Md Nadim Mahamood, Md Imran Hasan, Md Rasheduzzaman
et al.
The rapid growth of the global population, alongside exponential technological advancement, has intensified the demand for food production. Meeting this demand depends not only on increasing agricultural yield but also on minimizing food loss caused by crop diseases. Diseases account for a substantial portion of apple production losses, despite apples being among the most widely produced and nutritionally valuable fruits worldwide. Previous studies have employed machine learning techniques for feature extraction and early diagnosis of apple leaf diseases, and more recently, deep learning-based models have shown remarkable performance in disease recognition. However, most state-of-the-art deep learning models are highly parameter-intensive, resulting in increased training and inference time. Although lightweight models are more suitable for user-friendly and resource-constrained applications, they often suffer from performance degradation. To address the trade-off between efficiency and performance, we propose Mam-App, a parameter-efficient Mamba-based model for feature extraction and leaf disease classification. The proposed approach achieves competitive state-of-the-art performance on the PlantVillage Apple Leaf Disease dataset, attaining 99.58% accuracy, 99.30% precision, 99.14% recall, and a 99.22% F1-score, while using only 0.051M parameters. This extremely low parameter count makes the model suitable for deployment on drones, mobile devices, and other low-resource platforms. To demonstrate the robustness and generalizability of the proposed model, we further evaluate it on the PlantVillage Corn Leaf Disease and Potato Leaf Disease datasets. The model achieves 99.48%, 99.20%, 99.34%, and 99.27% accuracy, precision, recall, and F1-score on the corn dataset and 98.46%, 98.91%, 95.39%, and 97.01% on the potato dataset, respectively.
Modern disease classification often overlooks molecular commonalities hidden beneath divergent clinical presentations. This study introduces a transcriptomics-driven framework for discovering disease relationships by analyzing over 1300 disease-condition pairs using GenoMAS, a fully automated agentic AI system. Beyond identifying robust gene-level overlaps, we develop a novel pathway-based similarity framework that integrates multi-database enrichment analysis to quantify functional convergence across diseases. The resulting disease similarity network reveals both known comorbidities and previously undocumented cross-category links. By examining shared biological pathways, we explore potential molecular mechanisms underlying these connections-offering functional hypotheses that go beyond symptom-based taxonomies. We further show how background conditions such as obesity and hypertension modulate transcriptomic similarity, and identify therapeutic repurposing opportunities for rare diseases like autism spectrum disorder based on their molecular proximity to better-characterized conditions. In addition, this work demonstrates how biologically grounded agentic AI can scale transcriptomic analysis while enabling mechanistic interpretation across complex disease landscapes. All results are publicly accessible at github.com/KeeeeChen/Pathway_Similarity_Network.
Shih-Huan Huang, Matthew W. Cotton, Tuomas P. J. Knowles
et al.
A central challenge in modeling neurodegenerative diseases is connecting cellular-level mechanisms to tissue-level pathology, in particular to determine whether pathology is driven primarily by cell-autonomous triggers or by propagation from cells that are already in a pathological, runaway aggregation state. To bridge this gap, we here develop a bottom-up physical model that explicitly incorporates these two fundamental cell-level drivers of protein aggregation dynamics. We show that our model naturally explains the characteristic long, slow development of pathology followed by a rapid acceleration, a hallmark of many neurodegenerative diseases. Furthermore, the model reveals the existence of a critical switch point at which the system's dynamics transition from being dominated by slow, spontaneous formation of diseased cells to being driven by fast propagation. This framework provides a robust physical foundation for interpreting pathological data and offers a method to predict which class of therapeutic strategies is best matched to the underlying drivers of a specific disease.
Ummay Maria Muna, Fahim Hafiz, Shanta Biswas
et al.
Small nucleolar RNAs (snoRNAs) are increasingly recognized for their critical role in the pathogenesis and characterization of various human diseases. Consequently, the precise identification of snoRNA-disease associations (SDAs) is essential for the progression of diseases and the advancement of treatment strategies. However, conventional biological experimental approaches are costly, time-consuming, and resource-intensive; therefore, machine learning-based computational methods offer a promising solution to mitigate these limitations. This paper proposes a model called 'GBDTSVM', representing a novel and efficient machine learning approach for predicting snoRNA-disease associations by leveraging a Gradient Boosting Decision Tree (GBDT) and Support Vector Machine (SVM). 'GBDTSVM' effectively extracts integrated snoRNA-disease feature representations utilizing GBDT and SVM is subsequently utilized to classify and identify potential associations. Furthermore, the method enhances the accuracy of these predictions by incorporating Gaussian kernel profile similarity for both snoRNAs and diseases. Experimental evaluation of the GBDTSVM model demonstrated superior performance compared to state-of-the-art methods in the field, achieving an area under the receiver operating characteristic (AUROC) of 0.96 and an area under the precision-recall curve (AUPRC) of 0.95 on MDRF dataset. Moreover, our model shows superior performance on two more datasets named LSGT and PsnoD. Additionally, a case study on the predicted snoRNA-disease associations verified the top 10 predicted snoRNAs across nine prevalent diseases, further validating the efficacy of the GBDTSVM approach. These results underscore the model's potential as a robust tool for advancing snoRNA-related disease research. Source codes and datasets our proposed framework can be obtained from: https://github.com/mariamuna04/gbdtsvm
Crop diseases pose significant threats to global food security, agricultural productivity, and sustainable farming practices, directly affecting farmers' livelihoods and economic stability. To address the growing need for effective crop disease management, AI-based disease alerting systems have emerged as promising tools by providing early detection and actionable insights for timely intervention. However, existing systems often overlook critical aspects such as data privacy, market pricing power, and farmer-friendly usability, leaving farmers vulnerable to privacy breaches and economic exploitation. To bridge these gaps, we propose AgriSentinel, the first Privacy-Enhanced Embedded-LLM Crop Disease Alerting System. AgriSentinel incorporates a differential privacy mechanism to protect sensitive crop image data while maintaining classification accuracy. Its lightweight deep learning-based crop disease classification model is optimized for mobile devices, ensuring accessibility and usability for farmers. Additionally, the system includes a fine-tuned, on-device large language model (LLM) that leverages a curated knowledge pool to provide farmers with specific, actionable suggestions for managing crop diseases, going beyond simple alerting. Comprehensive experiments validate the effectiveness of AgriSentinel, demonstrating its ability to safeguard data privacy, maintain high classification performance, and deliver practical, actionable disease management strategies. AgriSentinel offers a robust, farmer-friendly solution for automating crop disease alerting and management, ultimately contributing to improved agricultural decision-making and enhanced crop productivity.
Genetic mutations can disrupt protein structure, stability, and solubility, contributing to a wide range of diseases. Existing predictive models often lack interpretability and fail to integrate physical and chemical interactions critical to molecular mechanisms. Moreover, current approaches treat disease association, stability changes, and solubility alterations as separate tasks, limiting model generalizability. In this study, we introduce a unified framework based on multiscale commutative algebra to capture intrinsic physical and chemical interactions for the first time. Leveraging Persistent Stanley-Reisner Theory, we extract multiscale algebraic invariants to build a Commutative Algebra neural Network (CANet). Integrated with transformer features and auxiliary physical features, we apply CANet to tackle three key domains for the first time: disease-associated mutations, mutation-induced protein stability changes, and solubility changes upon mutations. Across six benchmark tasks, CANet and its gradient boosting tree counterpart, CATree, consistently attain state-of-the-art performance, achieving up to 7.5% improvement in predictive accuracy. Our approach offers multiscale, mechanistic, interpretable,and generalizable models for predicting disease-mutation associations.
Aziz A. Chentoufi, Jeffrey B. Ulmer, Lbachir BenMohamed
The COVID-19 pandemic, caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), is in its sixth year and is being maintained by the inability of current spike-alone-based COVID-19 vaccines to prevent transmission leading to the continuous emergence of variants and sub-variants of concern (VOCs). This underscores the critical need for next-generation broad-spectrum pan-Coronavirus vaccines (pan-CoV vaccine) to break this cycle and end the pandemic. The development of a pan-CoV vaccine offering protection against a wide array of VOCs requires two key elements: (1) identifying protective antigens that are highly conserved between passed, current, and future VOCs; and (2) developing a safe and efficient antigen delivery system for induction of broad-based and long-lasting B- and T-cell immunity. This review will (1) present the current state of antigen delivery platforms involving a multifaceted approach, including bioinformatics, molecular and structural biology, immunology, and advanced computational methods; (2) discuss the challenges facing the development of safe and effective antigen delivery platforms; and (3) highlight the potential of nucleoside-modified mRNA encapsulated in lipid nanoparticles (LNP) as the platform that is well suited to the needs of a next-generation pan-CoV vaccine, such as the ability to induce broad-based immunity and amenable to large-scale manufacturing to safely provide durable protective immunity against current and future Coronavirus threats.
Kohei Iwano, Shogo Shibuya, Satoshi Kagiwada
et al.
Recently, object detection methods (OD; e.g., YOLO-based models) have been widely utilized in plant disease diagnosis. These methods demonstrate robustness to distance variations and excel at detecting small lesions compared to classification methods (CL; e.g., CNN models). However, there are issues such as low diagnostic performance for hard-to-detect diseases and high labeling costs. Additionally, since healthy cases cannot be explicitly trained, there is a risk of false positives. We propose the Hierarchical object detection and recognition framework (HODRF), a sophisticated and highly integrated two-stage system that combines the strengths of both OD and CL for plant disease diagnosis. In the first stage, HODRF uses OD to identify regions of interest (ROIs) without specifying the disease. In the second stage, CL diagnoses diseases surrounding the ROIs. HODRF offers several advantages: (1) Since OD detects only one type of ROI, HODRF can detect diseases with limited training images by leveraging its ability to identify other lesions. (2) While OD over-detects healthy cases, HODRF significantly reduces these errors by using CL in the second stage. (3) CL's accuracy improves in HODRF as it identifies diagnostic targets given as ROIs, making it less vulnerable to size changes. (4) HODRF benefits from CL's lower annotation costs, allowing it to learn from a larger number of images. We implemented HODRF using YOLOv7 for OD and EfficientNetV2 for CL and evaluated its performance on a large-scale dataset (4 crops, 20 diseased and healthy classes, 281K images). HODRF outperformed YOLOv7 alone by 5.8 to 21.5 points on healthy data and 0.6 to 7.5 points on macro F1 scores, and it improved macro F1 by 1.1 to 7.2 points over EfficientNetV2.
Danielle C. Ompad, Timir K. Padhan, Anne Kessler
et al.
AbstractDurgama Anchalare Malaria Nirakaran (DAMaN) is a multi-component malaria intervention for hard-to-reach villages in Odisha, India. The main component, malaria camps (MCs), consists of mass screening, treatment, education, and intensified vector control. We evaluated MC effectiveness using a quasi-experimental cluster-assigned stepped-wedge study with a pretest–posttest control group in 15 villages: six immediate (Arm A), six delayed (Arm B), and three previous interventions (Arm C). The primary outcome was PCR + Plasmodium infection prevalence. The time (i.e., baseline vs. follow-up 3) x study arm interaction term shows that there were statistically significant lower odds of PCR + Plasmodium infection in Arm A (AOR = 0.36, 95% CI = 0.17, 0.74) but not Arm C as compared to Arm B at the third follow-up. The cost per person ranged between US$3–8, the cost per tested US$4–9, and the cost per treated US$82–1,614, per camp round. These results suggest that the DAMaN intervention is a promising and financially feasible approach for malaria control.
In this study, we investigated the application of bio-inspired optimization algorithms, including Genetic Algorithm, Particle Swarm Optimization, and Whale Optimization Algorithm, for feature selection in chronic disease prediction. The primary goal was to enhance the predictive accuracy of models streamline data dimensionality, and make predictions more interpretable and actionable. The research encompassed a comparative analysis of the three bio-inspired feature selection approaches across diverse chronic diseases, including diabetes, cancer, kidney, and cardiovascular diseases. Performance metrics such as accuracy, precision, recall, and f1 score are used to assess the effectiveness of the algorithms in reducing the number of features needed for accurate classification. The results in general demonstrate that the bio-inspired optimization algorithms are effective in reducing the number of features required for accurate classification. However, there have been variations in the performance of the algorithms on different datasets. The study highlights the importance of data pre-processing and cleaning in ensuring the reliability and effectiveness of the analysis. This study contributes to the advancement of predictive analytics in the realm of chronic diseases. The potential impact of this work extends to early intervention, precision medicine, and improved patient outcomes, providing new avenues for the delivery of healthcare services tailored to individual needs. The findings underscore the potential benefits of using bio-inspired optimization algorithms for feature selection in chronic disease prediction, offering valuable insights for improving healthcare outcomes.
We construct a set of new epidemiological thresholds to address the general problem of spreading and containment of a disease with influx of infected individuals when the classic $\mathcal R_0$ is no longer meaningful. We provide analytical properties of these indices and illustrate their usefulness in a compartmental model of COVID-19 with data taken from Chile showing a good predictive potential when contrasted with the recorded disease behaviour. This approach and the associated analytical and numerical results allow us to quantify the severity of an immigration of infectious individuals into a community, and identification of the key parameters that are capable of changing or reversing the spread of an infectious disease in specific models.
Ritesh Chandra, Sadhana Tiwari, Sonali Agarwal
et al.
Vector-borne diseases (VBDs) are a kind of infection caused through the transmission of vectors generated by the bites of infected parasites, bacteria, and viruses, such as ticks, mosquitoes, triatomine bugs, blackflies, and sandflies. If these diseases are not properly treated within a reasonable time frame, the mortality rate may rise. In this work, we propose a set of ontologies that will help in the diagnosis and treatment of vector-borne diseases. For developing VBD's ontology, electronic health records taken from the Indian Health Records website, text data generated from Indian government medical mobile applications, and doctors' prescribed handwritten notes of patients are used as input. This data is then converted into correct text using Optical Character Recognition (OCR) and a spelling checker after pre-processing. Natural Language Processing (NLP) is applied for entity extraction from text data for making Resource Description Framework (RDF) medical data with the help of the Patient Clinical Data (PCD) ontology. Afterwards, Basic Formal Ontology (BFO), National Vector Borne Disease Control Program (NVBDCP) guidelines, and RDF medical data are used to develop ontologies for VBDs, and Semantic Web Rule Language (SWRL) rules are applied for diagnosis and treatment. The developed ontology helps in the construction of decision support systems (DSS) for the NVBDCP to control these diseases.
Aziz A. Chentoufi, Nisha R. Dhanushkodi, Ruchi Srivastava
et al.
The development of vaccines against herpes simplex virus type 1 and type 2 (HSV1 and HSV-2) is an important goal for global health. In this review we reexamined (i) the status of ocular herpes vaccines in clinical trials; and (ii) discusses the recent scientific advances in the understanding of differential immune response between HSV infected asymptomatic and symptomatic individuals that form the basis for the new combinatorial vaccine strategies targeting HSV; and (iii) shed light on our novel “asymptomatic” herpes approach based on protective immune mechanisms in seropositive asymptomatic individuals who are “naturally” protected from recurrent herpetic diseases. We previously reported that phenotypically and functionally distinct HSV-specific memory CD8+T cell subsets in asymptomatic and symptomatic HSV-infected individuals. Moreover, a better protection induced following a prime/pull vaccine approach that consists of first priming anti-viral effector memory T cells systemically and then pulling them to the sites of virus reactivation (e.g., sensory ganglia) and replication (e.g., eyes and vaginal mucosa), following mucosal administration of vectors expressing T cell-attracting chemokines. In addition, we reported that a combination of prime/pull vaccine approach with approaches to reverse T cell exhaustion led to even better protection against herpes infection and disease. Blocking PD-1, LAG-3, TIGIT and/or TIM-3 immune checkpoint pathways helped in restoring the function of antiviral HSV-specific CD8+T cells in latently infected ganglia and increased efficacy and longevity of the prime/pull herpes vaccine. We discussed that a prime/pull vaccine strategy that use of asymptomatic epitopes, combined with immune checkpoint blockade would prove to be a successful herpes vaccine approach.
M. Alejandra Mandel, Sinem Beyhan, Mark Voorhies
et al.
Coccidioides spp. are mammalian fungal pathogens endemic to the Southwestern US and other desert regions of Mexico, Central and South America, with the bulk of US infections occurring in California and Arizona. In the soil, Coccidioides grows in a hyphal form that differentiates into 3–5 micron asexual spores (arthroconidia). When arthroconidia are inhaled by mammals they undergo a unique developmental transition from polar hyphal growth to isotropic expansion with multiple rounds of nuclear division, prior to segmentation, forming large spherules filled with endospores. Very little is understood about the molecular basis of spherule formation. Here we characterize the role of the conserved transcription factor Ryp1 in Coccidioides development. We show that Coccidioides Δ ryp1 mutants have altered colony morphology under hypha-promoting conditions and are unable to form mature spherules under spherule-promoting conditions. We analyze the transcriptional profile of wild-type and Δ ryp1 mutant cells under hypha- and spherule-promoting conditions, thereby defining a set of hypha- or spherule-enriched transcripts (“morphology-regulated” genes) that are dependent on Ryp1 for their expression. Forty percent of morphology-regulated expression is Ryp1-dependent, indicating that Ryp1 plays a dual role in both hyphal and spherule development. Ryp1-dependent transcripts include key virulence factors such as SOWgp, which encodes the spherule outer wall glycoprotein. Concordant with its role in spherule development, we find that the Δ ryp1 mutant is completely avirulent in the mouse model of coccidioidomycosis, indicating that Ryp1-dependent pathways are essential for the ability of Coccidioides to cause disease. Vaccination of C57BL/6 mice with live Δ ryp1 spores does not provide any protection from lethal C . posadasii intranasal infection, consistent with our findings that the Δ ryp1 mutant fails to make mature spherules and likely does not express key antigens required for effective vaccination. Taken together, this work identifies the first transcription factor that drives mature spherulation and virulence in Coccidioides .
Matthew G. Brewer, Stephanie R. Monticelli, Mary C. Moran
et al.
Individuals with underlying chronic skin conditions, notably atopic dermatitis (AD), are disproportionately affected by infections from members of the herpesviridae, papovaviridae, and poxviridae families. Many patients with AD experience recurrent, widespread cutaneous viral infections that can lead to viremia, serious organ complications, and even death. Little is known about how the type 2 inflammatory environment observed in the skin of AD patients impacts the susceptibility of epidermal cells (keratinocytes) to viral pathogens. Herein, we studied the susceptibility of keratinocytes to the prototypical poxvirus, vaccinia virus (VV)—the causative agent of eczema vaccinatum—under conditions that simulate the epidermal environment observed in AD. Treatment of keratinocytes with type 2 cytokines (IL-4 and -13) to simulate the inflammatory environment or a tight junction disrupting peptide to mirror the barrier disruption observed in AD patients, resulted in a differentiation-dependent increase in susceptibility to VV. Furthermore, pan JAK inhibition was able to diminish the VV susceptibility occurring in keratinocytes exposed to type 2 cytokines. We propose that in AD, the increased viral susceptibility of keratinocytes leads to enhanced virus production in the skin, which contributes to the rampant dissemination and pathology seen within patients.
The human aorta is a high-risk area for vascular diseases, which are commonly restored by thoracic endovascular aortic repair. In this paper, we report a promising shear-activated targeted nanoparticle drug delivery strategy to assist in the treatment of coarctation of the aorta and aortic aneurysm. Idealized three-dimensional geometric models of coarctation of the aorta and aortic aneurysm are designed, respectively. The unique hemodynamic environment of the diseased aorta is used to improve nanoparticle drug delivery. Micro-carriers with nanoparticle drugs would be targeting activated to release nanoparticle drugs by local abnormal shear stress rate (SSR). Coarctation of the aorta provides a high SSR hemodynamic environment, while the aortic aneurysm is exposed to low SSR. We propose a method to calculate the SSR thresholds for the diseased aorta. Results show that the upstream near-wall area of the diseased location is an ideal injection location for the micro-carriers, which could be activated by the abnormal SSR. Released nanoparticle drugs would be successfully targeted delivered to the aortic diseased wall. Besides, the high diffusivity of the micro-carriers and nanoparticle drugs has a significant impact on the surface drug concentrations of the diseased aortic walls, especially for aortic aneurysms. This study preliminary demonstrates the feasibility of shear-activated targeted nanoparticle drug delivery in the treatment of aortic diseases and provides a theoretical basis for developing the drug delivery system and novel therapy.
We develop a mathematical framework to study the economic impact of infectious diseases by integrating epidemiological dynamics with a kinetic model of wealth exchange. The multi-agent description leads to study the evolution over time of a system of kinetic equations for the wealth densities of susceptible, infectious and recovered individuals, whose proportions are driven by a classical compartmental model in epidemiology. Explicit calculations show that the spread of the disease seriously affects the distribution of wealth, which, unlike the situation in the absence of epidemics, can converge towards a stationary state with a bimodal form. Furthermore, simulations confirm the ability of the model to describe different phenomena characteristics of economic trends in situations compromised by the rapid spread of an epidemic, such as the unequal impact on the various wealth classes and the risk of a shrinking middle class.
We introduce a Python package for modeling and studying the spread of infectious diseases using an agent-based SEIR style epidemiological model with a focus on university campuses. This document explains the epidemiological model used in the package and gives examples highlighting the ways that the package can be used.
Rare diseases affect a relatively small number of people, which limits investment in research for treatments and cures. Developing an efficient method for rare disease detection is a crucial first step towards subsequent clinical research. In this paper, we present a semi-supervised learning framework for rare disease detection using generative adversarial networks. Our method takes advantage of the large amount of unlabeled data for disease detection and achieves the best results in terms of precision-recall score compared to baseline techniques.