A Novel Blood Proteomic Signature for Prostate Cancer.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36831393", "kind": "science-record", "revision": 4, "content_hash": "sha256:3c91e24ed2c7c79a658ea86f15d528cce702f6da4ef64371694b00bf75034994", "created_at": "2026-11-01T19:01:26Z", "updated_at": "2026-11-01T22:51:21Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A Novel Blood Proteomic Signature for Prostate Cancer.", "doi": "10.3390/cancers15041051", "pmid": "36831393", "authors": ["Ammara Muazzam", "Matt Spick", "Olivier N F Cexus", "Bethany Geary", "Fowz Azhar", "Hardev Pandha", "Agnieszka Michael", "Rachel Reed", "Sarah Lennon", "Lee A Gethings", "Robert S Plumb", "Anthony D Whetton", "Nophar Geifman", "Paul A Townsend"], "journal": "Cancers", "year": 2023, "abstract": "Prostate cancer is the most common malignant tumour in men. Improved testing for diagnosis, risk prediction, and response to treatment would improve care. Here, we identified a proteomic signature of prostate cancer in peripheral blood using data-independent acquisition mass spectrometry combined with machine learning. A highly predictive signature was derived, which was associated with relevant pathways, including the coagulation, complement, and clotting cascades, as well as plasma lipoprotein particle remodeling. We further validated the identified biomarkers against a second cohort, identifying a panel of five key markers (GP5, SERPINA5, ECM1, IGHG1, and THBS1) which retained most of the diagnostic power of the overall dataset, achieving an AUC of 0.91. Taken together, this study provides a proteomic signature complementary to PSA for the diagnosis of patients with localised prostate cancer, with the further potential for assessing risk of future development of prostate cancer. Data are available via ProteomeXchange with identifier PXD025484.", "claims": [{"id": "claim-method", "statement": "A random forest (RF) model was used for feature selection from the initial protein dataset, splitting the data in the ratio of 67:33 (training/testing using stratification), setting ntree to 1000, maximum leaf nodes to 16, and random seed to 1. Recursive feature elimination with cross-validation was used to select the individual features from the training set (maximising accuracy). Classifier model construction was performed using logistic regression.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36831393", "locator": "sections[9] \"2.7. Biomarker Analysis and Development and Evaluation of Classification and Regression Models\" paragraph 2", "quote": "A random forest (RF) model was used for feature selection from the initial protein dataset, splitting the data in the ratio of 67:33 (training/testing using stratification), setting ntree to 1000, maximum leaf nodes to 16, and random seed to 1. Recursive feature elimination with cross-validation was used to select the individual features from the training set (maximising accuracy). Classifier model construction was performed using logistic regression."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data needed to evaluate the conclusions in the paper are present in the paper and/or the Supplementary information. Raw data files are available via ProteomeXchange with identifier PXD025484 and can be accessed through ProteomeXchange using reviewer account details: Username: reviewer_pxd025484@ebi.ac.uk and Password: W0lWREBN.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36831393", "locator": "sections[22] \"Data Availability Statement\" paragraph 2", "quote": "All data needed to evaluate the conclusions in the paper are present in the paper and/or the Supplementary information. Raw data files are available via ProteomeXchange with identifier PXD025484 and can be accessed through ProteomeXchange using reviewer account details: Username: reviewer_pxd025484@ebi.ac.uk and Password: W0lWREBN."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A five-marker serum protein signature—GP5, SERPINA5, ECM1, IGHG1, and THBS1—distinguished newly diagnosed prostate cancer patients from healthy controls with an AUC of 0.91.", "kind": "quantitative", "target": {"value": 0.91, "unit": "auc", "tolerance": null, "source": "We further validated the identified biomarkers against a second cohort, identifying a panel of five key markers (GP5, SERPINA5, ECM1, IGHG1, and THBS1) which retained most of the diagnostic power of the overall dataset, achieving an AUC of 0.91."}, "evidence": [{"asset": "source:pmid:36831393", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We further validated the identified biomarkers against a second cohort, identifying a panel of five key markers (GP5, SERPINA5, ECM1, IGHG1, and THBS1) which retained most of the diagnostic power of the overall dataset, achieving an AUC of 0.91."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "A five-marker serum protein signature—GP5, SERPINA5, ECM1, IGHG1, and THBS1—distinguished newly diagnosed prostate cancer patients from healthy controls with an AUC of 0.91.", "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:36831393"], "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:PXD025484"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:machine_learning_random_forest", "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:PXD025484"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36831393", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/cancers15041051", "sha256": "sha256:061414ce0daf8c32708730e74e6e8b3c3b9c6d4fcd62f59727053622217a11e3", "bytes": 67735, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/cancers15041051", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9954127", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD025484", "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=PXD025484", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD025484", "version": null, "note": "All data needed to evaluate the conclusions in the paper are present in the paper and/or the Supplementary information. Raw data files are available via ProteomeXchange with identifier PXD025484 and can be accessed through ProteomeXchange using reviewer account details: Username: reviewer_pxd025484@ebi.ac.uk and Password: W0lWREBN.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data needed to evaluate the conclusions in the paper are present in the paper and/or the Supplementary information. Raw data files are available via ProteomeXchange with identifier PXD025484 and can be accessed through ProteomeXchange using reviewer account details: Username: reviewer_pxd025484@ebi.ac.uk and Password: W0lWREBN.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Peripheral blood proteomic signature of newly diagnosed prostate cancer", "resolution_checked_at": "2026-11-01T18:46:41Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD025484 not downloaded", "asset:data:geo:PXD025484 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A random forest (RF) model was used for feature selection from the initial protein dataset, splitting the data in the ratio of 67:33 (training/testing using stratification), setting ntree to 1000, maximum leaf nodes to 16, and random seed to 1. Recursive feature elimination with cross-validation was used to select the individual features from the training set (maximising accuracy). Classifier model construction was performed using logistic regression."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-3", "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-4", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "linear regression"}}, {"id": "method-5", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "logistic regression"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "glm_logit_fit", "expected_value": 0.91, "unit": "auc", "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_differs_from_extractor", "method.machine_learning_random_forest"]}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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": ["PXD025484"], "resolved_accessions": ["PXD025484"], "statements": ["All data needed to evaluate the conclusions in the paper are present in the paper and/or the Supplementary information. Raw data files are available via ProteomeXchange with identifier PXD025484 and can be accessed through ProteomeXchange using reviewer account details: Username: reviewer_pxd025484@ebi.ac.uk and Password: W0lWREBN."], "basis": "The paper names PXD025484 in ProteomeXchange and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:36831393", "data:geo:PXD025484"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD025484"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:31:24Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 19391, "completion_tokens": 1534, "cached_tokens": 256}}, "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:36831393", "type": "paper", "label": "pmid:36831393"}, {"id": "source:pmid:36831393", "type": "manuscript", "label": "PMID 36831393 full text"}, {"id": "data:geo:PXD025484", "type": "dataset", "label": "GEO PXD025484"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36831393", "type": "paper", "label": "pmid:36831393"}, {"id": "source:pmid:36831393", "type": "manuscript", "label": "PMID 36831393 full text"}, {"id": "data:geo:PXD025484", "type": "dataset", "label": "GEO PXD025484"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36831393", "type": "extraction", "used": ["source:pmid:36831393"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD025484", "type": "accession_resolution", "used": ["data:geo:PXD025484"], "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:36831393", "parent_hash": "sha256:988973bc47eb1164b344196da968d0537866e76ff9b7438a150904337518729b", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:PXD025484 licence not read", "asset:data:geo:PXD025484 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "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": ["A Novel Blood Proteomic Signature for Prostate Cancer.", "0.91. Taken together, this study provides a proteomic signature complementary to PSA for the diagn", "ancer Patients To identify a specific, novel proteomic signature for clinical onset in PCa patients", "ression analysis of the relationship between proteomic signature and PSA score, however, did not fi"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "elisa", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["addition of PSA level values (as measured by ELISA) further increased the predictive ability of"], "order_basis": "paper_text_order:6837", "id": "assay:2"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["A random forest (RF) model was used for feature selection from the initial protein dataset, splitting the data in the ratio of 67:33 (training/testing using stratification), setting ntree to 1000, maximum leaf nodes to 16, and random seed to 1. Recursive feature elimination with cross-validation was used to select the individual features from the training set (maximising accuracy). Classifier model construction was performed using logistic regression."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]}