GrainShape: A landmark-annotated image dataset of japonica rice grains for geometric morphometric analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40612480", "kind": "science-record", "revision": 2, "content_hash": "sha256:e8a247a2c2a559414604f8e6b09624899967a06c5a07e6de3b7064a1e9ca1fd8", "created_at": "2026-11-01T20:30:42Z", "updated_at": "2026-11-01T21:35:23Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "GrainShape: A landmark-annotated image dataset of japonica rice grains for geometric morphometric analysis.", "doi": "10.1016/j.dib.2025.111781", "pmid": "40612480", "authors": ["Jiexiong Xu"], "journal": "Data in brief", "year": 2025, "abstract": "This open-access dataset comprises matched image and landmark files for 231 rice grains representing distinct Oryza sativa japonica landraces cultivated in China's Lake Taihu region. Grains were grown in a single 2022 field season under uniform management. One mature, fully-filled kernel per accession was photographed dorsoventral side up with an Olympus TG-6 macro camera (4000 × 3000 px, 314 dpi, f/2.3, 1/13 s, +1 EV) under fixed laboratory lighting. Each frame includes a matte-green background, a 30 mm plastic ruler, and two printed fiducials, enabling pixel-to-millimeter scaling and consistent orientation. The repository is organized into four zip archives. grainimages.zip holds the 231 color JPEG photographs. landmarks.zip provides 231 plain-text tables listing the x,y coordinates of 30 homologous radial landmarks that capture length, width, curvature, tip geometry, shoulder position, awn insertion point, and subtle asymmetries. contours.zip contains 231 standalone PNG drawings showing a spline-interpolated outline reconstructed solely from each landmark set-no photographic background is included-facilitating rapid visual checks of digitization accuracy. scripts.zip contains all custom Python scripts for generating the landmark sets and reproducing the figures and tables presented in the paper. The dataset, available on Zenodo (DOI:10.5281/zenodo.15515366) under a CC BY 4.0 license, can be reused for landmark- or outline-based morphometric analysis, color and awn-length phenotyping, benchmarking of computer-vision pipelines, and instructional demonstrations of geometric morphometric workflows.", "claims": [{"id": "claim-method", "statement": "To evaluate how well the 30 landmark points capture grain shape variation, a principal component analysis (PCA) was conducted on the landmark coordinate matrices.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40612480", "locator": "sections[10] \"Data quality analysis\" paragraph 2", "quote": "To evaluate how well the 30 landmark points capture grain shape variation, a principal component analysis (PCA) was conducted on the landmark coordinate matrices."}], "state": "complete"}, {"id": "claim-data-access", "statement": "ZENODOGrainShape: a landmark-annotated image dataset of japonica rice grains for geometric morphometric analysis (Original data)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40612480", "locator": "sections[19] \"Data Availability\" paragraph 2", "quote": "ZENODOGrainShape: a landmark-annotated image dataset of japonica rice grains for geometric morphometric analysis (Original data)"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "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:40612480"], "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:40612480", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2025.111781", "sha256": "sha256:39772511f00cc08991e7079165d1124643bb290d0bafcd86e16d6df22795a6b6", "bytes": 28995, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2025.111781", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12221751", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "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": 1.0, "band": "verbatim", "quote": "To evaluate how well the 30 landmark points capture grain shape variation, a principal component analysis (PCA) was conducted on the landmark coordinate matrices."}}], "targets": [], "gaps": []}, "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": [], "resolved_accessions": [], "statements": ["ZENODOGrainShape: a landmark-annotated image dataset of japonica rice grains for geometric morphometric analysis (Original data)"], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:40612480"], "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": "2026-11-01T19:56:02Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8456, "completion_tokens": 1104, "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:40612480", "type": "paper", "label": "pmid:40612480"}, {"id": "source:pmid:40612480", "type": "manuscript", "label": "PMID 40612480 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40612480", "type": "paper", "label": "pmid:40612480"}, {"id": "source:pmid:40612480", "type": "manuscript", "label": "PMID 40612480 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40612480", "type": "extraction", "used": ["source:pmid:40612480"], "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:40612480", "parent_hash": "sha256:2472a1ae7ca57e63c0324559e039e4582b69214dce9ad917667ab12c24358b61", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "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": 1.0, "evidence": ["To evaluate how well the 30 landmark points capture grain shape variation, a principal component analysis (PCA) was conducted on the landmark coordinate matrices."], "order_basis": "analysis_only", "id": "assay:1"}]}