Generation of a zebrafish SWATH-MS spectral library to quantify 10,000 proteins.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30747917", "kind": "science-record", "revision": 4, "content_hash": "sha256:a3f8adcd91e49fb129e91423839fdf458ac78c197f8bf5ec6f00794c9483732e", "created_at": "2026-11-01T15:40:42Z", "updated_at": "2026-11-01T21:21:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Generation of a zebrafish SWATH-MS spectral library to quantify 10,000 proteins.", "doi": "10.1038/sdata.2019.11", "pmid": "30747917", "authors": ["Peter Blattmann", "Vivienne Stutz", "Giulia Lizzo", "Joy Richard", "Philipp Gut", "Ruedi Aebersold"], "journal": "Scientific data", "year": 2019, "abstract": "Sequential window acquisition of all theoretical mass spectra (SWATH-MS) requires a spectral library to extract quantitative measurements from the mass spectrometry data acquired in data-independent acquisition mode (DIA). Large combined spectral libraries containing SWATH assays have been generated for humans and several other organisms, but so far no publicly available library exists for measuring the proteome of zebrafish, a rapidly emerging model system in biomedical research. Here, we present a large zebrafish SWATH spectral library to measure the abundance of 104,185 proteotypic peptides from 10,405 proteins. The library includes proteins expressed in 9 different zebrafish tissues (brain, eye, heart, intestine, liver, muscle, ovary, spleen, and testis) and provides an important new resource to quantify 40% of the protein-coding zebrafish genes. We employ this resource to quantify the proteome across brain, muscle, and liver and characterize divergent expression levels of paralogous proteins in different tissues. Data are available via ProteomeXchange (PXD010876, PXD010869) and SWATHAtlas (PASS01237).", "claims": [{"id": "claim-method", "statement": "The error bars represent standard deviation of six different fish and the difference in abundance was tested using an unpaired t-test for ohnologues quantified in the same tissue (∗∗∗adj. p-value<0.001, ∗∗adj. p-value<0.01, ∗adj. p-value<0.05, n.s. adj. p-value>0.05).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30747917", "locator": "sections[15] \"Reproducibility of coordinates in SWATH spectral library\" paragraph 3", "quote": "The error bars represent standard deviation of six different fish and the difference in abundance was tested using an unpaired t-test for ohnologues quantified in the same tissue (∗∗∗adj. p-value<0.001, ∗∗adj. p-value<0.01, ∗adj. p-value<0.05, n.s. adj. p-value>0.05)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange (PXD010876, PXD010869) and SWATHAtlas (PASS01237).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30747917", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange (PXD010876, PXD010869) and SWATHAtlas (PASS01237)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:30747917"], "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:PXD010869"], "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:PXD010869"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30747917", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/sdata.2019.11", "sha256": "sha256:ce116ffd0072b7e62f2a140989498619ca39a3a07096bb9d5b9328b11d56e60e", "bytes": 39121, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/sdata.2019.11", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6371892", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD010869", "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=PXD010869", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD010869", "version": null, "note": "Data are available via ProteomeXchange (PXD010876, PXD010869) and SWATHAtlas (PASS01237).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange (PXD010876, PXD010869) and SWATHAtlas (PASS01237).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Quantification of brain, muscle, and liver using large SWATH-spectral library", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD010876", "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=PXD010876", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD010876", "version": null, "note": "Data are available via ProteomeXchange (PXD010876, PXD010869) and SWATHAtlas (PASS01237).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange (PXD010876, PXD010869) and SWATHAtlas (PASS01237).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Zebrafish SWATH-MS spectral library to quantify 10,000 proteins", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30747917:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:66a967cb27e45f3922a5b04a66e95334c4d49cd3ac5533dfaec99a8ab28f5ba2", "bytes": 1097, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t1", "version": null, "note": "Samples acquired for the zebrafish SWATH spectral library.", "structure": {"pmcid": "PMC6371892", "section_index": 1, "section_title": "Background & Summary", "row_count": 21, "column_count": 4}, "table": {"label": "Table 1", "caption": "Samples acquired for the zebrafish SWATH spectral library.", "rows": [["Tissue", "Peptide fractionation", "MS Samples", "MS Injections"], ["Peptides from unfractionated peptide samples were injected in three technical replicates, fractionated peptide samples were only injected once. For the eye, two unfractionated peptide samples (the eye and the vitreous body) were processed."], ["Brain", "None", "1", "3"], ["Brain", "high-pH RP-HPLC", "8", "8"], ["Eye", "None", "2", "6"], ["Eye", "high-pH RP-HPLC", "8", "8"], ["Heart", "None", "1", "3"], ["Heart", "high-pH RP-HPLC", "8", "8"], ["Intestine", "None", "1", "3"], ["Intestine", "high-pH RP-HPLC", "7", "7"], ["Liver", "None", "1", "3"], ["Liver", "high-pH RP-HPLC", "8", "8"], ["Muscle", "None", "3", "3"], ["Muscle", "high-pH RP-HPLC", "8", "8"], ["Ovary", "None", "1", "3"], ["Ovary", "high-pH RP-HPLC", "8", "8"], ["Spleen", "None", "1", "3"], ["Spleen", "high-pH RP-HPLC", "8", "8"], ["Testis", "None", "1", "3"], ["Testis", "high-pH RP-HPLC", "8", "8"], ["Total", "", "83", "101"]], "row_count": 21, "column_count": 4, "numeric_cells": 38, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:30747917:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b699261b5558828f3dc0d440a4771d7c9310cde5e94b5b29d55f2cb868f740b4", "bytes": 595, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#t2", "version": null, "note": "Size of the zebrafish SWATH spectral library.", "structure": {"pmcid": "PMC6371892", "section_index": 13, "section_title": "Protein sequence database", "row_count": 6, "column_count": 3}, "table": {"label": "Table 2", "caption": "Size of the zebrafish SWATH spectral library.", "rows": [["", "Proteotypic", "Proteotypic and Shared"], ["Number of proteins, peptides, precursors, and transitions that pass a protein FDR of 1% are shown (see Methods). The number of proteins etc. supported by proteotypic as well as proteotypic and shared peptides are shown."], ["Proteins", "10,405", "12,770"], ["Peptides", "104,185", "114,912"], ["Precursors", "129,561", "143,901"], ["Transitions", "777,366", "863,406"]], "row_count": 6, "column_count": 3, "numeric_cells": 9, "header_rows": 1, "locator": "section[13]/table-wrap[1]#t2"}}], "gaps": ["asset:data:geo:PXD010869 not downloaded", "asset:data:geo:PXD010869 licence not read", "asset:data:geo:PXD010876 not downloaded", "asset:data:geo:PXD010876 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "unpaired t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The error bars represent standard deviation of six different fish and the difference in abundance was tested using an unpaired t-test for ohnologues quantified in the same tissue (∗∗∗adj. p-value<0.001, ∗∗adj. p-value<0.01, ∗adj. p-value<0.05, n.s. adj. p-value>0.05)."}}], "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": "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 (unpaired t-test), 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": ["PXD010876", "PXD010869"], "resolved_accessions": ["PXD010876", "PXD010869"], "statements": ["Data are available via ProteomeXchange (PXD010876, PXD010869) and SWATHAtlas (PASS01237)."], "basis": "The paper names PXD010876, PXD010869 in PRIDE, via the ProteomeXchange Consortium and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:30747917", "data:geo:PXD010869", "asset:table:pmid:30747917:1", "asset:table:pmid:30747917:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD010869"]}, "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": "2026-10-31T18:13:51Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 30274, "completion_tokens": 1922, "cached_tokens": 784}}, "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:30747917", "type": "paper", "label": "pmid:30747917"}, {"id": "source:pmid:30747917", "type": "manuscript", "label": "PMID 30747917 full text"}, {"id": "data:geo:PXD010869", "type": "dataset", "label": "GEO PXD010869"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30747917", "type": "paper", "label": "pmid:30747917"}, {"id": "source:pmid:30747917", "type": "manuscript", "label": "PMID 30747917 full text"}, {"id": "data:geo:PXD010869", "type": "dataset", "label": "GEO PXD010869"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30747917", "type": "extraction", "used": ["source:pmid:30747917"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD010869", "type": "accession_resolution", "used": ["data:geo:PXD010869"], "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:30747917", "parent_hash": "sha256:ce9be569a7f30d64f0c90ce4c7114997e419d86ff75847b3a0241eb3a82d8fc8", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:PXD010869 licence not read", "asset:data:geo:PXD010869 not downloaded", "asset:data:geo:PXD010876 licence not read", "asset:data:geo:PXD010876 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": 0.93, "evidence": ["o extract quantitative measurements from the mass spectrometry data acquired in data-independent acquisitio"], "order_basis": "paper_text_order:183", "id": "assay:1"}]}