Morphological and Pathogenic Characterization of Sclerotium rolfsii, the Causal Agent of Southern Blight Disease on Common Bean in Uganda.

Over the last 5 years, Southern blight caused by Sclerotium rolfsii Sacc. has superseded root rots caused by pathogens such as Fusarium and Pythium spp. as a major constraint of common bean (Phaseolus vulgaris L.) production in Uganda. Although S. rolfsii is prevalent in all bean-growing regions of Uganda, there is a lack of information about its diversity and pathogenicity to guide the development of effective management strategies. In total, 348 S. rolfsii isolates were obtained from bean fields in seven agroecological zones of Uganda, with the following objectives: to characterize their morphology, based on mycelial growth rate, mycelium texture, and number of sclerotia; and to determine the pathogenicity of 75 selected isolates on five common bean varieties in artificially inoculated soils in a screenhouse. We found that mycelial growth rate and the number of sclerotia produced on artificial media varied among agroecological zones but not within a zone. The five bean varieties tested were found to be susceptible to S. rolfsii, including varieties MLB49-89A and RWR719 that are resistant to Fusarium and Pythium root rots, respectively. Preemergence damping-off ranged between 0 and 100%, and disease severity index ranged between 4.4 and 100%. The widespread and high levels of S. rolfsii virulence on varieties of common bean indicate that management intervention is urgently required to help reduce losses incurred by Ugandan smallholder farmers.[Formula: see text] Copyright © 2020 The Author(s). This is an open access article distributed under the CC BY 4.0 International license.

Advancing common bean (Phaseolus vulgaris L.) disease detection with YOLO driven deep learning to enhance agricultural AI.

Common beans (CB), a vital source for high protein content, plays a crucial role in ensuring both nutrition and economic stability in diverse communities, particularly in Africa and Latin America. However, CB cultivation poses a significant threat to diseases that can drastically reduce yield and quality. Detecting these diseases solely based on visual symptoms is challenging, due to the variability across different pathogens and similar symptoms caused by distinct pathogens, further complicating the detection process. Traditional methods relying solely on farmers' ability to detect diseases is inadequate, and while engaging expert pathologists and advanced laboratories is necessary, it can also be resource intensive. To address this challenge, we present a AI-driven system for rapid and cost-effective CB disease detection, leveraging state-of-the-art deep learning and object detection technologies. We utilized an extensive image dataset collected from disease hotspots in Africa and Colombia, focusing on five major diseases: Angular Leaf Spot (ALS), Common Bacterial Blight (CBB), Common Bean Mosaic Virus (CBMV), Bean Rust, and Anthracnose, covering both leaf and pod samples in real-field settings. However, pod images are only available for Angular Leaf Spot disease. The study employed data augmentation techniques and annotation at both whole and micro levels for comprehensive analysis. To train the model, we utilized three advanced YOLO architectures: YOLOv7, YOLOv8, and YOLO-NAS. Particularly for whole leaf annotations, the YOLO-NAS model achieves the highest mAP value of up to 97.9% and a recall of 98.8%, indicating superior detection accuracy. In contrast, for whole pod disease detection, YOLOv7 and YOLOv8 outperformed YOLO-NAS, with mAP values exceeding 95% and 93% recall. However, micro annotation consistently yields lower performance than whole annotation across all disease classes and plant parts, as examined by all YOLO models, highlighting an unexpected discrepancy in detection accuracy. Furthermore, we successfully deployed YOLO-NAS annotation models into an Android app, validating their effectiveness on unseen data from disease hotspots with high classification accuracy (90%). This accomplishment showcases the integration of deep learning into our production pipeline, a process known as DLOps. This innovative approach significantly reduces diagnosis time, enabling farmers to take prompt management interventions. The potential benefits extend beyond rapid diagnosis serving as an early warning system to enhance common bean productivity and quality.

Closing the access barrier for effective anti-malarials in the private sector in rural Uganda: consortium for ACT private sector subsidy (CAPSS) pilot study.

BACKGROUND: Artemisinin-based combination therapy (ACT), the treatment of choice for uncomplicated falciparum malaria, is unaffordable and generally inaccessible in the private sector, the first port of call for most malaria treatment across rural Africa. Between August 2007 and May 2010, the Uganda Ministry of Health and the Medicines for Malaria Venture conducted the Consortium for ACT Private Sector Subsidy (CAPSS) pilot study to test whether access to ACT in the private sector could be improved through the provision of a high level supply chain subsidy. METHODS: Four intervention districts were purposefully selected to receive branded subsidized medicines - "ACT with a leaf", while the fifth district acted as the control. Baseline and evaluation outlet exit surveys and retail audits were conducted at licensed and unlicensed drug outlets in the intervention and control districts. A survey-adjusted, multivariate logistic regression model was used to analyse the intervention's impact on: ACT uptake and price; purchase of ACT within 24 hours of symptom onset; ACT availability and displacement of sub-optimal anti-malarial. RESULTS: At baseline, ACT accounted for less than 1% of anti-malarials purchased from licensed drug shops for children less than five years old. However, at evaluation, "ACT with a leaf" accounted for 69% of anti-malarial purchased in the interventions districts. Purchase of ACT within 24 hours of symptom onset for children under five years rose from 0.8% at baseline to 26.2% (95% CI: 23.2-29.2%) at evaluation in the intervention districts. In the control district, it rose modestly from 1.8% to 5.6% (95% CI: 4.0-7.3%). The odds of purchasing ACT within 24 hours in the intervention districts compared to the control was 0.46 (95% CI: 0.08-2.68, p=0.4) at baseline and significant increased to 6.11 (95% CI: 4.32-8.62, p<0.0001) at evaluation. Children less than five years of age had "ACT with a leaf" purchased for them more often than those aged above five years. There was no evidence of price gouging. CONCLUSIONS: These data demonstrate that a supply-side subsidy and an intensive communications campaign significantly increased the uptake and use of ACT in the private sector in Uganda.

Caregivers' perceived treatment failure in home-based management of fever among Ugandan children aged less than five years.

BACKGROUND: Home-based management of fever (HBMF) could improve prompt access to antimalarial medicines for African children. However, the perception of treatment failure by caregivers has not been assessed. METHODS: Caregiver's perceived treatment outcome in HBMF and in alternative sources of fever treatment was assessed in a rural Ugandan setting using nine hundred and seventy eight (978) caregivers of children between two and 59 months of age, who had reported fever within two weeks prior to the study. RESULTS: Lower caregivers' perceived treatment failure (15% and 23%) was observed in the formal health facilities and in HBMF, compared to private clinics (38%), drug shops (55%) or among those who used herbs (56%). Under HBMF, starting treatment within 24 hours of symptoms onset and taking treatment for the recommended three days duration was associated with a lower perceived treatment failure. Conversely, vomiting, convulsions and any illness in the month prior to the fever episode was associated with a higher perceived treatment failure. CONCLUSION: In this medium malaria transmission setting, caregiver's perceived treatment outcome was better in HBMF compared to alternative informal sources of treatment.

The draft genome sequence of Xanthomonas species strain Nyagatare, isolated from diseased bean in Rwanda.

We announce the genome sequence for Xanthomonas species strain Nyagatare, isolated from beans showing unusual disease symptoms in Rwanda. This strain represents the first sequenced genome belonging to an as-yet undescribed Xanthomonas species known as species-level clade 1. It has at least 100 kb of genomic sequence that shows little or no sequence similarity to other xanthomonads, including a unique lipopolysaccharide synthesis gene cluster. At least one genomic region appears to have been acquired from relatives of Agrobacterium or Rhizobium species. The genome encodes homologues of only three known type-three secretion system effectors: AvrBs2, XopF1 and AvrXv4. Availability of the genome sequence will facilitate development of molecular tools for detection and diagnostics for this newly discovered pathogen of beans and facilitate epidemiological investigations of a potential causal link between this pathogen and the disease outbreak.