"METAGENOTE: a simplified web platform for metadata annotation of genomic samples and streamlined submission to NCBI's sequence read archive".

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32883210", "kind": "science-record", "revision": 2, "content_hash": "sha256:d5af3d112cefd8bb4cbcfcbb40903309d51be834fbf1f559e98fa7267b8f48cc", "created_at": "2026-11-01T17:34:02Z", "updated_at": "2026-11-01T18:53:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "\"METAGENOTE: a simplified web platform for metadata annotation of genomic samples and streamlined submission to NCBI's sequence read archive\".", "doi": "10.1186/s12859-020-03694-0", "pmid": "32883210", "authors": ["Mariam Quiñones", "David T Liou", "Conrad Shyu", "Wongyu Kim", "Ivan Vujkovic-Cvijin", "Yasmine Belkaid", "Darrell E Hurt"], "journal": "BMC bioinformatics", "year": 2020, "abstract": "BACKGROUND: The improvements in genomics methods coupled with readily accessible high-throughput sequencing have contributed to our understanding of microbial species, metagenomes, infectious diseases and more. To maximize the impact of these genomics studies, it is important that data from biological samples will become publicly available with standardized metadata. The availability of data at public archives provides the hope that greater insights could be obtained through integration with multi-omics data, reproducibility of published studies, or meta-analyses of large diverse datasets. These datasets should include a description of the host, organism, environmental source of the specimen, spatial-temporal information and other relevant metadata, but unfortunately these attributes are often missing and when present, they show inconsistencies in the use of metadata standards and ontologies.\nRESULTS: METAGENOTE ( https://metagenote.niaid.nih.gov ) is a web portal that greatly facilitates the annotation of samples from genomic studies and streamlines the submission process of sequencing files and metadata to the Sequence Read Archive (SRA) (Leinonen R, et al, Nucleic Acids Res, 39:D19-21, 2011) for public access. This platform offers a wide selection of packages for different types of biological and experimental studies with a special emphasis on the standardization of metadata reporting. These packages follow the guidelines from the MIxS standards developed by the Genomics Standard Consortium (GSC) and adopted by the three partners of the International Nucleotides Sequencing Database Collaboration (INSDC) (Cochrane G, et al, Nucleic Acids Res, 44:D48-50, 2016) - National Center for Biotechnology Information (NCBI), European Bioinformatics Institute (EBI) and the DNA Data Bank of Japan (DDBJ). METAGENOTE then compiles, validates and manages the submission through an easy-to-use web interface minimizing submission errors and eliminating the need for submitting sequencing files via a separate file transfer mechanism.\nCONCLUSIONS: METAGENOTE is a public resource that focuses on simplifying the annotation and submission process of data with its corresponding metadata. Users of METAGENOTE will benefit from the easy to use annotation interface but most importantly will be encouraged to publish metadata following standards and ontologies that make the public data available for reuse.", "claims": [{"id": "claim-data-access", "statement": "Availability of data and materialshttp://github.com/niaid/metagenote", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32883210", "locator": "sections[15] \"notes\" paragraph 1", "quote": "Availability of data and materialshttp://github.com/niaid/metagenote"}], "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:32883210"], "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:32883210", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12859-020-03694-0", "sha256": "sha256:8865ef7c4c9e7c57eda26b0c7cfd327ed7f913abbd0b695c17fee98d01c5a4cd", "bytes": 25313, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12859-020-03694-0", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7471527", "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": ["Availability of data and materialshttp://github.com/niaid/metagenote"], "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:32883210"], "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": "2026-11-01T17:00:25Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7039, "completion_tokens": 621, "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:32883210", "type": "paper", "label": "pmid:32883210"}, {"id": "source:pmid:32883210", "type": "manuscript", "label": "PMID 32883210 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32883210", "type": "paper", "label": "pmid:32883210"}, {"id": "source:pmid:32883210", "type": "manuscript", "label": "PMID 32883210 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32883210", "type": "extraction", "used": ["source:pmid:32883210"], "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:32883210", "parent_hash": "sha256:8b2a3cb446d4fa4de56191ccfc1a80a23745239d8528cb606dd679640d323efb", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}