Backyard Proteomics: A Case Study with the Black Widow Spider.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40721992", "kind": "science-record", "revision": 1, "content_hash": "sha256:b06182649b2d4231e56cd3004f4a0e69eb90da4df8bcb860c47056210f92ef02", "created_at": "2026-11-01T20:30:48Z", "updated_at": "2026-11-01T20:30:48Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Backyard Proteomics: A Case Study with the Black Widow Spider.", "doi": "10.1021/acs.jproteome.5c00342", "pmid": "40721992", "authors": ["Tarsh Shah", "Jackson A Fitzpatrick", "Benjamin C Orsburn"], "journal": "Journal of proteome research", "year": 2025, "abstract": "Nearly all methods of mass-spectrometry-based proteomics rely on knowing the proteome of the species. In less studied organisms without annotated genomes, it can seem impossible to perform proteomic analysis. In this study, we sought to answer the question: does enough information exist to do proteomics on any organism we want? As a case study, we started with material available due to an infestation of a home with black widow spiders. Thanks to the recent publication of an annotated genome for one species of black widow spider, we were able to identify 5502 protein groups and assign putative annotations using ortholog mapping. We also demonstrate that had we not had this resource, over 2000 proteins could be identified using other available spider genome annotations, despite their unrelatedness. Moreover, regardless of the spider proteome used, proteins annotated as toxins were almost exclusively observed in the main body of the mature female black widow spider. Overall, these results provide a draft proteome map for the black widow spider and valuable data for validating machine learning models while also suggesting that the door to insightful quantitative proteomics may already be open for millions of less studied organisms. All raw and processed proteomic data are available through the ProteomeXchange repository as accession PXD051601.", "claims": [{"id": "claim-data-access", "statement": "All raw and processed proteomic data are available through the ProteomeXchange repository as accession PXD051601.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40721992", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "All raw and processed proteomic data are available through the ProteomeXchange repository as accession PXD051601."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Over 2000 proteins could be identified using other available spider genome annotations, despite their unrelatedness.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40721992", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Moreover, regardless of the spider proteome used, proteins annotated as toxins were almost exclusively observed in the main body of the mature female black widow spider."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Over 2000 proteins could be identified using other available spider genome annotations, despite their unrelatedness.", "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:40721992"], "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_unresolved", "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:PXD051601"], "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:PXD051601"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_unresolved"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40721992", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acs.jproteome.5c00342", "sha256": "sha256:c6f5dae3beedbecc5e657ddc5641ae5ee14dd0ad463d361573c6d37bba787d29", "bytes": 31420, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acs.jproteome.5c00342", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12418487", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD051601", "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=PXD051601", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD051601", "version": null, "note": "All raw and processed proteomic data are available through the ProteomeXchange repository as accession PXD051601.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All raw and processed proteomic data are available through the ProteomeXchange repository as accession PXD051601.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T20:16:17Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD051601 not downloaded", "asset:data:geo:PXD051601 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": "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": ["PXD051601"], "resolved_accessions": [], "statements": ["All raw and processed proteomic data are available through the ProteomeXchange repository as accession PXD051601."], "basis": "The paper names PXD051601, but the accession does not resolve in the repository (not_in_proteomexchange), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40721992", "data:geo:PXD051601"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD051601"]}, "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": "2026-11-01T19:57:54Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8375, "completion_tokens": 1450, "cached_tokens": 264}}, "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:40721992", "type": "paper", "label": "pmid:40721992"}, {"id": "source:pmid:40721992", "type": "manuscript", "label": "PMID 40721992 full text"}, {"id": "data:geo:PXD051601", "type": "dataset", "label": "GEO PXD051601"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40721992", "type": "paper", "label": "pmid:40721992"}, {"id": "source:pmid:40721992", "type": "manuscript", "label": "PMID 40721992 full text"}, {"id": "data:geo:PXD051601", "type": "dataset", "label": "GEO PXD051601"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40721992", "type": "extraction", "used": ["source:pmid:40721992"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD051601", "type": "accession_resolution", "used": ["data:geo:PXD051601"], "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:PXD051601 licence not read", "asset:data:geo:PXD051601 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"]}