] \"Data availability\" paragraph 2", "quote": "The novel L. serriola genome, which is described as a use case in the Supplementary data, has been published at NCBI GenBank (GCA_051521515.1). Underlying HiFi and ONT sequencing data has been published under BioProject PRJNA412928. HTML reports created by MoGAAAP for the use cases described in the Supplementary data are available through data. 4TU (DOI: 10.4121/4b39da65-2eef-4e05-8583-25f8850cf932)."}], "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:41585413"], "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_unresolved", "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": ["data:geo:PRJNA412928"], "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": ["data:geo:PRJNA412928"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_unresolved"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41585413", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/nargab/lqag008", "sha256": "sha256:3bf2ac68ccbd0be85afc391c5ee1784208418a5c2b2b641e508b7023486df13e", "bytes": 27655, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/nargab/lqag008", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12824462", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PRJNA412928", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=PRJNA412928", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PRJNA412928", "version": null, "note": "The novel L. serriola genome, which is described as a use case in the Supplementary data, has been published at NCBI GenBank (GCA_051521515.1). Underlying HiFi and ONT sequencing data has been published under BioProject PRJNA412928. HTML reports created by MoGAAAP for the use cases described in the Supplementary data are available through data. 4TU (DOI: 10.4121/4b39da65-2eef-4e05-8583-25f8850cf932).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The novel L. serriola genome, which is described as a use case in the Supplementary data, has been published at NCBI GenBank (GCA_051521515.1). Underlying HiFi and ONT sequencing data has been published under BioProject PRJNA412928. HTML reports created by MoGAAAP for the use cases described in the Supplementary data are available through data. 4TU (DOI: 10.4121/4b39da65-2eef-4e05-8583-25f8850cf932).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T20:16:20Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PRJNA412928 not downloaded", "asset:data:geo:PRJNA412928 licence not read"]}, "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": ["PRJNA412928"], "resolved_accessions": [], "statements": ["The novel L. serriola genome, which is described as a use case in the Supplementary data, has been published at NCBI GenBank (GCA_051521515.1). Underlying HiFi and ONT sequencing data has been published under BioProject PRJNA412928. HTML reports created by MoGAAAP for the use cases described in the Supplementary data are available through data. 4TU (DOI: 10.4121/4b39da65-2eef-4e05-8583-25f8850cf932)."], "basis": "The paper names PRJNA412928, but the accession does not resolve in the repository (not_in_ncbi_bioproject), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41585413", "data:geo:PRJNA412928"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PRJNA412928"]}, "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": "2026-11-01T20:11:04Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8550, "completion_tokens": 1377, "cached_tokens": 264}}, "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:41585413", "type": "paper", "label": "pmid:41585413"}, {"id": "source:pmid:41585413", "type": "manuscript", "label": "PMID 41585413 full text"}, {"id": "data:geo:PRJNA412928", "type": "dataset", "label": "GEO PRJNA412928"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41585413", "type": "paper", "label": "pmid:41585413"}, {"id": "source:pmid:41585413", "type": "manuscript", "label": "PMID 41585413 full text"}, {"id": "data:geo:PRJNA412928", "type": "dataset", "label": "GEO PRJNA412928"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41585413", "type": "extraction", "used": ["source:pmid:41585413"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PRJNA412928", "type": "accession_resolution", "used": ["data:geo:PRJNA412928"], "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": ["asset:data:geo:PRJNA412928 licence not read", "asset:data:geo:PRJNA412928 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"]}