A large-scale proteogenomics study of apicomplexan pathogens-Toxoplasma gondii and Neospora caninum.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:25867681", "kind": "science-record", "revision": 4, "content_hash": "sha256:89ab568c5e32304ca70c1abe00a8ffa59c53b47691f32cbd686cd883fa879703", "created_at": "2026-11-01T15:40:08Z", "updated_at": "2026-11-01T21:19:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A large-scale proteogenomics study of apicomplexan pathogens-Toxoplasma gondii and Neospora caninum.", "doi": "10.1002/pmic.201400553", "pmid": "25867681", "authors": ["Ritesh Krishna", "Dong Xia", "Sanya Sanderson", "Achchuthan Shanmugasundram", "Sarah Vermont", "Axel Bernal", "Gianluca Daniel-Naguib", "Fawaz Ghali", "Brian P Brunk", "David S Roos", "Jonathan M Wastling", "Andrew R Jones"], "journal": "Proteomics", "year": 2015, "abstract": "Proteomics data can supplement genome annotation efforts, for example being used to confirm gene models or correct gene annotation errors. Here, we present a large-scale proteogenomics study of two important apicomplexan pathogens: Toxoplasma gondii and Neospora caninum. We queried proteomics data against a panel of official and alternate gene models generated directly from RNASeq data, using several newly generated and some previously published MS datasets for this meta-analysis. We identified a total of 201 996 and 39 953 peptide-spectrum matches for T. gondii and N. caninum, respectively, at a 1% peptide FDR threshold. This equated to the identification of 30 494 distinct peptide sequences and 2921 proteins (matches to official gene models) for T. gondii, and 8911 peptides/1273 proteins for N. caninum following stringent protein-level thresholding. We have also identified 289 and 140 loci for T. gondii and N. caninum, respectively, which mapped to RNA-Seq-derived gene models used in our analysis and apparently absent from the official annotation (release 10 from EuPathDB) of these species. We present several examples in our study where the RNA-Seq evidence can help in correction of the current gene model and can help in discovery of potential new genes. The findings of this study have been integrated into the EuPathDB. The data have been deposited to the ProteomeXchange with identifiers PXD000297and PXD000298.", "claims": [{"id": "claim-method", "statement": "For general identifications of protein groups—1% FDR is implemented. For (protein group) identifications that suggest improvements to the current gene models, 5% FDR threshold is applied—as discussed in the ProteoAnnotator publication [47]. The MS/MS datasets and result files are available at the ProteomeXchange Consortium with the dataset identifiers PXD000297 and PXD000298.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25867681", "locator": "sections[6] \"2.2 Proteogenomic analysis pipeline\" paragraph 2", "quote": "For general identifications of protein groups—1% FDR is implemented."}, {"asset": "source:pmid:25867681", "locator": "sections[6] \"2.2 Proteogenomic analysis pipeline\" paragraph 2", "quote": "For (protein group) identifications that suggest improvements to the current gene models, 5% FDR threshold is applied—as discussed in the ProteoAnnotator publication [47]."}, {"asset": "source:pmid:25867681", "locator": "sections[13] \"3.2 Description of available result files\" paragraph 2", "quote": "The MS/MS datasets and result files are available at the ProteomeXchange Consortium with the dataset identifiers PXD000297 and PXD000298."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The MS/MS datasets and result files are available at the ProteomeXchange Consortium with the dataset identifiers PXD000297 and PXD000298.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25867681", "locator": "sections[13] \"3.2 Description of available result files\" paragraph 2", "quote": "The MS/MS datasets and result files are available at the ProteomeXchange Consortium with the dataset identifiers PXD000297 and PXD000298."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using a 1% peptide-FDR threshold, the study identified 201,996 peptide-spectrum matches for T. gondii and 39,953 for N. caninum, with the MS/MS datasets and result files available through ProteomeXchange identifiers PXD000297 and PXD000298.", "kind": "quantitative", "target": {"value": 1.0, "unit": "per cent", "tolerance": null, "source": "We identified a total of 201 996 and 39 953 peptide-spectrum matches for T. gondii and N. caninum, respectively, at a 1% peptide FDR threshold."}, "evidence": [{"asset": "source:pmid:25867681", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We identified a total of 201 996 and 39 953 peptide-spectrum matches for T. gondii and N. caninum, respectively, at a 1% peptide FDR threshold."}, {"asset": "source:pmid:25867681", "locator": "sections[13] \"3.2 Description of available result files\" paragraph 2", "quote": "The MS/MS datasets and result files are available at the ProteomeXchange Consortium with the dataset identifiers PXD000297 and PXD000298."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Using a 1% peptide-FDR threshold, the study identified 201,996 peptide-spectrum matches for T. gondii and 39,953 for N. caninum, with the MS/MS datasets and result files available through ProteomeXchange identifiers PXD000297 and PXD000298.", "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:25867681"], "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:25867681", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/pmic.201400553", "sha256": "sha256:359b2fccd4c471cc85c91a3a4b078f131a6835ed93bcbcd949e8531cc4b6ecbe", "bytes": 46533, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/pmic.201400553", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4692086", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:25867681:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:38cc40606428c6e577a163c5ab49eb0d2b5399baa5b0cb25fb6c7a7ee0909c5d", "bytes": 650, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tbl1", "version": null, "note": "The composition of gene models and the number of representative proteins identified in total across our full data collection", "structure": {"pmcid": "PMC4692086", "section_index": 11, "section_title": "3 Results and discussion", "row_count": 5, "column_count": 6}, "table": {"label": "Table 1", "caption": "The composition of gene models and the number of representative proteins identified in total across our full data collection", "rows": [["Species", "Gene model", "Total database entries", "Total amino acid count", "Representative proteins identified as group leadersa)", "Alternate loci with q-value < 0.05"], ["T. gondii", "Official", "8322", "6 669 204", "2921", "0"], ["", "RNA-Seq", "86 699", "37 847 722", "289", "191"], ["N. caninum", "Official", "7122", "6 054 032", "1273", "0"], ["", "RNA-Seq", "13 777", "8 158 875", "140", "101"]], "row_count": 5, "column_count": 6, "numeric_cells": 17, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tbl1"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "False discovery rate (FDR) control using 1% FDR for general protein-group identifications and 5% FDR for identifications suggesting gene-model improvements.", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "For general identifications of protein groups—1% FDR is implemented. For (protein group) identifications that suggest improvements to the current gene models, 5% FDR threshold is applied—as discussed in the ProteoAnnotator publication [47]. The MS/MS datasets and result files are available at the ProteomeXchange Consortium with the dataset identifiers PXD000297 and PXD000298."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": null, "expected_value": 1.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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 (False discovery rate (FDR) control using 1% FDR for general protein-group identifications and 5% FDR for identifications suggesting gene-model improvements.), 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": ["PXD000297 and PXD000298"], "resolved_accessions": [], "statements": ["The MS/MS datasets and result files are available at the ProteomeXchange Consortium with the dataset identifiers PXD000297 and PXD000298."], "basis": "The paper names PXD000297 and PXD000298, but the accession does not resolve in the repository (no reason recorded), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:25867681", "asset:table:pmid:25867681:1"], "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": "2026-10-31T18:23:44Z", "independence": "same_provider"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 99725, "completion_tokens": 4198, "cached_tokens": 25888}}, "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:25867681", "type": "paper", "label": "pmid:25867681"}, {"id": "source:pmid:25867681", "type": "manuscript", "label": "PMID 25867681 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:25867681", "type": "paper", "label": "pmid:25867681"}, {"id": "source:pmid:25867681", "type": "manuscript", "label": "PMID 25867681 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-25867681", "type": "extraction", "used": ["source:pmid:25867681"], "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:25867681", "parent_hash": "sha256:ab0df7db7ec07d6b5b1902bd23e6ffa250163da07011228c5f0099d647655564", "fork_of": null, "generation": 3}, "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"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["lternate gene models generated directly from RNASeq data, using several newly generated and some", "nd N. caninum, respectively, which mapped to RNA-Seq-derived gene models used in our analysis and", "sent several examples in our study where the RNA-Seq evidence can help in correction of the curre"], "order_basis": "paper_text_order:433", "id": "assay:1"}]}