{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:25104955", "kind": "science-record", "revision": 7, "content_hash": "sha256:b08164a58f0157324b3d871ffb90c3d710c290ac1512c1dbcb048161c355551e", "created_at": "2026-11-01T15:40:05Z", "updated_at": "2026-11-01T21:58:20Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Unravelling the proteomic profile of rice meiocytes during early meiosis.", "doi": "10.3389/fpls.2014.00356", "pmid": "25104955", "authors": ["Melania Collado-Romero", "Enriqueta Alós", "Pilar Prieto"], "journal": "Frontiers in plant science", "year": 2014, "abstract": "Transfer of genetic traits from wild or related species into cultivated rice is nowadays an important aim in rice breeding. Breeders use genetic crosses to introduce desirable genes from exotic germplasms into cultivated rice varieties. However, in many hybrids there is only a low level of pairing (if existing) and recombination at early meiosis between cultivated rice and wild relative chromosomes. With the objective of getting deeper into the knowledge of the proteins involved in early meiosis, when chromosomes associate correctly in pairs and recombine, the proteome of isolated rice meiocytes has been characterized by nLC-MS/MS at every stage of early meiosis (prophase I). Up to 1316 different proteins have been identified in rice isolated meiocytes in early meiosis, being 422 exclusively identified in early prophase I (leptotene, zygotene, or pachytene). The classification of proteins in functional groups showed that 167 were related to chromatin structure and remodeling, nucleic acid binding, cell-cycle regulation, and cytoskeleton. Moreover, the putative roles of 16 proteins which have not been previously associated to meiosis or were not identified in rice before, are also discussed namely: seven proteins involved in chromosome structure and remodeling, five regulatory proteins [such as SKP1 (OSK), a putative CDK2 like effector], a protein with RNA recognition motifs, a neddylation-related protein, and two microtubule-related proteins. Revealing the proteins involved in early meiotic processes could provide a valuable tool kit to manipulate chromosome associations during meiosis in rice breeding programs. The data have been deposited to the ProteomeXchange with the PXD001058 identifier.", "claims": [{"id": "claim-method", "statement": "Search against decoy database (integrated decoy approach) was performed using false discovery rate (FDR) < 0.01.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25104955", "locator": "sections[7] \"Reverse phase-liquid chromatography RP-LC-MS/MS analysis\" paragraph 4", "quote": "Search against decoy database (integrated decoy approach) was performed using false discovery rate (FDR) < 0.01."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data have been deposited to the ProteomeXchange with the PXD001058 identifier.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25104955", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The data have been deposited to the ProteomeXchange with the PXD001058 identifier."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:25104955"], "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:PXD001058"], "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:PXD001058"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:25104955", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fpls.2014.00356", "sha256": "sha256:774a0aa6d389c2e8f3970f9755d9457a2bee2d9cdc1e4c5ae83402886463d053", "bytes": 66858, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fpls.2014.00356", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4109522", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD001058", "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=PXD001058", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD001058", "version": null, "note": "The data have been deposited to the ProteomeXchange with the PXD001058 identifier.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data have been deposited to the ProteomeXchange with the PXD001058 identifier.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Unravelling the proteomic profile of rice meiocytes during early meiosis", "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:25104955:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:153316a3878add642567bf3726737a79e66a5b4842ecfd2d56bc1554223c0b6c", "bytes": 20342, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T1", "version": null, "note": "Proteins identified in rice isolated meiocytes at early prophase I associated to putative functions involved in chromosome recognition.", "structure": {"pmcid": "PMC4109522", "section_index": 12, "section_title": "Functional classification of proteins identified in rice meiocytes only at early prophase I of meiosis (leptotene, zygotene, and pachytene)", "row_count": 197, "column_count": 6}, "table": {"label": "Table 1", "caption": "Proteins identified in rice isolated meiocytes at early prophase I associated to putative functions involved in chromosome recognition.", "rows": [["Biological function", "Molecular function", "LEP", "ZYG", "PAC", "MSU annotation"], ["PROTEINS INVOLVED IN CHROMATIN STRUCTURE AND REMODELING"], ["Nucleosome components and chromatin structure"], ["Chromatin binding"], ["(SMC2) chromosome segregation protein, putative, expressed", "Protein-binding", "", "", "2", "LOC_Os01g67740.1"], ["Histone deacetylase, putative, expressed", "Catalytic activity", "", "", "2", "LOC_Os07g41090.1"], ["Histone deacetylase, putative, expressed", "Catalytic activity", "", "", "2", "LOC_Os08g25570.1"], ["* Chromatin-remodeling complex ATPase chain, putative, expressed (ATP-dependent chromatin-remodeling protein", "Catalytic activity", "", "6", "", "LOC_Os01g27040.1"], ["* SWIB/MDM2 domain containing protein, expressed (ATP-dependent chromatin-remodeling protein)", "Catalytic activity", "4", "2", "", "LOC_Os02g03730.1"], ["* SWIB/MDM2 domain containing protein, expressed (ATP-dependent chromatin-remodeling protein)", "Catalytic activity", "3", "", "", "LOC_Os03g55310.1"], ["* PWWP domain containing protein, expressed", "Protein-binding", "", "3", "", "LOC_Os05g38810.1"], ["Nucleosome assembly related proteins"], ["Core Histone H2A/H2B/H3/H4 domain containing protein, putative, expressed (H2A variant 3; H2A.3)", "DNA-binding", "3", "", "", "LOC_Os03g53190.1"], ["Histone H1, putative, expressed", "DNA-binding", "3", "", "2", "LOC_Os04g18090.1"], ["Histone H3, putative, expressed (CenH3)", "DNA-binding", "", "2", "", "LOC_Os05g41080.2"], ["* SET, putative, expressed (Nucleosome assembly protein, Nap1-related protein)", "DNA-binding", "2", "2", "2", "LOC_Os02g36710.1"], ["NAP domain containing protein, putative, expressed (Nucleosome assembly protein)", "DNA-binding", "", "", "2", "LOC_Os04g38620.1"], ["Centromeres associated"], ["Tetratricopeptide repeat containing protein, putative, expressed (NASP-related)", "Prot-binding", "", "2", "2", "LOC_Os07g03070.1"], ["CS domain containing protein, putative, expressed (nudC)", "Prot-binding", "3", "3", "5", "LOC_Os06g12530.1"], ["Proteins involved in replication/DNA repair and recombination"], ["DNA polymerase V, putative, expressed", "DNA-binding", "", "2", "", "LOC_Os02g04270.1"], ["Proliferating cell nuclear antigen (PCNA)—Putative DNA replicative polymerase clamp, expressed", "DNA-binding", "3", "", "4", "LOC_Os02g56130.1"], ["MCM5—Putative minichromosome maintenance MCM complex subunit 5, expressed", "DNA-binding", "2", "2", "", "LOC_Os02g55410.2"], ["RAD23 DNA repair protein, putative, expressed", "DNA-binding", "", "2", "", "LOC_Os02g08300.2"], ["RAD23 DNA repair protein, putative, expressed", "DNA-binding", "", "2", "2", "LOC_Os08g33340.2"], ["Hydrolase, NUDIX family, domain containing protein, expressed", "Catalytic activity", "", "2", "2", "LOC_Os04g58900.1"], ["3-5 exonuclease domain-containing protein, putative, expressed", "Catalytic activity", "2", "", "2", "LOC_Os01g47180.1"], ["XPA-binding protein 2, putative, expressed", "Protein-binding", "", "", "3", "LOC_Os07g44970.1"], ["Phosphoesterase, putative, expressed", "DNA-binding", "", "", "2", "LOC_Os01g53560.1"], ["PPR repeat domain containing protein, putative, expressed", "RNA-binding", "", "", "2", "LOC_Os01g67210.1"], ["ruvB-like 2, putative, expressed (Reptin or TIP49b)", "DNA-binding", "4", "", "3", "LOC_Os06g08770.1"], ["WD domain, G-beta repeat domain containing protein, expressed (REC14)", "Protein-binding", "", "", "3", "LOC_Os11g43890.1"], ["Basic helix-loop-helix, putative, expressed (APRATAXIN-like protein)", "DNA-binding", "", "", "2", "LOC_Os03g18210.1"], ["Other DNA binding proteins"], ["DNA binding motifs"], ["* AT hook motif family protein, expressed (BRI1-KD interacting protein 135)", "DNA-binding", "", "3", "", "LOC_Os02g39920.1"], ["* AT hook motif family protein, expressed (BRI1-KD interacting protein 135)", "DNA-binding", "", "", "2", "LOC_Os04g42320.1"], ["AT hook motif domain containing protein, expressed", "DNA-binding", "", "2", "", "LOC_Os08g40150.1"], ["DNA-binding protein-related, putative, expressed (OB-fold nucleic acid binding domain containing protein)", "DNA-binding", "2", "2", "2", "LOC_Os01g13700.1"], ["DNA-binding protein-related, putative, expressed (OB-fold nucleic acid binding domain containing protein)", "DNA-binding", "", "3", "3", "LOC_Os06g01370.1"], ["Transposon protein, putative, unclassified, expressed", "DNA-binding", "2", "", "2", "LOC_Os03g52310.1"], ["RNA Polymerases"], ["RNA polymerase Rpb1, domain 2 family protein, expressed", "DNA-binding", "", "", "2", "LOC_Os02g05880.1"], ["DNA-directed RNA polymerase subunit, putative, expressed", "DNA-binding", "", "", "3", "LOC_Os09g02284.1"], ["Transcription regulation factors"], ["Transcription initiation factor IIF, alpha subunit domain containing protein, expressed", "DNA-binding", "", "", "2", "LOC_Os10g10990.3"], ["CCR4-NOT transcription factor, putative, expressed (NOT2/NOT3/NOT5 family protein)", "Nucleic acid binding", "", "2", "2", "LOC_Os03g52594.5"], ["PUR ALPHA-1, putative, expressed (PurA sequence specific DNA and RNA-binding protein)", "Nucleic acid binding", "", "2", "2", "LOC_Os01g15600.1"], ["ZF-HD protein dimerization region containing protein, expressed", "DNA-binding", "2", "", "", "LOC_Os12g10630.1"], ["ZOS8-11—C2H2 zinc finger protein, expressed", "DNA-binding", "", "2", "", "LOC_Os08g40560.2"], ["Zinc finger helicase family protein, putative, expressed", "Nucleic acid binding", "", "", "3", "LOC_Os01g15300.2"], ["ZOS3-17—C2H2 zinc finger protein, expressed", "DNA-binding", "", "3", "2", "LOC_Os03g50850.2"], ["SH2 motif, putative, expressed", "RNA-binding", "2", "2", "", "LOC_Os05g41510.1"], ["PROTEINS WITH KNOWN OR PUTATIVE FUNCTION IN REGULATION"], ["Cell-cycle regulation"], ["* Skp1 family, tetramerization domain containing protein, expressed (OSK27)", "Ubiquitin-related protein", "3", "2", "4", "LOC_Os07g43230.1"], ["* CDK5RAP3, putative, expressed (CDK5 activator-binding proteins)", "Protein binding", "", "", "3", "LOC_Os06g21560.1"], ["* E3 UFM1-protein ligase 1 (UFL1)", "Ubiquitin-related protein", "", "", "2", "LOC_Os05g02650.1"], ["* SIT4 phosphatase-associated protein family protein, expressed", "Catlytic activity", "2", "", "", "LOC_Os01g40340.3"], ["Pachytene checkpoint protein 2 (AAA-type ATPase family protein, putative, expressed)", "Catlytic activity", "", "2", "", "LOC_Os04g40290.1"], ["Mitotic checkpoint protein, putative, expressed (putative Rae1)", "RNA binding", "", "", "2", "LOC_Os01g44394.1"], ["Split hand/foot malformation type 1, putative, expressed (Similar to DSS1)", "Ubiquitin-related protein", "", "2", "", "LOC_Os01g16640.1"], ["Protein kinase family protein, putative, expressed (SCY1-related protein kinase like)", "RNA binding", "", "", "2", "LOC_Os01g42950.1"], ["CWC15 homolog A, putative, expressed (Cwf15/Cwc15 cell cycle control protein family protein)", "RNA processing", "4", "2", "2", "LOC_Os06g01700.1"], ["Zinc finger C-x8-C-x5-C-x3-H type family protein, expressed", "DNA-binding", "", "", "2", "LOC_Os04g57010.1"], ["* HECT-domain domain containing protein, expressed", "Ubiquitin-related protein", "", "2", "", "LOC_Os02g01170.1"], ["Ubiquitin family domain containing protein, expressed", "Ubiquitin-related protein", "3", "2", "", "LOC_Os01g68950.1"], ["Similar to FU (FUSED); MAPK KINASE 2-RELATED", "Catlytic activity", "", "2", "", "LOC_Os12g24550.1"], ["Prohibitin, putative, expressed", "Protein binding", "2", "5", "", "LOC_Os04g38900.2"], ["Transposon protein, putative, CACTA, En/Spm sub-class, expressed", "Protein binding", "", "", "2", "LOC_Os05g46780.1"], ["Development and flowering control"], ["Cell development regulation"], ["GTP-binding protein, putative, expressed", "RNA-binding", "2", "2", "5", "LOC_Os07g43470.1"], ["GLTP domain containing protein, putative, expressed", "Catalytic activity", "2", "", "", "LOC_Os03g57140.1"], ["Similar to H0525E10.11 protein. (Exocyst complex component SEC5)", "Ubiquitin-related protein", "", "", "2", "LOC_Os04g34450.1"], ["Beta-catenin-like protein 1, putative, expressed", "Nucleic acid-Protein bond", "", "", "2", "LOC_Os02g58460.1"], ["DNA-binding TFAR19-related protein family protein", "DNA-binding", "4", "3", "3", "LOC_Os05g47446.2"], ["Flower development/Flowering time"], ["OsSPL13—SBP-box gene family member, expressed", "DNA-binding", "3", "", "2", "LOC_Os07g32170.1"], ["Flowering time control protein FCA, putative, expressed", "RNA-binding", "2", "", "", "LOC_Os09g03610.3"], ["Glutamate–cysteine ligase, chloroplast precursor, putative, expressed", "Catlytic activity", "2", "", "", "LOC_Os05g03820.3"], ["Male sterility protein 2 (MS2), putative, expressed", "Catlytic activity", "", "2", "", "LOC_Os08g44360.1"], ["NLI interacting factor-like phosphatase, putative, expressed", "Catlytic activity", "", "", "2", "LOC_Os05g43770.1"], ["Polygalacturonase inhibitor 1 precursor, putative, expressed", "Signal transduction", "3", "2", "2", "LOC_Os07g38130.1"], ["Polygalacturonase inhibitor 1 precursor, putative, expressed", "Signal transduction", "", "", "2", "LOC_Os09g31450.1"], ["HEN1, putative, expressed (Methyltransferase type 12 domain containing protein)", "RNA-binding", "", "", "2", "LOC_Os07g06970.1"], ["KH domain containing protein, putative, expressed (FLK, flowering locus KH domain)", "RNA-binding", "", "", "2", "LOC_Os03g42900.2"], ["Plant development"], ["WD domain, G-beta repeat domain containing protein, expressed (Transducin/WD40 repeat-like superfamily protein)", "Signal transduction", "", "", "2", "LOC_Os09g24260.1"], ["RNA processing/ Splicing factors/ RNA stabilization/ RNA recognition"], ["Splicing and/or RNA processing factors"], ["Splicing factor 3 subunit 1, putative, expressed", "RNA-binding", "", "", "2", "LOC_Os02g14780.2"], ["Splicing factor, arginine/serine-rich, putative, expressed", "Nucleic acid-binding", "2", "", "", "LOC_Os01g06290.4"], ["Splicing factor, arginine/serine-rich 7, putative, expressed", "Nucleic acid-binding", "", "", "2", "LOC_Os05g07000.1"], ["RNA recognition motif containing protein, expressed", "RNA-binding", "2", "", "3", "LOC_Os06g08840.8"], ["DEAD-box ATP-dependent RNA helicase, putative, expressed", "RNA-binding", "2", "2", "", "LOC_Os03g06220.1"], ["Intron-binding protein aquarius, putative, expressed (DNA2/NAM7 helicase family)", "RNA-binding", "2", "", "4", "LOC_Os03g26960.1"], ["RNA recognition motif containing protein, expressed (Arginine/serine-rich splicing factor RSP41)", "RNA-binding", "", "2", "", "LOC_Os02g03040.4"], ["RNA-binding motif protein, putative, expressed (Pre-mRNA-splicing factor SLT11)", "RNA-binding", "", "", "2", "LOC_Os06g07350.1"], ["WD domain, G-beta repeat domain containing protein, expressed (Pre-mRNA-splicing factor 19)", "Protein binding", "", "3", "", "LOC_Os10g32880.1"], ["Ribonuclease T2 family domain containing protein, expressed", "RNA-binding", "2", "", "", "LOC_Os09g36700.1"], ["LSM domain containing protein, expressed (Small nuclear ribonucleoprotein Sm D3)", "RNA-binding", "2", "", "", "LOC_Os02g01250.1"], ["Protein binding protein, putative, expressed (Pre-mRNA-processing protein 40A)", "RNA-binding", "", "2", "", "LOC_Os01g34780.1"], ["Proline-rich spliceosome-associated (PSP) domain containing protein, expressed", "RNA-binding", "", "", "3", "LOC_Os02g58090.1"], ["U5 small nuclear ribonucleoprotein 200 kDa helicase, putative, expressed", "Nucleic acid-binding", "", "2", "", "LOC_Os02g01740.1"], ["Cleavage and polyadenylation specificity factor subunit 5, putative, expressed", "RNA-binding", "", "2", "", "LOC_Os04g58640.1"], ["Transposon protein, putative, unclassified, expressed", "Nucleic acid-binding", "2", "3", "", "LOC_Os05g50624.2"], ["RNA recognition motifs"], ["* Transcription factor X1, putative, expressed (OXHS4)", "RNA-binding", "", "", "2", "LOC_Os02g19130.1"], ["RNA recognition motif containing protein, expressed (Glycine-rich RNA-binding protein 7)", "RNA-binding", "", "", "2", "LOC_Os07g08960.1"], ["RNA recognition motif containing protein, putative, expressed", "RNA-binding", "2", "3", "2", "LOC_Os05g13620.1"], ["RNA recognition motif containing protein, putative, expressed", "RNA-binding", "3", "2", "4", "LOC_Os07g33330.1"], ["RNA recognition motif containing protein, putative, expressed", "RNA-binding", "", "", "2", "LOC_Os06g02240.1"], ["Expressed protein", "RNA-binding", "2", "", "", "LOC_Os10g34370.1"], ["PPR repeat domain containing protein, putative, expressed", "RNA-binding", "", "3", "2", "LOC_Os07g40800.1"], ["Retrotransposon protein, putative, unclassified, expressed (DEAD-box ATP-dependent RNA helicase, putative)", "RNA-binding", "", "2", "2", "LOC_Os11g46240.1"], ["Glycine-rich RNA-binding protein 7, putative, expressed", "RNA-binding", "3", "2", "3", "LOC_Os03g61990.2"], ["Nucleus cytoplasm transport"], ["Nucleus-cytoplasm transport"], ["Nucleoporin interacting component, putative, expressed", "Protein binding", "", "3", "2", "LOC_Os03g22690.1"], ["OsNucAP3—Putative Nucleoporin Autopeptidase homolog, expressed", "Protein binding", "", "", "2", "LOC_Os12g06890.1"], ["Zinc finger family protein, putative, expressed (Similar to Testis expressed sequence 13A protein)", "Binding", "", "", "2", "LOC_Os02g10920.4"], ["Importin subunit beta, putative, expressed", "Binding", "2", "3", "2", "LOC_Os12g38110.1"], ["SRP40, C-terminal domain containing protein, expressed", "Protein binding", "", "", "3", "LOC_Os12g41930.1"], ["RNA nuclear transport factors"], ["Nuclear-pore anchor, putative, expressed", "RNA-binding", "2", "", "2", "LOC_Os02g50790.2"], ["Nuclear-pore anchor, putative, expressed", "RNA-binding", "2", "2", "2", "LOC_Os02g50799.1"], ["RNA-binding protein-like, putative, expressed (Nuclear transport factor 2)", "RNA-binding", "2", "", "2", "LOC_Os02g29480.1"], ["Nuclear transport factor 2, putative, expressed", "RNA-binding", "2", "3", "4", "LOC_Os04g30430.1"], ["Nucleoporin, putative, expressed", "RNA-binding", "", "2", "2", "LOC_Os03g12450.1"], ["Nonsense-mediated mRNA decay protein 3, putative, expressed (NMD3 family protein, expressed)", "RNA-binding", "2", "5", "3", "LOC_Os10g42320.1"], ["Other protein with putative regulatory functions"], ["Ubiquitination and related post-traslational modifications"], ["E3 ubiquitin ligase, putative, expressed", "Ubiquitin-related protein", "2", "", "2", "LOC_Os01g49470.2"], ["Ubiquitin family domain containing protein, expressed", "Ubiquitin-related protein", "", "2", "2", "LOC_Os02g10510.1"], ["Ubiquitin family domain containing protein, expressed", "Ubiquitin-related protein", "2", "2", "", "LOC_Os03g03920.4"], ["Ubiquitin-activating enzyme, putative, expressed", "Ubiquitin-related protein", "", "3", "3", "LOC_Os03g18380.1"], ["Ubiquitin-conjugating enzyme, putative, expressed", "Ubiquitin-related protein", "", "2", "2", "LOC_Os12g41220.1"], ["Ubiquitin carboxyl-terminal hydrolase, putative, expressed", "Ubiquitin-related protein", "", "", "2", "LOC_Os08g41550.1"], ["UBX domain-containing protein, putative, expressed", "Ubiquitin-related protein", "", "", "2", "LOC_Os04g57520.1"], ["UBX domain-containing protein, putative, expressed", "Ubiquitin-related protein", "4", "2", "3", "LOC_Os08g43300.1"], ["* Defective in cullin neddylation (DCN) DCN1-like protein 2, putative, expressed", "Ubiquitin-related protein", "", "3", "2", "LOC_Os06g12690.3"], ["Chaperones and chaperone-like functions"], ["ATP-dependent Clp protease ATP-binding subunit clpA homolog CD4B,chloroplast precursor, putative, expressed", "Catalytic activity", "2", "", "2", "LOC_Os04g32560.2"], ["ATP-dependent Clp protease ATP-binding subunit clpA homolog CD4B,chloroplast precursor, putative, expressed", "Catalytic activity", "2", "", "", "LOC_Os11g16590.1"], ["Chaperone protein clpB 1, putative, expressed", "Catalytic activity", "2", "2", "", "LOC_Os02g08490.1"], ["Chaperonin, putative, expressed", "Catalytic activity", "2", "3", "", "LOC_Os03g25050.1"], ["Chaperonin, putative, expressed", "Catalytic activity", "3", "3", "", "LOC_Os07g44740.1"], ["Chaperonin, putative, expressed", "Catalytic activity", "", "2", "", "LOC_Os09g26730.1"], ["DnaK family protein, putative, expressed", "Catalytic activity", "3", "", "", "LOC_Os03g50250.1"], ["Dehydrogenase, putative, expressed", "Catalytic activity", "", "3", "", "LOC_Os01g54940.1"], ["hsp20/alpha crystallin family protein, putative, expressed", "Catalytic activity", "", "", "2", "LOC_Os01g08860.1"], ["Prefoldin, putative, expressed", "Catalytic activity", "", "", "2", "LOC_Os12g37590.1"], ["SCO1 protein homolog, mitochondrial precursor, putative, expressed", "Catalytic activity", "", "2", "", "LOC_Os09g20430.1"], ["Peptidyl-prolyl cis-trans isomerase, putative, expressed", "Catalytic activity", "", "", "2", "LOC_Os01g18210.1"], ["Peptidyl-prolyl cis-trans isomerase, putative, expressed", "Catalytic activity", "", "2", "2", "LOC_Os09g39780.2"], ["Proteins involved in signal-transduction/regulatory proteins"], ["GTPase-activating protein, putative, expressed (Similar to ARF GAP-like zinc finger-containing protein ZIGA2)", "Catalytic activity", "", "", "2", "LOC_Os03g63710.2"], ["Zinc finger family protein, putative, expressed", "Protein binding", "2", "", "2", "LOC_Os08g36774.1"], ["GCK domain containing protein", "Signal transduction", "", "", "3", "LOC_Os03g44520.1"], ["Ras-related protein, putative, expressed", "Signal transduction", "3", "", "", "LOC_Os07g09680.1"], ["Ras-related protein, putative, expressed", "Signal transduction", "2", "2", "", "LOC_Os10g23100.1"], ["PB1 domain containing protein, expressed", "Signal transduction", "", "2", "2", "LOC_Os01g04650.1"], ["Salt stress root protein RS1, putative, expressed", "Protein binding", "2", "", "2", "LOC_Os01g13210.1"], ["WD domain, G-beta repeat domain containing protein, expressed", "Catalytic activity", "2", "", "2", "LOC_Os03g48090.1"], ["PTEN, putative, expressed", "Catalytic activity", "", "", "3", "LOC_Os12g21890.1"], ["NB-ARC/LRR disease resistance protein, putative, expressed", "Protein binding", "2", "", "", "LOC_Os03g14900.1"], ["Zinc finger C-x8-C-x5-C-x3-H type family protein, expressed (BRI1-kinase domain-interacting protein 105)", "Protein binding", "2", "2", "", "LOC_Os02g06584.2"], ["CBS domain containing membrane protein, putative, expressed (Similar to AKIN gamma)", "Catalytic activity", "", "", "2", "LOC_Os01g40420.1"], ["Copine, putative, expressed", "Signal transduction", "", "", "2", "LOC_Os05g30970.1"], ["phospholipase D, putative, expressed", "Catalytic activity", "2", "", "3", "LOC_Os01g07760.1"], ["Serine/threonine protein phosphatase 5, putative, expressed", "Catalytic activity", "", "", "2", "LOC_Os05g11550.2"], ["Inactive receptor kinase At2g26730 precursor, putative, expressed", "Catalytic activity", "", "2", "3", "LOC_Os01g42294.1"], ["Protein of unknown function DUF1296 domain containing protein, expressed", "Nucleic acid-binding", "", "", "2", "LOC_Os06g10430.3"], ["Universal stress protein domain containing protein, putative, expressed", "Catalytic activity", "", "", "2", "LOC_Os01g57450.1"], ["Universal stress protein domain containing protein, putative, expressed", "Catalytic activity", "2", "", "4", "LOC_Os05g42230.1"], ["Zinc finger C-x8-C-x5-C-x3-H type family protein, expressed", "Protein binding", "", "", "3", "LOC_Os01g61830.1"], ["CYTOSKELETON RELATED PROTEINS"], ["Actin related proteins"], ["Actin, putative, expressed", "Structural molecule activity", "2", "2", "5", "LOC_Os08g04280.2"], ["Actin-depolymerizing factor, putative, expressed", "Catalytic activity", "", "2", "2", "LOC_Os03g56790.1"], ["ACBP4 (acyl-CoA binding protein 4), putative, expressed", "Protein binding", "3", "2", "3", "LOC_Os03g61930.2"], ["Kelch repeat protein, putative, expressed", "Protein binding", "", "", "2", "LOC_Os02g57690.1"], ["Fimbrin-like protein 2, putative, expressed", "Protein binding", "", "2", "", "LOC_Os01g33080.1"], ["Fimbrin-like protein 2, putative, expressed", "Protein binding", "", "2", "", "LOC_Os02g48740.1"], ["Villin protein, putative, expressed", "Protein binding", "2", "", "", "LOC_Os03g24220.1"], ["Canopy homolog 2 precursor, putative, expressed", "Binding", "", "", "2", "LOC_Os02g02524.1"], ["WD domain, G-beta repeat domain containing protein, expressed", "Catalytic activity", "", "", "2", "LOC_Os02g57220.1"], ["Expressed protein", "Structural molecule activity", "", "", "2", "LOC_Os04g54410.1"], ["SH3 domain containing protein, expressed", "Signal transduction", "", "2", "", "LOC_Os03g15900.2"], ["Microtubules related proteins"], ["* Microtubule associated protein, putative, expressed (MAP65-1a)", "Protein binding", "6", "3", "4", "LOC_Os06g20370.1"], ["* Targeting protein for Xklp2 (TPX2), putative, expressed", "Protein binding", "", "", "2", "LOC_Os06g40450.3"], ["T-complex protein, putative, expressed (TCP-1)", "Catalytic activity", "2", "3", "3", "LOC_Os02g22780.2"], ["Lissencephaly type-1-like homology motif, putative, expressed (OsLIS-L1)", "Protein binding", "2", "", "3", "LOC_Os08g06480.1"], ["Expressed protein", "Catalytic activity", "2", "", "", "LOC_Os01g42770.1"]], "row_count": 197, "column_count": 6, "numeric_cells": 482, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T1"}}], "gaps": ["asset:data:geo:PXD001058 not downloaded", "asset:data:geo:PXD001058 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "sequence_alignment", "specific": "blast", "label": "Sequence alignment / homology", "dsl_operations": ["sequence_align", "alignment_identity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["sequence_records"], "evidence": {"score": 0.8, "band": "high", "quote": "blast"}}, {"id": "method-2", "family": null, "specific": null, "label": "False discovery rate (FDR) control using an integrated decoy database, with FDR < 0.01", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Search against decoy database (integrated decoy approach) was performed using false discovery rate (FDR) < 0.01."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["sequence_align", "alignment_identity"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: blast."}, "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": ["PXD001058"], "resolved_accessions": ["PXD001058"], "statements": ["The data have been deposited to the ProteomeXchange with the PXD001058 identifier."], "basis": "The paper names PXD001058 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["sequence_align", "alignment_identity"], "assets": ["source:pmid:25104955", "data:geo:PXD001058", "asset:table:pmid:25104955:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD001058"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:04:28Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 52846, "completion_tokens": 1591, "cached_tokens": 52843}}, "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:25104955", "type": "paper", "label": "pmid:25104955"}, {"id": "source:pmid:25104955", "type": "manuscript", "label": "PMID 25104955 full text"}, {"id": "data:geo:PXD001058", "type": "dataset", "label": "GEO PXD001058"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:25104955", "type": "paper", "label": "pmid:25104955"}, {"id": "source:pmid:25104955", "type": "manuscript", "label": "PMID 25104955 full text"}, {"id": "data:geo:PXD001058", "type": "dataset", "label": "GEO PXD001058"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-25104955", "type": "extraction", "used": ["source:pmid:25104955"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD001058", "type": "accession_resolution", "used": ["data:geo:PXD001058"], "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:25104955", "parent_hash": "sha256:18ce4bc316309a2d2a77c69353ff0b2b64cfd5868db03cc777f23f275fc5bafe", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:PXD001058 licence not read", "asset:data:geo:PXD001058 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": ["Unravelling the proteomic profile of rice meiocytes during early meios", "dditional information. The mass spectrometry proteomics results have been deposited to the ProteomeX", "in UniProtKB for additional information. The mass spectrometry proteomics results have been deposited to th"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "sequence_alignment", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["sequence_align", "alignment_identity"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["blast"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:51:17+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}