The proteome of human retina.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:25407473", "kind": "science-record", "revision": 2, "content_hash": "sha256:2b6191816deca86963e5bbf5ff2ef0e7ff981182fdb6ab68d9535045e2019cfe", "created_at": "2026-11-01T15:40:07Z", "updated_at": "2026-11-01T18:47:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "The proteome of human retina.", "doi": "10.1002/pmic.201400397", "pmid": "25407473", "authors": ["Pingbo Zhang", "Craig Dufresne", "Randi Turner", "Sara Ferri", "Vidya Venkatraman", "Rabia Karani", "Gerard A Lutty", "Jennifer E Van Eyk", "Richard D Semba"], "journal": "Proteomics", "year": 2015, "abstract": "The retina is a delicate tissue that detects light, converts photochemical energy into neural signals, and transmits the signals to the visual cortex of the brain. A detailed protein inventory of the proteome of the normal human eye may provide a foundation for new investigations into both the physiology of the retina and the pathophysiology of retinal diseases. To provide an inventory, proteins were extracted from five retinas of normal eyes and fractionated using SDS-PAGE. After in-gel digestion, peptides were analyzed in duplicate using LC-MS/MS on an Orbitrap Elite mass spectrometer. A total of 3436 nonredundant proteins were identified in the human retina, including 20 unambiguous protein isoforms, of which eight have not previously been demonstrated to exist at the protein level. The proteins identified in the retina included most of the enzymes involved in the visual cycle and retinoid metabolism. One hundred and fifty-eight proteins that have been associated with age-related macular degeneration were identified in the retina. The MS proteome database of the human retina may serve as a valuable resource for future investigations of retinal biology and disease. All MS data have been deposited in the ProteomeXchange with identifier PXD001242 (http://proteomecentral.proteomexchange.org/dataset/PXD001242).", "claims": [{"id": "claim-target-result", "statement": "The study identified 3,436 non-redundant proteins in the normal human retina using protein identifications accepted at ≥90.0% probability with a false discovery rate of 0.81% for proteins; the mass spectrometry data were deposited in ProteomeXchange via PRIDE under PXD001242.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:25407473", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A total of 3,436 non-redundant proteins were identified in the human retina, including 20 unambiguous protein isoforms, of which 8 have not previously been demonstrated to exist at the protein level."}, {"asset": "source:pmid:25407473", "locator": "sections[7] \"p\" paragraph 1", "quote": "Protein identifications were accepted if they could be established at ≥90.0% probability and contained at least 1 identified peptide."}, {"asset": "source:pmid:25407473", "locator": "sections[7] \"p\" paragraph 1", "quote": "Protein Prophet algorithm was used to assign protein probabilities [10] using a false discovery rate of 0.13% for peptides and 0.81% for proteins."}, {"asset": "source:pmid:25407473", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD001242."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The study identified 3,436 non-redundant proteins in the normal human retina using protein identifications accepted at ≥90.0% probability with a false discovery rate of 0.81% for proteins; the mass spectrometry data were deposited in ProteomeXchange via PRIDE under PXD001242.", "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:25407473"], "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:25407473", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/pmic.201400397", "sha256": "sha256:d65c7d68d69de1acb5d5e02200e9f2bf8e47772ec2bc9a66f90bcf54a2834d9a", "bytes": 13064, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/pmic.201400397", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4329094", "source": "ncbi_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "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": [], "resolved_accessions": [], "statements": [], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:25407473"], "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": "2026-10-31T18:23:10Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 2, "usage": {"prompt_tokens": 7142, "completion_tokens": 537, "cached_tokens": 512}}, "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:25407473", "type": "paper", "label": "pmid:25407473"}, {"id": "source:pmid:25407473", "type": "manuscript", "label": "PMID 25407473 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:25407473", "type": "paper", "label": "pmid:25407473"}, {"id": "source:pmid:25407473", "type": "manuscript", "label": "PMID 25407473 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-25407473", "type": "extraction", "used": ["source:pmid:25407473"], "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:25407473", "parent_hash": "sha256:33813e9631171ef098c433ed204093b4ee35c2a28773ee2f0f7738f5bbc00c64", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": 0.93, "evidence": ["n, peptides were analyzed in duplicate using LC-MS/MS on an Orbitrap Elite mass spectrometer. A to"], "order_basis": "paper_text_order:531", "id": "assay:1"}]}