The TriMet_DB: A Manually Curated Database of the Metabolic Proteins of Triticum aestivum.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36558536", "kind": "science-record", "revision": 1, "content_hash": "sha256:270c3649e57a513569083f1c56a745839df76c783cb8e8b520f6895917af3ace", "created_at": "2026-11-01T19:01:05Z", "updated_at": "2026-11-01T19:01:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "The TriMet_DB: A Manually Curated Database of the Metabolic Proteins of Triticum aestivum.", "doi": "10.3390/nu14245377", "pmid": "36558536", "authors": ["Vincenzo Cunsolo", "Antonella Di Francesco", "Maria Gaetana Giovanna Pittalà", "Rosaria Saletti", "Salvatore Foti"], "journal": "Nutrients", "year": 2022, "abstract": "Mass-spectrometry-based wheat proteomics is challenging because the current interpretation of mass spectrometry data relies on public databases that are not exhaustive (UniProtKB/Swiss-Prot) or contain many redundant and poor or un-annotated entries (UniProtKB/TrEMBL). Here, we report the development of a manually curated database of the metabolic proteins of Triticum aestivum (hexaploid wheat), named TriMet_DB (Triticum aestivum Metabolic Proteins DataBase). The manually curated TriMet_DB was generated in FASTA format so that it can be read directly by programs used to interpret the mass spectrometry data. Furthermore, the complete list of entries included in the TriMet_DB is reported in a freely available resource, which includes for each protein the description, the gene code, the protein family, and the allergen name (if any). To evaluate its performance, the TriMet_DB was used to interpret the MS data acquired on the metabolic protein fraction extracted from the cultivar MEC of Triticum aestivum. Data are available via ProteomeXchange with identifier PXD037709.", "claims": [{"id": "claim-data-access", "statement": "Data are available via ProteomeXchange (www.proteomexchange.org, accessed on 1 November 2022) with identifier PXD037709.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36558536", "locator": "sections[19] \"notes\" paragraph 1", "quote": "Data are available via ProteomeXchange (www.proteomexchange.org, accessed on 1 November 2022) with identifier PXD037709."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:36558536"], "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": "complete", "blocked_on": null, "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:PXD037709"], "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:PXD037709"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36558536", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/nu14245377", "sha256": "sha256:898be01deae230a711193215194e08c0a7022496bc838e25836361f64278532d", "bytes": 36278, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/nu14245377", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9781733", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD037709", "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=PXD037709", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD037709", "version": null, "note": "Data are available via ProteomeXchange (www.proteomexchange.org, accessed on 1 November 2022) with identifier PXD037709.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange (www.proteomexchange.org, accessed on 1 November 2022) with identifier PXD037709.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "The TriMet_DB: a manually curated database of the metabolic proteins of Triticum aestivum", "resolution_checked_at": "2026-11-01T18:46:41Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD037709 not downloaded", "asset:data:geo:PXD037709 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": "method", "blocked_on": "method:not_determinable", "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": "R1", "reachable": true, "accessions": ["PXD037709"], "resolved_accessions": ["PXD037709"], "statements": ["Data are available via ProteomeXchange (www.proteomexchange.org, accessed on 1 November 2022) with identifier PXD037709."], "basis": "The paper names PXD037709 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:36558536", "data:geo:PXD037709"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD037709"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:21:09Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9996, "completion_tokens": 1372, "cached_tokens": 188}}, "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:36558536", "type": "paper", "label": "pmid:36558536"}, {"id": "source:pmid:36558536", "type": "manuscript", "label": "PMID 36558536 full text"}, {"id": "data:geo:PXD037709", "type": "dataset", "label": "GEO PXD037709"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36558536", "type": "paper", "label": "pmid:36558536"}, {"id": "source:pmid:36558536", "type": "manuscript", "label": "PMID 36558536 full text"}, {"id": "data:geo:PXD037709", "type": "dataset", "label": "GEO PXD037709"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36558536", "type": "extraction", "used": ["source:pmid:36558536"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD037709", "type": "accession_resolution", "used": ["data:geo:PXD037709"], "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:PXD037709 licence not read", "asset:data:geo:PXD037709 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["enging because the current interpretation of mass spectrometry data relies on public databases that are not", "d directly by programs used to interpret the mass spectrometry data. Furthermore, the complete list of entr", "Mass-spectrometry-based wheat proteomics is challenging because the current interpret"], "order_basis": "paper_text_order:91", "id": "assay:1"}]}