Biology subjects

Hossain, K.

Publications and source records attributed to Hossain, K..

9 recordsLinked to original sources

bioRxiv2026

Drought-Spec-Net: Early Tomato Drought Detection and Potential Yield-Impact Assessment Using Vis NIR Data

Drought stress significantly reduces tomato (Solanum lycopersicum L.) productivity, and early detection is critical to minimize yield losses through timely interventions. In this study, we developed Drought-Spec-Net, a hybrid 1D convolutional neural network that integrates local and global spectral feature extraction to detect early drought stress from visible and near infrared (Vis NIR) spectra data of tomato seedlings. The model was trained on 378 samples using an 80:20 train test split, with 20% of the training set reserved for validation. DroughtSpecNet outperformed the evaluated baseline and state of the art models, achieving 97% accuracy, 95% precision, 98% recall, and an F1 score of 97%. To improve the agronomic interpretation of the model outputs, predicted drought probabilities were converted into a literature-informed potential yield impact indicator using a maximum impact level of 60%. On the test set (76 samples), mapped potential yield-impact values ranged from 0% to 60%, with an average reduction of 12.97%. We also conducted an initial experiment using our greenhouse RGB dataset, collected daily from drought treated and well-watered tomato plants at West Virginia State University (WVSU). From this dataset, 44 images were selected for ilastik-based canopy segmentation, producing plant-level drought severity indices (DSI) with a mean of 0.28, median of 0.14, and range of 0.01 to 0.91. Additionally, we trained and fine-tuned a large language model (LLM) based on PLLaMA7BInstruct, called AgriLLaMA, for automated agronomic report generation from Drought-Spec-Net outputs. The generated reports summarize predicted stress levels, mapped potential yield impacts, and preliminary management considerations. This integrated approach not only improves early drought stress detection but also delivers quantitative and interpretable estimates of potential productivity losses, providing a complete framework connecting physiological stress detection to actionable agricultural outcomes.

plant biology↗

bioRxiv2026

DIRTNet: Enabling Root Phenotyping with Fiber Bragg Grating Sensors

Non-destructive methods for real-time phenotyping of root growth and development are essential to accelerate the breeding of climate-resilient crops. We present DIRTNet (Digital Investigations of Root Traits Net), a hybrid deep learning model that interprets in-soil signals collected by Fiber Bragg Grating (FBG) sensors. We first evaluated DIRTNet in a controlled simulation study in which metal rods of varying diameters were inserted into soil to emulate root growth. Using augmented training data with an 80:20 train-test split, DIRTNet surpassed baseline models, achieving 0.97 accuracy for root depth prediction and 0.94 for root diameter prediction. We then applied the best-performing models to maize (Zea mays) roots monitored by six FBG sensors placed at different soil location and depths. A control trial and a drought-stress trial yielded 192 samples, split 80:20 into training and holdout sets; the hold-out portion was divided equally into validation and test sets. Augmentation was applied only to the training data. On real maize root data, DIRTNet achieved 0.92 accuracy for both root depth and root width prediction across variable growth periods, covering root mass lengths up to 20 cm and diameters up to 10 cm. The prediction accuracy is independent of the soil moisture and drought condition. In a fixed-interval analysis, accuracy reached 0.97 for days 25-42 after planting and 0.93 for days 25-48, demonstrating robust performance as root complexity increased.

plant biology↗

bioRxiv2026

LeafyVGG-16: Transfer Learning for Plant Disease Detection with Cyber Risk Analysis

Plant disease detection using deep learning is essential for precision agriculture, enabling early and automated crop health monitoring. This study proposes an end-to-end transfer learning pipeline, LeafyVGG-16, for multi-class classification of plant diseases and nutrient deficiencies using a tomato leaf dataset. The framework integrates data preprocessing, augmentation, and a VGG-16 backbone with a two-stage fine-tuning strategy. The proposed model is evaluated against CNN, DenseNet-121, Inception-V3, EfficientNetB0, and ResNet-50, achieving an accuracy of 0.93 with precision, recall, and F1-scores of 0.93, 0.90, and 0.92, respectively. These results demonstrate the effectiveness of transfer learning for fine-grained plant disease recognition. We further evaluate model robustness under adversarial cyber attacks to assess deployment reliability in agricultural systems. Under Fast Gradient Sign Method (FGSM) attacks ({epsilon} = 0.01- 0.05), the model shows an accuracy drop of 1%-7.5%, while Projected Gradient Descent (PGD) attacks ({epsilon} = 0.05, step size = 0.005, 10 iterations) produce similar degradation, highlighting the models vulnerability to adversarial perturbations. These findings highlight potential security and reliability risks in AI-based agricultural decision-making systems. Future work will focus on improving robustness and cyber-resilience and extending this framework to other crops for secure and context-aware deployment in resource-constrained environments.

plant biology↗

bioRxiv2025

LeafyResNet: Fusarium Wilt Detection in Lettuce Using UAV RGB Imaging and Advanced Deep Learning Model

Lettuce, one of the most consumed leafy greens globally, offers significant health benefits due to its high vitamin, mineral, and fiber content. However, Fusarium wilt, a soil-borne fungus, threatens lettuce yields by reducing both quality and quantity. Traditional disease detection methods, such as manual inspection, are time-consuming and inefficient. This study proposes a Unmanned Aerial Vehicle (UAV)-based approach for detecting Fusarium wilt in lettuce using high-resolution Red-Green-Blue (RGB) imagery. (1) a high resolution RGB lettuce dataset captured by drones at approximately 10 m altitude in collaboration with the Yuma Center of Excellence for Desert Agriculture, (2) identification of candidate Fusarium-infected regions by evaluating 300x300 pixel image patches for light tan coloration, followed by the application of a customized Residual Neural Network (ResNet), called LeafyResNet, to confirm Fusarium presence, and (3) a method for quantifying Fusarium infection severity, which was validated against an expert-ground truth. Our approach to detect Fusarium wilt achieves 96.30% accuracy, 94.10% precision, 100% recall, and a 97.10% F1-score, with a 4% false positive rate. Disease severity scores showed an overall accuracy of 86%. We compared the model to state-of-the-art models, including two variants of ResNet (ResNet18 and ResNet34), Inception_v3, and VGG16. LeafyResNet showed superior results compared to available standard models, highlighting the potential of customizing models for agricultural applications. LeafyResNet provides an efficient and scalable solution for Fusarium wilt monitoring for lettuce crops to advance precision agriculture.

bioinformatics↗

bioRxiv2024

Fiber Bragg grating based sensing system for non-destructive root phenotyping using ResNet prediction

Real-time measurements of crop root architecture can overcome limitations faced by plant breeders when developing climate-resilient plants. Due to current measurement methods failing to continuously monitor root growth in a non-destructive and scalable fashion, we propose a first in-soil sensing system based on fiber Bragg gratings (FBG). The sensing system logs three-dimensional strain generated by a growing pseudo-root. Two ResNet models confirm the utility of in-soil FBG sensors by predicting pseudo-root width and depth with accuracies of 92% and 93%, respectively. To analyze model robustness, a preliminary experiment was performed where FBGs logged strain generated from a corn plants roots for 30 days. The models were then retrained on new data where they achieved accuracies of 98% and 96%, respectively. Our presented prototype has potential prospects to go beyond measuring root parameters and sense its surrounding soil environment.

plant biology↗

bioRxiv2024

In mice, discrete odors can selectively promote the neurogenesis of sensory neuron subtypes that they stimulate

In mammals, olfactory sensory neurons (OSNs) are born throughout life, ostensibly solely to replace neurons lost via turnover or injury. This assumption follows from the hypothesis that olfactory neurogenesis is stochastic with respect to neuron subtype, as defined by the single odorant receptor that each neural precursor stochastically chooses out of hundreds of possibilities. This assumption is challenged, however, by recent findings that the birthrates of a fraction of OSN subtypes are selectively reduced by olfactory deprivation. These findings raise questions about how, and why, olfactory stimuli are required to accelerate the neurogenesis rates of some subtypes, including whether the stimuli are specific (e.g., discrete odorants) or generic (e.g., broadly activating odors or mechanical stimuli). Based on previous findings that the exposure of mice to sex-specific odors can increase the representations of subtypes responsive to those odors, we hypothesized that the neurogenic stimuli comprise discrete odorants that selectively stimulate OSNs of the same subtypes whose birthrates are accelerated. In support of this, we have found, using scRNA-seq and subtype-specific OSN birthdating, that exposure to male and exogenous musk odors can accelerate the birthrates of subtypes responsive to those odors. These findings reveal that certain odor experiences can selectively amplify specific OSN subtypes and suggest that persistent OSN neurogenesis serves, in part, an adaptive function.

neuroscience↗

bioRxiv2022

Convection-enhanced diffusion and directed withdrawal of methylene blue in agarose hydrogel using finite element analyses

Precision drug delivery for optimized therapeutic targeting requires knowledge of momentum transport and molecular diffusion of molecules within the patients interstitial tissue, especially for tumor treatment within the brain. Dispersion in the interstitial space is impacted by delivery method, tissue material properties, individual-specific fluid flow, and particle size of the input solute. Knowledge of a drugs dispersion allows for optimizing solute delivery, concentration, and flow rates to maximize drug distribution and biomarker recovery. For delivering drugs, increased knowledge of drug location after delivery can improve therapeutic treatment by optimizing the dosing of healthy and unhealthy tissue. Finite element methods (FEM) tools, such as COMSOL Multiphysics, can simulate molecular distribution inside-individual specific shapes and porous material properties. Furthermore, an additional unmet need is delivery methods that can be adjusted to manipulate diffusion regions through tissue via techniques such as directed flow. This would be especially valuable in targeted drug delivery within tumors to increase the cancerous surface area covered while limiting damage to surrounding tissues. In this project, the directed flow was induced by perfusing the injected solution at an input probe while withdrawing fluid at an output probe, enabling targeted flow through the desired region. FEM computation faithfully replicated these conditions and could be used to determine the effective concentrations perfused over the region of interest. We leveraged COMSOL Multiphysics to perform a computational study simulating convection-enhanced delivery (CED) with an output probe pulling the concentration profile over the region of interest. This simulation system can be applied to therapeutics targeting, vaccine subcutaneous injection, and waste and media diffusion in tissue engineering.

bioengineering↗

bioRxiv2022

A Ferroptosis-mediated regulation of the biogenesis of the oxidative phosphorylation system

Several subunits in the matrix domain of mitochondrial complex I (CI) have been posited to be redox sensors for CI; but how elevated levels of reactive oxygen species (ROS) impinge on CI assembly is unknown. We report that when the mitochondrial NADPH-generating enzyme - Isocitrate Dehydrogenase 2 - is genetically disrupted, ROS levels are elevated and assembly of the oxidative phosphorylation system (OXPHOS) is impaired. Mechanistically, this begins with a ROS-mediated inhibition of biosynthesis of the matrix domain of CI, which progresses to a point where ferroptotic signals are induced, the mitochondrial unfolded protein response is activated and multiple OXPHOS complexes are impaired. Disruption of other enzymes that eliminate hydrogen peroxide, but not those that eliminate the superoxide radical, recapitulates the phenotype; implicating hydrogen peroxide as the signaling molecule involved. Thus, the redox status of the mitochondrion modulates the assembly of the matrix domain of CI and ultimately that of the entire OXPHOS.

cell biology↗

bioRxiv2020

Early cis-regulatory events in the formation of retinal horizontal cells

During retinal development, multipotent and restricted progenitor cells generate all of the neuronal cells of the retina. Among these are horizontal cells, which are interneurons that modulate the light-induced signal from photoreceptors. This study utilizes the identification of novel cis-regulatory elements as a method to examine the gene regulatory networks that direct the development of horizontal cells. Here we describe a screen for cis-regulatory elements, or enhancers, for the horizontal cell-associated genes PTF1A, ONECUT1 (OC1), TFAP2A (AP2A), and LHX1. The OC1ECR22 and Tfap2aACR5 elements were shown to be potential enhancers for OC1 and TFAP2A, respectively, and to be specifically active in developing horizontal cells. The OC1ECR22 element is activated by PTF1A and RBPJ, which translates to regulation of OC1 expression and suggests that PTF1A is a direct activator of OC1 expression in developing horizontal cells. The region within the Tfap2aACR5 element that is responsible for its activation was determined to be a 100 bp sequence named Motif 4. Both OC1ECR22 and Tfap2aACR5 are negatively regulated by the nuclear receptors THRB and RXRG, as is the expression of OC1 and AP2A, suggesting that nuclear receptors may have a role in the negative regulation of horizontal cell development.

developmental biology↗