DiSCount: computer vision for automated quantification of Striga seed germination.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32377220", "kind": "science-record", "revision": 3, "content_hash": "sha256:fa412c30a13274b4c235d78c74fa1e2e67c335747bb19433a90421dedf3be7c8", "created_at": "2026-11-01T15:41:00Z", "updated_at": "2026-11-01T18:52:24Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "DiSCount: computer vision for automated quantification of Striga seed germination.", "doi": "10.1186/s13007-020-00602-8", "pmid": "32377220", "authors": ["Raul Masteling", "Lodewijk Voorhoeve", "Joris IJsselmuiden", "Francisco Dini-Andreote", "Wietse de Boer", "Jos M Raaijmakers"], "journal": "Plant methods", "year": 2020, "abstract": "BACKGROUND: Plant parasitic weeds belonging to the genus Striga are a major threat for food production in Sub-Saharan Africa and Southeast Asia. The parasite's life cycle starts with the induction of seed germination by host plant-derived signals, followed by parasite attachment, infection, outgrowth, flowering, reproduction, seed set and dispersal. Given the small seed size of the parasite (< 200 μm), quantification of the impact of new control measures that interfere with seed germination relies on manual, labour-intensive counting of seed batches under the microscope. Hence, there is a need for high-throughput assays that allow for large-scale screening of compounds or microorganisms that adversely affect Striga seed germination.\nRESULTS: Here, we introduce DiSCount (Digital Striga Counter): a computer vision tool for automated quantification of total and germinated Striga seed numbers in standard glass fibre filter assays. We developed the software using a machine learning approach trained with a dataset of 98 manually annotated images. Then, we validated and tested the model against a total dataset of 188 manually counted images. The results showed that DiSCount has an average error of 3.38 percentage points per image compared to the manually counted dataset. Most importantly, DiSCount achieves a 100 to 3000-fold speed increase in image analysis when compared to manual analysis, with an inference time of approximately 3 s per image on a single CPU and 0.1 s on a GPU.\nCONCLUSIONS: DiSCount is accurate and efficient in quantifying total and germinated Striga seeds in a standardized germination assay. This automated computer vision tool enables for high-throughput, large-scale screening of chemical compound libraries and biological control agents of this devastating parasitic weed. The complete software and manual are hosted at https://gitlab.com/lodewijk-track32/discount_paper and the archived version is available at Zenodo with the DOI 10.5281/zenodo.3627138. The dataset used for testing is available at Zenodo with the DOI 10.5281/zenodo.3403956.", "claims": [{"id": "claim-data-access", "statement": "The software and user manual are freely available at https://gitlab.com/lodewijk-track32/discount_paper. The archived version of the repository is available at 10.5281/zenodo.3627138. The dataset analysed to assess the performance of the software is publically available at 10.5281/zenodo.3403956. The input dataset used to test the installation of the software is publically available at 10.5281/zenodo.3404131.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32377220", "locator": "sections[13] \"Availability of data and materials\" paragraph 2", "quote": "The software and user manual are freely available at https://gitlab.com/lodewijk-track32/discount_paper. The archived version of the repository is available at 10.5281/zenodo.3627138. The dataset analysed to assess the performance of the software is publically available at 10.5281/zenodo.3403956. The input dataset used to test the installation of the software is publically available at 10.5281/zenodo.3404131."}], "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:32377220"], "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:32377220", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s13007-020-00602-8", "sha256": "sha256:398cd6071c37689921c4491b05a4889fb43fef1cec902800e207d7b05d21d045", "bytes": 34736, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s13007-020-00602-8", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7195706", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:32377220:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:151764b3cc89662114d51fefd339fd7aa6d33ed2605248b5e5886292b3f9a768", "bytes": 422, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#Tab1", "version": null, "note": "Test results of the model versus the hand-count", "structure": {"pmcid": "PMC7195706", "section_index": 8, "section_title": "Results and discussion", "row_count": 4, "column_count": 5}, "table": {"label": "Table 1", "caption": "Test results of the model versus the hand-count", "rows": [["", "Seeds", "Radicles", "Average germination (%)", "Average difference per image (percentage points)"], ["Hand-count", "4848", "910", "21.42", "3.38"], ["DiSCount", "4486", "851", "20.03", ""], ["Underestimation (%)", "7.467", "6.484", "", ""]], "row_count": 4, "column_count": 5, "numeric_cells": 9, "header_rows": 1, "locator": "section[8]/table-wrap[1]#Tab1"}}], "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": ["The software and user manual are freely available at https://gitlab.com/lodewijk-track32/discount_paper. The archived version of the repository is available at 10.5281/zenodo.3627138. The dataset analysed to assess the performance of the software is publically available at 10.5281/zenodo.3403956. The input dataset used to test the installation of the software is publically available at 10.5281/zenodo.3404131."], "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:32377220", "asset:table:pmid:32377220:1"], "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": "2026-10-31T18:19:47Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 26984, "completion_tokens": 1513, "cached_tokens": 9224}}, "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:32377220", "type": "paper", "label": "pmid:32377220"}, {"id": "source:pmid:32377220", "type": "manuscript", "label": "PMID 32377220 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32377220", "type": "paper", "label": "pmid:32377220"}, {"id": "source:pmid:32377220", "type": "manuscript", "label": "PMID 32377220 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32377220", "type": "extraction", "used": ["source:pmid:32377220"], "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:32377220", "parent_hash": "sha256:e1f2b5f3b49f636b5df7ff84a7209837266a8a7e3ebc85485122cfd9e5b1381e", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}