Biology subjects

Ghaffar, A.

Publications and source records attributed to Ghaffar, A..

2 recordsLinked to original sources

bioRxiv2025

CitriBEiTNet: A Hybrid CNN-Transformer Architecture Combining MobileNetV2 with BEiT's Global Attention for Automated Citrus Leaf Disease Diagnosis

Citrus farming plays an essential role in agriculture; however, diseases like canker, greening, black spot, and melanose significantly reduce yield and fruit quality. Efficient classification of citrus leaf diseases is important for crop health maintenance and optimal crop yield. Traditional methods for leaf disease detection are slow, labor-intensive, and often inaccurate, which highlights the need for automated solutions. This research presents a novel hybrid approach for identifying citrus diseases by combining a vision transformer with deep learning architectures. Using Bidirectional Encoder Representation from Image Transformers (BEIT) and MobileNetV2 as feature extractors, the proposed model captures distinctive features from images, which are then classified using Support Vector Machine (SVM). The dataset includes four different disease categories and a healthy class. Data augmentation techniques are applied to improve model robustness. The experimental findings demonstrate that CitriBEiTNet achieves a remarkable training accuracy of 99.82% and a testing accuracy of 99.57%, outperforming current leading techniques. This model provides an efficient, scalable, and economical approach for early disease identification, enabling farmers to take preventive measures and improve agricultural yields.

bioengineering↗

bioRxiv2020

Novel Loss-of-Function Mutations in COCH Cause Autosomal Recessive Nonsyndromic Deafness

COCH is the most abundantly expressed gene in the cochlea. Unsurprisingly, mutations in COCH underly deafness in mice and humans. Two forms of deafness are linked to mutations in COCH, the well-established autosomal dominant nonsyndromic hearing loss, with or without vestibular dysfunction (DFNA9) via a gain-of-function/dominant-negative mechanism, and more recently autosomal recessive nonsyndromic hearing loss (DFNB110) via nonsense variants. Using a combination of targeted gene panels, exome sequencing and functional studies, we identified four novel pathogenic variants (two nonsense variants, one missense and one inframe deletion) in COCH as the cause of autosomal recessive hearing loss in a multi-ethnic cohort. To investigate whether the non-truncating variants exert their effect via a loss-of-function mechanism, we used mini-gene splicing assays. Our data showed both the missense and inframe deletion variants altered RNA-splicing by creating an exon splicing silencer and abolishing an exon splicing enhancer, respectively. Both variants create frameshifts and are predicted to result in a null allele. This study confirms the involvement of loss-of-function mutations in COCH in autosomal recessive nonsyndromic hearing loss, expands the mutational landscape of DFNB110 to include coding variants that alter RNA-splicing, and highlights the need to investigate the effect of coding variants on RNA-splicing.

genetics↗