Dataset of quantitative proteomic analysis to understand aging processes in rabbit liver.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32490075", "kind": "science-record", "revision": 7, "content_hash": "sha256:660e7849468b4a8edfdfff9b00a3da5aeb1fc9a7a1231b6b248a5c894898add4", "created_at": "2026-11-01T15:41:02Z", "updated_at": "2026-11-01T22:01:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset of quantitative proteomic analysis to understand aging processes in rabbit liver.", "doi": "10.1016/j.dib.2020.105701", "pmid": "32490075", "authors": ["Bushra Amin", "Renã A S Robinson"], "journal": "Data in brief", "year": 2020, "abstract": "Here, we present a proteomics dataset of liver proteins to understand aging in rabbits, which complements the publication \"Quantitative proteomics to study aging in rabbit liver\" [1]. This dataset was generated to understand the molecular basis and metabolic changes of aging processes in liver, which is the main organ involved in metabolism, detoxification, transport, and signaling. Proteins from young, middle, and old age rabbits were extracted and digested. Generated peptides were labeled with light or heavy dimethyl groups at their N-termini, while lysine amines were labeled with TMT10-plex using a cPILOT workflow [2]. Labeled peptides were fractionated by basic pH reverse phase chromatography and analyzed with online reverse phase LC coupled with tandem mass spectrometry (MS/MS and MS3). The RAW files were generated using a Fusion Lumos Orbitrap mass spectrometer (Thermo Scientific) and processed with Proteome Discoverer (PD) version 2.2 to generate a list of identified and quantified proteins. Data was searched against the Rabbit UniProtKB redundant database. A total of 3,867 proteins were identified corresponding to 2,586 protein groups and 22,229 peptides. Dynamic levels of age-related proteins associated with fat metabolism, mitochondrial dysfunction, and protein degradation were detected. The mass spectrometry proteomics data (RAW files) and processed Proteome Discoverer 2.2 files (MSF files) have been deposited to the Proteomics Identification Database (PRIDE) ProteomeXchange Consortium and can be accessed with the dataset identifier PDX013220 (http://www.ebi.ac.uk/pride/archive/projects/PXD013220).", "claims": [{"id": "claim-method", "statement": "A list of statistically-significant proteins was generated through a student's t-test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32490075", "locator": "sections[10] \"Data normalization and statistics\" paragraph 2", "quote": "A list of statistically-significant proteins was generated through a student's t-test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data and processed PD 2.2 files are available at Proteomics Identifications Database (PRIDE) ProteomeXchange Consortium with the dataset identifier PXD013220 http://www.ebi.ac.uk/pride/archive/projects/PXD013220 and full description of research findings [1].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32490075", "locator": "sections[14] \"Transparency document\" paragraph 2", "quote": "The mass spectrometry proteomics data and processed PD 2.2 files are available at Proteomics Identifications Database (PRIDE) ProteomeXchange Consortium with the dataset identifier PXD013220 http://www.ebi.ac.uk/pride/archive/projects/PXD013220 and full description of research findings [1]."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "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:32490075"], "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:PXD013220"], "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:student_t", "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:PXD013220"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32490075", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2020.105701", "sha256": "sha256:d2e2d9ea2562292a101d2edfa980bd75ab150a8b3ae77f37b28845ee8c571c4b", "bytes": 17280, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2020.105701", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7262418", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD013220", "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=PXD013220", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD013220", "version": null, "note": "The mass spectrometry proteomics data and processed PD 2.2 files are available at Proteomics Identifications Database (PRIDE) ProteomeXchange Consortium with the dataset identifier PXD013220 http://www.ebi.ac.uk/pride/archive/projects/PXD013220 and full description of research findings [1].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data and processed PD 2.2 files are available at Proteomics Identifications Database (PRIDE) ProteomeXchange Consortium with the dataset identifier PXD013220 http://www.ebi.ac.uk/pride/archive/projects/PXD013220 and full description of research findings [1].", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Quantitative Proteomics to Study Aging in Rabbit Liver", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32490075:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c5921b072fe6281ce0c2d78313726f58f73e99ee039a938ed0adeaef06a9904c", "bytes": 576, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#tbl0001", "version": null, "note": "Biological and technical variation with and without data normalization.", "structure": {"pmcid": "PMC7262418", "section_index": 4, "section_title": "Data", "row_count": 5, "column_count": 9}, "table": {"label": "Table 1", "caption": "Biological and technical variation with and without data normalization.", "rows": [["", "Raw Data", "Normalized Data"], ["", "CVa", "Fold Cutoff", "CVb", "Fold Cutoff", "CVa", "Fold Cutoff", "CVb", "Fold Cutoff"], ["Biological replicatesc", "0.32", "", "0.19", "", "0.29", "", "0.14", ""], ["Technical replicatesd", "0.36", "1.26", "0.29", "1.17", "0.27", "1.23", "0.17", "1.12"], ["Minimum fold cutoff = 1.12, Maximum fold cutoff = 1.26, Mean fold cutoff = 1.195"]], "row_count": 5, "column_count": 9, "numeric_cells": 13, "header_rows": 2, "locator": "section[4]/table-wrap[1]#tbl0001"}}], "gaps": ["asset:data:geo:PXD013220 not downloaded", "asset:data:geo:PXD013220 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A list of statistically-significant proteins was generated through a student's t-test."}}], "targets": [], "gaps": ["method.student_t"]}, "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": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_test."}, "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": ["PXD013220"], "resolved_accessions": ["PXD013220"], "statements": ["The mass spectrometry proteomics data and processed PD 2.2 files are available at Proteomics Identifications Database (PRIDE) ProteomeXchange Consortium with the dataset identifier PXD013220 http://www.ebi.ac.uk/pride/archive/projects/PXD013220 and full description of research findings [1]."], "basis": "The paper names PXD013220 in Proteomics Identifications Database (PRIDE) 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:32490075", "data:geo:PXD013220", "asset:table:pmid:32490075:1"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD013220"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:22Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 14306, "completion_tokens": 1279, "cached_tokens": 785}}, "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:32490075", "type": "paper", "label": "pmid:32490075"}, {"id": "source:pmid:32490075", "type": "manuscript", "label": "PMID 32490075 full text"}, {"id": "data:geo:PXD013220", "type": "dataset", "label": "GEO PXD013220"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32490075", "type": "paper", "label": "pmid:32490075"}, {"id": "source:pmid:32490075", "type": "manuscript", "label": "PMID 32490075 full text"}, {"id": "data:geo:PXD013220", "type": "dataset", "label": "GEO PXD013220"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32490075", "type": "extraction", "used": ["source:pmid:32490075"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD013220", "type": "accession_resolution", "used": ["data:geo:PXD013220"], "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:32490075", "parent_hash": "sha256:dd24e3b0778ec18198e08c9200034ea1da262cfcb736aad9cd1b48292948cd82", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:PXD013220 licence not read", "asset:data:geo:PXD013220 not downloaded", "execution.not_run", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["A list of statistically-significant proteins was generated through a student's t-test."], "order_basis": "analysis_only", "id": "assay:1"}]}