MHASS: Microbiome HiFi Amplicon Sequencing Simulator.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41351823", "kind": "science-record", "revision": 2, "content_hash": "sha256:5fa29d5a1ce0c5fd40aa961168f38aeeb3ab7f08fc84f10daee13864bfa599b5", "created_at": "2026-11-01T20:31:22Z", "updated_at": "2026-11-01T21:36:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "MHASS: Microbiome HiFi Amplicon Sequencing Simulator.", "doi": "10.1093/bioinformatics/btaf656", "pmid": "41351823", "authors": ["Rye Howard-Stone", "Ion I Măndoiu"], "journal": "Bioinformatics (Oxford, England)", "year": 2026, "abstract": "SUMMARY: Microbiome HiFi Amplicon Sequence Simulator (MHASS) creates realistic synthetic PacBio HiFi amplicon sequencing datasets for microbiome studies, by integrating genome-aware abundance modeling, realistic dual-barcoding strategies, and empirically derived pass-number distributions from actual sequencing runs. MHASS generates datasets tailored for rigorous benchmarking and validation of long-read microbiome analysis workflows, including ASV clustering and taxonomic assignment.\nAVAILABILITY AND IMPLEMENTATION: Implemented in Python with automated dependency management, the source code for MHASS is freely available at https://github.com/rhowardstone/MHASS along with installation instructions. Our code is also published on Zenodo at https://doi.org/10.5281/zenodo.17486364. The data underlying this article are available on GitHub at https://github.com/rhowardstone/MHASS_evaluation/.", "claims": [{"id": "claim-method", "statement": "(ii) Abundance Correlation—Pearson correlation between expected and observed ASV abundances at both genome and ASV levels", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41351823", "locator": "sections[5] \"2.3 Evaluation metrics\" paragraph 2", "quote": "(ii) Abundance Correlation—Pearson correlation between expected and observed ASV abundances at both genome and ASV levels"}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data underlying this article are available on GitHub at https://github.com/rhowardstone/MHASS_evaluation/.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41351823", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "The data underlying this article are available on GitHub at https://github.com/rhowardstone/MHASS_evaluation/."}], "state": "complete"}, {"id": "claim-target-result", "statement": "MHASS accurately reproduces key characteristics of real PacBio HiFi data, including complex error patterns and abundance distributions.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41351823", "locator": "sections[13] \"5 Conclusion\" paragraph 2", "quote": "Our validation experiments demonstrate that MHASS accurately reproduces key characteristics of real PacBio HiFi data, including complex error patterns and abundance distributions."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "MHASS accurately reproduces key characteristics of real PacBio HiFi data, including complex error patterns and abundance distributions.", "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:41351823"], "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:41351823", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf656", "sha256": "sha256:56e5ab69512cf479c24c6ae7b145cfd64225e8cb35e2ccae8598ee54aea0bb39", "bytes": 16919, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf656", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12790812", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "(ii) Abundance Correlation—Pearson correlation between expected and observed ASV abundances at both genome and ASV levels"}}], "targets": [], "gaps": []}, "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": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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 data underlying this article are available on GitHub at https://github.com/rhowardstone/MHASS_evaluation/."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:41351823"], "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": "2026-11-01T20:07:21Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5680, "completion_tokens": 2094, "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:41351823", "type": "paper", "label": "pmid:41351823"}, {"id": "source:pmid:41351823", "type": "manuscript", "label": "PMID 41351823 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41351823", "type": "paper", "label": "pmid:41351823"}, {"id": "source:pmid:41351823", "type": "manuscript", "label": "PMID 41351823 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41351823", "type": "extraction", "used": ["source:pmid:41351823"], "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:41351823", "parent_hash": "sha256:b3d68857a792d2854b3354f9a8b707d8c398d184d94abf29571ed5715d924767", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["MHASS: Microbiome HiFi Amplicon Sequencing Simulator.", "ASS) creates realistic synthetic PacBio HiFi amplicon sequencing datasets for microbiome studies, by integrat"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["(ii) Abundance Correlation—Pearson correlation between expected and observed ASV abundances at both genome and ASV levels"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}