GRUMB: a genome-resolved metagenomic framework for monitoring urban microbiomes and diagnosing pathogen risk.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41002268", "kind": "science-record", "revision": 2, "content_hash": "sha256:5760c933009151cce5832275886af2359a2f30fbc41cd1ce394edf4fb469b838", "created_at": "2026-11-01T20:31:04Z", "updated_at": "2026-11-01T21:35:48Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "GRUMB: a genome-resolved metagenomic framework for monitoring urban microbiomes and diagnosing pathogen risk.", "doi": "10.1093/bioinformatics/btaf548", "pmid": "41002268", "authors": ["Suleiman Aminu", "AbdulAziz Ascandari", "Rachid Benhida", "Rachid Daoud"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "SUMMARY: Urban infrastructure hosts dynamic microbial communities that complicate biosurveillance and AMR monitoring. Existing tools rarely combine genome-resolved reconstruction with ecological modeling and batch-aware analytics tailored to infrastructure-scale studies. We present GRUMB (Genome-Resolved Urban Microbiome Biosurveillance), an open-source, SLURM-compatible pipeline that reconstructs high-quality metagenome-assembled genomes (MAGs) from shotgun sequencing reads and integrates taxonomic/functional annotation (CARD, VFDB), batch-aware normalization, ecological diagnostics and machine learning classification of environment types with uncertainty and risk scoring. GRUMB accepts either SRA project accessions or paired-end FASTQ files with metadata, and produces assemblies, MAGs, taxonomic and functional profiles, ecological outputs and risk-informed classification. Its modular design enables reproducible, infrastructure-scale biosurveillance across diverse environments.\nAVAILABILITY AND IMPLEMENTATION: GRUMB is freely available under the MIT License at: https://github.com/SuleimanAminu/genome-resolved-urban-microbiome-biosurveillance; Zenodo DOI: https://doi.org/10.5281/zenodo.15505402. Requirements: Linux (Ubuntu 20.04+), Python 3.11, R 4.2+, SLURM. Issues and feature requests are tracked on GitHub.", "claims": [{"id": "claim-method", "statement": "Module 03: Ecological analysis (03_Ecology/). Alpha and beta diversity, NMDS ordination, PERMANOVA and ANOSIM (vegan) (Oksanen et al. 2001), and indicator-species analysis (indicspecies) for interpretable community structure across infrastructure types.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41002268", "locator": "sections[3] \"2.1 Modular architecture\" paragraph 2", "quote": "Module 03: Ecological analysis (03_Ecology/). Alpha and beta diversity, NMDS ordination, PERMANOVA and ANOSIM (vegan) (Oksanen et al. 2001), and indicator-species analysis (indicspecies) for interpretable community structure across infrastructure types."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All datasets used in this study are publicly available. Accession numbers and project identifiers are provided in the Supplementary Material. The full pipeline and example data are accessible via GitHub and Zenodo.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41002268", "locator": "sections[13] \"Data availability\" paragraph 2", "quote": "All datasets used in this study are publicly available. Accession numbers and project identifiers are provided in the Supplementary Material. The full pipeline and example data are accessible via GitHub and Zenodo."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We present GRUMB (Genome-Resolved Urban Microbiome Biosurveillance), an open-source, SLURM-compatible pipeline that reconstructs high-quality metagenome-assembled genomes (MAGs) from shotgun sequencing reads and integrates taxonomic/functional annotation (CARD, VFDB), batch-aware normalization, ecological diagnostics and machine learning classification of environment types with uncertainty and risk scoring.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41002268", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We present GRUMB (Genome-Resolved Urban Microbiome Biosurveillance), an open-source, SLURM-compatible pipeline that reconstructs high-quality metagenome-assembled genomes (MAGs) from shotgun sequencing reads and integrates taxonomic/functional annotation (CARD, VFDB), batch-aware normalization, ecological diagnostics and machine learning classification of environment types with uncertainty and risk scoring."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "We present GRUMB (Genome-Resolved Urban Microbiome Biosurveillance), an open-source, SLURM-compatible pipeline that reconstructs high-quality metagenome-assembled genomes (MAGs) from shotgun sequencing reads and integrates taxonomic/functional annotation (CARD, VFDB), batch-aware normalization, ecological diagnostics and machine learning classification of environment types with uncertainty and risk scoring.", "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:41002268"], "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:41002268", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf548", "sha256": "sha256:705ad3e17a31d88308757eb4b7a943fe694ab6ff4bb7b6ca6efe55ab1c1fadca", "bytes": 23036, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf548", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12548037", "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": "PERMANOVA and ANOSIM", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Module 03: Ecological analysis (03_Ecology/). Alpha and beta diversity, NMDS ordination, PERMANOVA and ANOSIM (vegan) (Oksanen et al. 2001), and indicator-species analysis (indicspecies) for interpretable community structure across infrastructure types."}}], "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 (PERMANOVA and ANOSIM), 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": ["All datasets used in this study are publicly available. Accession numbers and project identifiers are provided in the Supplementary Material. The full pipeline and example data are accessible via GitHub and Zenodo."], "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:41002268"], "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": "2026-11-01T20:01:56Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7402, "completion_tokens": 1395, "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:41002268", "type": "paper", "label": "pmid:41002268"}, {"id": "source:pmid:41002268", "type": "manuscript", "label": "PMID 41002268 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41002268", "type": "paper", "label": "pmid:41002268"}, {"id": "source:pmid:41002268", "type": "manuscript", "label": "PMID 41002268 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41002268", "type": "extraction", "used": ["source:pmid:41002268"], "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:41002268", "parent_hash": "sha256:427fe7d6d2707f63e90b7d4353c982cea2a738af55346c7689d1e93aee97e8c4", "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"]}