Defining the Soluble and Extracellular Vesicle Protein Compartments of Plasma Using In-Depth Mass Spectrometry-Based Proteomics.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39141927", "kind": "science-record", "revision": 2, "content_hash": "sha256:ff94ba084f46c5c4c7bea446ebc6a14b607cb975e0962e8a74a54a4423faf2e1", "created_at": "2026-11-01T20:29:14Z", "updated_at": "2026-11-01T21:33:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Defining the Soluble and Extracellular Vesicle Protein Compartments of Plasma Using In-Depth Mass Spectrometry-Based Proteomics.", "doi": "10.1021/acs.jproteome.4c00490", "pmid": "39141927", "authors": ["Nidhi Sharma", "Silvia Angori", "AnnSofi Sandberg", "Georgios Mermelekas", "Janne Lehtiö", "Oscar P B Wiklander", "André Görgens", "Samir El Andaloussi", "Hanna Eriksson", "Maria Pernemalm"], "journal": "Journal of proteome research", "year": 2024, "abstract": "Plasma-derived extracellular vesicles (pEVs) are a potential source of diseased biomarker proteins. However, characterizing the pEV proteome is challenging due to its relatively low abundance and difficulties in enrichment. This study presents a streamlined workflow to identify EV proteins from cancer patient plasma using minimal sample input. Starting with 400 μL of plasma, we generated a comprehensive pEV proteome using size exclusion chromatography (SEC) combined with HiRIEF prefractionation-based mass spectrometry (MS). First, we compared the performance of HiRIEF and long gradient MS workflows using control pEVs, quantifying 2076 proteins with HiRIEF. In a proof-of-concept study, we applied SEC-HiRIEF-MS to a small cohort (12) of metastatic lung adenocarcinoma (LUAD) and malignant melanoma (MM) patients. We also analyzed plasma samples from the same patients to study the relationship between plasma and pEV proteomes. We identified and quantified 1583 proteins in cancer pEVs and 1468 proteins in plasma across all samples. While there was substantial overlap, the pEV proteome included several unique EV markers and cancer-related proteins. Differential analysis revealed 30 DEPs in LUAD vs the MM group, highlighting the potential of pEVs as biomarkers. This work demonstrates the utility of a prefractionation-based MS for comprehensive pEV proteomics and EV biomarker discovery. Data are available via ProteomeXchange with the identifiers PXD039338 and PXD038528.", "claims": [{"id": "claim-method", "statement": "The DEPs in the plasma and EV data sets were also identified using the t test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39141927", "locator": "sections[21] \"Statistical Analysis\" paragraph 2", "quote": "The DEPs in the plasma and EV data sets were also identified using the t test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during the study, are either included in the article or uploaded as supplementary data. MS raw data have been uploaded to the PRIDE repository via ProteomeXchange with accession number PXD039338 and PXD038528.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39141927", "locator": "sections[30] \"notes\" paragraph 1", "quote": "All data generated or analyzed during the study, are either included in the article or uploaded as supplementary data. MS raw data have been uploaded to the PRIDE repository via ProteomeXchange with accession number PXD039338 and PXD038528."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Differential analysis revealed 30 DEPs in LUAD vs the MM group, highlighting the potential of pEVs as biomarkers.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39141927", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Differential analysis revealed 30 DEPs in LUAD vs the MM group, highlighting the potential of pEVs as biomarkers."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Differential analysis revealed 30 DEPs in LUAD vs the MM group, highlighting the potential of pEVs as biomarkers.", "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:39141927"], "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:39141927", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acs.jproteome.4c00490", "sha256": "sha256:2462bd21c1c33b6c805479ee9b3ab4454ab0ac4963c6eace513aa875f6fafb89", "bytes": 61299, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acs.jproteome.4c00490", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11385381", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "principal component analysis"}}, {"id": "method-2", "family": null, "specific": null, "label": "t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The DEPs in the plasma and EV data sets were also identified using the t test."}}], "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": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": ["PXD039338 and PXD038528"], "resolved_accessions": [], "statements": ["All data generated or analyzed during the study, are either included in the article or uploaded as supplementary data. MS raw data have been uploaded to the PRIDE repository via ProteomeXchange with accession number PXD039338 and PXD038528."], "basis": "The paper names PXD039338 and PXD038528, 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": ["pca_fit"], "assets": ["source:pmid:39141927"], "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": "2026-11-01T19:28:11Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15928, "completion_tokens": 1260, "cached_tokens": 128}}, "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:39141927", "type": "paper", "label": "pmid:39141927"}, {"id": "source:pmid:39141927", "type": "manuscript", "label": "PMID 39141927 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39141927", "type": "paper", "label": "pmid:39141927"}, {"id": "source:pmid:39141927", "type": "manuscript", "label": "PMID 39141927 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39141927", "type": "extraction", "used": ["source:pmid:39141927"], "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:39141927", "parent_hash": "sha256:62ebaa0372852336b08314a258c0b0973eb691daf8dc353c1749222babc1e48a", "fork_of": null, "generation": 1}, "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": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["principal component analysis"], "order_basis": "analysis_only", "id": "assay:1"}]}