A multi-protease, multi-dissociation, bottom-up-to-top-down proteomic view of the Loxosceles intermedia venom.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28696408", "kind": "science-record", "revision": 5, "content_hash": "sha256:7e85e81a5451114d15954a7e06110258ab923578ad5cd5792db7965d1fda5268", "created_at": "2026-11-01T15:40:27Z", "updated_at": "2026-11-01T18:48:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A multi-protease, multi-dissociation, bottom-up-to-top-down proteomic view of the Loxosceles intermedia venom.", "doi": "10.1038/sdata.2017.90", "pmid": "28696408", "authors": ["Dilza Trevisan-Silva", "Aline V Bednaski", "Juliana S G Fischer", "Silvio S Veiga", "Nuno Bandeira", "Adrian Guthals", "Fabricio K Marchini", "Felipe V Leprevost", "Valmir C Barbosa", "Andrea Senff-Ribeiro", "Paulo C Carvalho"], "journal": "Scientific data", "year": 2017, "abstract": "Venoms are a rich source for the discovery of molecules with biotechnological applications, but their analysis is challenging even for state-of-the-art proteomics. Here we report on a large-scale proteomic assessment of the venom of Loxosceles intermedia, the so-called brown spider. Venom was extracted from 200 spiders and fractioned into two aliquots relative to a 10 kDa cutoff mass. Each of these was further fractioned and digested with trypsin (4 h), trypsin (18 h), pepsin (18 h), and chymotrypsin (18 h), then analyzed by MudPIT on an LTQ-Orbitrap XL ETD mass spectrometer fragmenting precursors by CID, HCD, and ETD. Aliquots of undigested samples were also analyzed. Our experimental design allowed us to apply spectral networks, thus enabling us to obtain meta-contig assemblies, and consequently de novo sequencing of practically complete proteins, culminating in a deep proteome assessment of the venom. Data are available via ProteomeXchange, with identifier PXD005523.", "claims": [{"id": "claim-data-access", "statement": "All mass spectrometry data are available from both the ProteomeXchange Consortium via the PRIDE45 partner repository, with dataset identifier PXD005523 (Data Citation 1), and our servers (http://proteomics.fiocruz.br/pcarvalho/lintermedia/venom/). A full list of the proteins, meta-contigs, and homologous sequences is made available in Table 1.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28696408", "locator": "sections[6] \"Data Records\" paragraph 2", "quote": "All mass spectrometry data are available from both the ProteomeXchange Consortium via the PRIDE45 partner repository, with dataset identifier PXD005523 (Data Citation 1), and our servers (http://proteomics.fiocruz.br/pcarvalho/lintermedia/venom/). A full list of the proteins, meta-contigs, and homologous sequences is made available in Table 1."}], "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:28696408"], "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:PXD005523"], "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:PXD005523"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28696408", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/sdata.2017.90", "sha256": "sha256:ac652a583129bb4eef175a72536f1a95bbb564c72b05aefbd531dc5ea58f8d83", "bytes": 23595, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/sdata.2017.90", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5505115", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD005523", "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=PXD005523", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD005523", "version": null, "note": "All mass spectrometry data are available from both the ProteomeXchange Consortium via the PRIDE45 partner repository, with dataset identifier PXD005523 (Data Citation 1), and our servers (http://proteomics.fiocruz.br/pcarvalho/lintermedia/venom/). A full list of the proteins, meta-contigs, and homologous sequences is made available in Table 1.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All mass spectrometry data are available from both the ProteomeXchange Consortium via the PRIDE45 partner repository, with dataset identifier PXD005523 (Data Citation 1), and our servers (http://proteomics.fiocruz.br/pcarvalho/lintermedia/venom/). A full list of the proteins, meta-contigs, and homologous sequences is made available in Table 1.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "A multi-protease, multi-dissociation, bottom-up-to-top-down proteomic view of the Loxosceles intermedia venom", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD005523 not downloaded", "asset:data:geo:PXD005523 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": ["PXD005523"], "resolved_accessions": ["PXD005523"], "statements": ["All mass spectrometry data are available from both the ProteomeXchange Consortium via the PRIDE45 partner repository, with dataset identifier PXD005523 (Data Citation 1), and our servers (http://proteomics.fiocruz.br/pcarvalho/lintermedia/venom/). A full list of the proteins, meta-contigs, and homologous sequences is made available in Table 1."], "basis": "The paper names PXD005523 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:28696408", "data:geo:PXD005523"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD005523"]}, "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": "2026-10-31T18:09:44Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 17373, "completion_tokens": 961, "cached_tokens": 11008}}, "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:28696408", "type": "paper", "label": "pmid:28696408"}, {"id": "source:pmid:28696408", "type": "manuscript", "label": "PMID 28696408 full text"}, {"id": "data:geo:PXD005523", "type": "dataset", "label": "GEO PXD005523"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28696408", "type": "paper", "label": "pmid:28696408"}, {"id": "source:pmid:28696408", "type": "manuscript", "label": "PMID 28696408 full text"}, {"id": "data:geo:PXD005523", "type": "dataset", "label": "GEO PXD005523"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28696408", "type": "extraction", "used": ["source:pmid:28696408"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD005523", "type": "accession_resolution", "used": ["data:geo:PXD005523"], "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:28696408", "parent_hash": "sha256:7c226bab8934be0a7bc6cece8d2fc06a3652beb6e32cd42ff041be320e6a1a2d", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:PXD005523 licence not read", "asset:data:geo:PXD005523 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"]}