Exploring the Molecular Tapestry: Organ-Specific Peptide and Protein Ultrafiltrates and Their Role in Therapeutics.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38474110", "kind": "science-record", "revision": 3, "content_hash": "sha256:a71d4f3e384713bebfcff81b45d45c70e8fe88200997aa4a38407c3063cfaafc", "created_at": "2026-11-01T19:20:25Z", "updated_at": "2026-11-01T21:32:41Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Exploring the Molecular Tapestry: Organ-Specific Peptide and Protein Ultrafiltrates and Their Role in Therapeutics.", "doi": "10.3390/ijms25052863", "pmid": "38474110", "authors": ["Jakub Peter Slivka", "Chris Bauer", "Alexander Younsi", "Michelle B F Wong", "Mike K S Chan", "Thomas Skutella"], "journal": "International journal of molecular sciences", "year": 2024, "abstract": "This study aims to characterize the proteome composition of organ-derived protein extracts from rabbits. Protein isolation was performed using soft homogenization and size exclusion via ultrafiltration. The proteome analysis of the ultrafiltrates was conducted using gel electrophoresis, and the mass spectrometry data were subjected to gene ontology analysis. Proteomic profiling revealed comprehensive protein profiles associated with RNA regulation, fatty acid binding, inflammatory response, oxidative stress, and metabolism. Additionally, our results demonstrate the presence of abundant small proteins, as observed in the mass spectrometry datasets. Small proteins and peptides are crucial in transcription modulation and various biological processes. The protein networks identified in the ultrafiltrates have the potential to enhance and complement biological therapeutic interventions. Data are available via ProteomeXchange with identifier PXD050039.", "claims": [{"id": "claim-method", "statement": "Functional components were found using an over-representation approach while utilizing the KEGG pathways repository, and we also examined other pathways.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38474110", "locator": "sections[18] \"4.6. Bioinformatics\" paragraph 3", "quote": "Functional components were found using an over-representation approach while utilizing the KEGG pathways repository, and we also examined other pathways."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange with identifier PXD050039.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38474110", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD050039."}], "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:38474110"], "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:PXD050039"], "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:PXD050039"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38474110", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/ijms25052863", "sha256": "sha256:a24a8bc3598ac0c44c18fcbe5216733898e843716662e7cc18c3eb91d031e82e", "bytes": 78458, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/ijms25052863", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10931619", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD050039", "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=PXD050039", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD050039", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD050039.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD050039.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Analysis of NOP ultrafiltrates from different rabbit tissues", "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:PXD050039 not downloaded", "asset:data:geo:PXD050039 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "over-representation analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Functional components were found using an over-representation approach while utilizing the KEGG pathways repository, and we also examined other pathways."}}], "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 (over-representation analysis), 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": ["PXD050039", "10.6019/PXD050039"], "resolved_accessions": ["PXD050039"], "statements": ["Data are available via ProteomeXchange with identifier PXD050039."], "basis": "The paper names PXD050039 in 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:38474110", "data:geo:PXD050039"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD050039"]}, "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": "2026-11-01T19:11:44Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 20502, "completion_tokens": 1457, "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:38474110", "type": "paper", "label": "pmid:38474110"}, {"id": "source:pmid:38474110", "type": "manuscript", "label": "PMID 38474110 full text"}, {"id": "data:geo:PXD050039", "type": "dataset", "label": "GEO PXD050039"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38474110", "type": "paper", "label": "pmid:38474110"}, {"id": "source:pmid:38474110", "type": "manuscript", "label": "PMID 38474110 full text"}, {"id": "data:geo:PXD050039", "type": "dataset", "label": "GEO PXD050039"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38474110", "type": "extraction", "used": ["source:pmid:38474110"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD050039", "type": "accession_resolution", "used": ["data:geo:PXD050039"], "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:38474110", "parent_hash": "sha256:6a484ac248c13a814d88867ce310e264f66f626a6496dd46f5d0d7dbea1f98dc", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD050039 licence not read", "asset:data:geo:PXD050039 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": 0.99, "evidence": ["conducted using gel electrophoresis, and the mass spectrometry data were subjected to gene ontology analysi", "abundant small proteins, as observed in the mass spectrometry datasets. Small proteins and peptides are cr", "ta were subjected to gene ontology analysis. Proteomic profiling revealed comprehensive protein pro"], "order_basis": "paper_text_order:367", "id": "assay:1"}]}