MultiTox: A sequence-based stacked ensemble model for multiclass protein toxin classification.

Understanding the structural and functional diversity of toxin proteins is critical for elucidating macromolecular behavior, mechanistic variability, and structure-driven bioactivity. Traditional approaches have primarily focused on binary toxicity prediction, offering limited resolution into distinct modes of action of toxins. Here, we present MultiTox, an ensemble stacking framework for the classification of toxin proteins based on their molecular mode of action: neurotoxins, cytotoxins, hemotoxins, and enterotoxins.

ESCMID workshop: Artificial Intelligence and Machine Learning in Medical Microbiology Diagnostics.

Rapid advancements in artificial intelligence (AI) and machine learning (ML) offer significant potential to transform medical microbiology diagnostics, improving pathogen identification, antimicrobial susceptibility prediction and outbreak detection. To address these opportunities and challenges, the ESCMID workshop, "Artificial Intelligence and Machine Learning in Medical Microbiology Diagnostics", was held in Zurich, Switzerland, from June 2-5, 2025. The course featured expert lectures, practical sessions and panel discussions covering foundational ML concepts and deep learning architectures, data interoperability, quality control processes, model development and validation strategies.

Prediction of exosomal miRNA-based biomarkers for liquid biopsy.

In this study, we investigated the properties of exosomal miRNAs to identify potential biomarkers for liquid biopsy. We collected 956 exosomal and 956 non-exosomal miRNA sequences from RNALocate and miRBase to develop predictive models. Our initial analysis reveals that specific nucleotides are preferred at certain positions in miRNAs associated with exosomes.

Machine learning-driven analysis of temporal pupil dynamics for interpretable ADHD diagnosis.

Attention-deficit/hyperactivity disorder (ADHD) is a prevalent neurodevelopmental disorder characterized by inattention and hyperactivity. Current diagnostic methods rely on bias-prone subjective assessments, such as clinical interviews and behavior rating scales. Objective biomarkers remain elusive hindering standardized ADHD diagnosis.

Protocol for cellular age prediction in yeast and human single cells using transfer learning.

Here, we present a protocol for predicting cellular age via computer vision analysis of cellular morphology and aging-related bioactivities from phase contrast microscopy images. We describe the steps for cultivating yeast cells, performing phase contrast microscopy of drug-treated yeast cells, and inducing senescence in human dermal fibroblasts. We detail the process of using the scCamAge Docker container, running the scCamAge model, applying the yeast-trained model to senescent human fibroblasts, and performing transfer learning to adapt scCamAge using human fibroblast data.

Cross-species comparison of rodent and human decision-making in the Iowa Gambling Task in select neurological and psychiatric disorders: translational approach to examine age- and sex-specific effects of stress and corticolimbic perturbations.

Introduction: Rodent models are widely used to understand brain pathologies and address cognitive deficits experienced by humans diagnosed with clinical disorders. However, stark differences in the nervous system and in the environmental demands of rodents and humans make it difficult to translate insights from rodents to humans. Age and sex further increase vulnerability to disorders via experiences marked by neglect, deprivation, threat, and constraining environments instead of care, nutrition, safety, and enriching environment.

NfκBin: a machine learning based method for screening TNF-α induced NF-κB inhibitors.

Introduction: Nuclear Factor kappa B (NF-κB) is a transcription factor whose upregulation is associated in chronic inflammatory diseases, including rheumatoid arthritis, inflammatory bowel disease, and asthma. In order to develop therapeutic strategies targeting NF-κB-related diseases, we developed a computational approach to predict drugs capable of inhibiting TNF-α induced NF-κB signaling pathways.

Method: We utilized a dataset comprising 1,149 inhibitors and 1,332 non-inhibitors retrieved from PubChem.

Enabling scalable single-cell transcriptomic analysis through distributed computing with Apache spark.

As the field of single-cell genomics continues to develop, the generation of large-scale scRNA-seq datasets has become more prevalent. Although these datasets offer tremendous potential for shedding light on the complex biology of individual cells, the sheer volume of data presents significant challenges for management and analysis. Off late, to address these challenges, a new discipline, known as "big single-cell data science," has emerged.

Understanding 30-Day Mortality After First STEMI Through DAGs: Unravelling Epidemiological Cause-Effect Links.

Background And Aim: Traditional statistical tests have limitations in analyzing cause-and-effect relationships. Directed acyclic graphs (DAGs) offer a structured representation of causality. This study aimed to utilize DAGs to explore the causal impact of epidemiological factors on 30-day mortality among patients following their first acute ST-elevation myocardial infarction (STEMI).

HAIRpred: Prediction of human antibody interacting residues in an antigen from its primary structure.

In the past, several methods have been developed for predicting conformational B-cell epitopes in antigens that are not specific to any host. Our primary analysis of antibody-antigen complexes indicated a need to develop host-specific B-cell epitopes. In this study, we present a novel approach to predict conformational B-cell epitopes specific to human hosts by focusing on human antibody interacting residues in antigens.

A large language model for predicting neurotoxic peptides and neurotoxins.

The accurate prediction of neurotoxicity in peptides and proteins is essential for the safety evaluation of therapeutic proteins and genetically modified (GM) organisms. Existing tools, including our earlier method NTxPred, typically use a single predictive model for both neurotoxic peptides and proteins, despite their structural and functional differences. This lack of specialization may lead to suboptimal performance and limited generalizability.

In Silico tool for predicting, designing and scanning IL-2 inducing peptides.

Interleukin-2 (IL-2) based immunotherapy has been approved for treating certain types of cancer, as IL-2 plays a crucial role in regulating the immune system. In this study, we developed a method for predicting IL-2-inducing peptides. Our method was trained, tested, and validated on a main dataset containing 6,574 experimentally validated Major histocompatibility complex (MHC) binders, including 3,429 IL-2-inducing and 3,145 non-inducing peptides.

Epigenetic modifications in the murine liver upon depletion of transcriptional coregulator host cell factor 1.

Background: Transcriptional co-regulators fine-tune gene expression by modulating transcription factor activity and chromatin dynamics. HCF-1 (Host Cell Factor 1), a conserved transcriptional co-regulator, has been implicated in cell cycle progression, liver metabolism, and regeneration. Loss of hepatocyte-specific HCF-1 in mice leads to spontaneous NAFLD, which rapidly exacerbates to NASH and compromises liver regeneration.

Biophysical and molecular characterization of HuR inhibitors, CMLD-2 and Dihydrotanshinone I (DHTS), in Triple Negative Breast Cancer (TNBC).

In the present study, we explored the oncogenic role of Human Antigen R (HuR), a post-transcriptional regulator implicated in cancer progression, metastasis, and therapy resistance. The present study evaluates the specificities and efficacies of two HuR inhibitors - CMLD2 and DHTS in silico and in vitro, in TNBCs. Apart from in-depth biophysical analysis, the cytotoxic effect of CMLD2 and DHTS was compared on the proliferation of TNBC cell lines [human: MDA-MB-231 & MDA-MB-468] and the 4T1[murine].

Synergistic Mn-Cr Co-doping in NaV(PO)OF Promising Cathode: Unlocking Superior Performance for Next-Generation Sodium-Ion Batteries.

Sodium vanadium fluorophosphate (NaVO(PO)F, NVOPF), with a NASICON framework, is a promising cathode material due to its robust 3D structure, high operating potential (∼3.8 V), and theoretical energy density (≈494 Wh kg). However, its commercial viability is limited by low electronic conductivity and a reduced practical energy density.

A comprehensive targeted panel of 295 genes: Unveiling key disease initiating and transformative biomarkers in multiple myeloma.

Background: Multiple myeloma (MM) is a hematological malignancy that progresses from a benign precursor stage known as Monoclonal Gammopathy of Undetermined Significance (MGUS). Distinguishing MM from MGUS at the molecular level by identifying key biomarkers, genomic alterations, and gene interactions is critical for early detection and deeper insight into MM pathogenesis.

Methods: We have developed an advanced genomics domain-rooted AI-workflow that combines the traditional statistical mutation profiling methods with the proposed BIO-DGI (Bio-Inspired Graph Network Learning-based Gene-Gene Interaction) attention-based deep learning architecture exploiting gene-gene interaction.

Maternal health education and social support needs across the perinatal continuum of care: a thematic analysis of interviews with postpartum women in Punjab, India.

Background: Perinatal social support and maternal education throughout the antenatal, childbirth, and postpartum phases contribute to the optimization of health and well-being of mothers and infants. Understanding deficits among support and educational resources can contribute to improved public health decision-making and maternal and child healthcare and wellbeing. This study aimed to explore health and social experiences and resources to characterize and unmet needs across the perinatal period.

CPPsite3: An updated large repository of experimentally validated cell-penetrating peptides.

Over the past two decades, cell-penetrating peptides (CPPs) have emerged as key intracellular drug delivery vehicles. This review provides a systematic overview of advancements in CPP research, encompassing both experimental techniques and computational resources crucial for their discovery. Our primary focus is on CPPsite3, a meticulously curated repository that currently houses 6788 entries, representing 4285 unique CPPs.

Effectiveness of Kushal Maa, a group-based mhealth interactive education and social support intervention for maternal and neonatal health outcomes: study protocol for a multisite randomised controlled trial in India.

Introduction: Perinatal care continuity across the full continuum is essential for optimising maternal and infant health; however, a stark gap occurs post partum, with less than one half of Indian mothers receiving postpartum care due to significant logistical and sociocultural barriers, particularly for periurban and rural residents. To overcome these barriers and reduce women's postpartum isolation, our international team of maternal and infant health clinicians and researchers developed and pilot-tested a culturally-tailored mobile interactive education and support group intervention, ), confirming feasibility and acceptability and preliminary effectiveness. The current study seeks to estimate the effectiveness of the intervention compared with standard care on maternal and neonatal health-related behaviours and health, characterise the mechanisms of intervention impact and evaluate the cost-effectiveness of the intervention in improving postpartum maternal and neonatal health compared with the standard of care.

Preliminary Effectiveness of a Postnatal mHealth and Virtual Social Support Intervention on Newborn and Infant Health and Feeding Practices in Punjab, India: Quasi-Experimental Pre-Post Pilot Study.

Background: We evaluated a pilot mobile health (mHealth) intervention aimed at improving postnatal maternal and infant health. The intervention featured provider-led group sessions for education, health care communication, in-person care referrals, and virtual mHealth support for postpartum mothers through weekly calls, texts, interactive voice response (IVR), and a phone app.

Objective: We aimed to assess the preliminary effectiveness of the pilot mHealth intervention, MeSSSSage (Maa Shishu Swasthya Sahayak Samooh, which means maternal and child health support group), on infant health knowledge, behaviors, and outcomes at 6 months post partum.

Ser/Thr phosphorylation of type II RelK toxin by PknK destabilizes TA interaction and interferes with toxin neutralization.

Unlabelled: Toxin-antitoxin (TA) modules represent genetic elements implicated in bacterial persistence. encodes 90+ TA modules, the majority of which are type II, comprising of a toxin component and an antitoxin counterpart that neutralizes the toxin. Under stressful environments, the antitoxin is degraded, releasing the toxin which then acts to halt cellular growth.

Artificial intelligence approaches for tumor phenotype stratification from single-cell transcriptomic data.

Single-cell RNA-sequencing (scRNA-seq) coupled with robust computational analysis facilitates the characterization of phenotypic heterogeneity within tumors. Current scRNA-seq analysis pipelines are capable of identifying a myriad of malignant and non-malignant cell subtypes from single-cell profiling of tumors. However, given the extent of intra-tumoral heterogeneity, it is challenging to assess the risk associated with individual cell subpopulations, primarily due to the complexity of the cancer phenotype space and the lack of clinical annotations associated with tumor scRNA-seq studies.

CytoLNCpred-a computational method for predicting cytoplasm associated long non-coding RNAs in 15 cell-lines.

The function of long non-coding RNA (lncRNA) is largely determined by its specific location within a cell. Previous methods have used noisy datasets, including mRNA transcripts in tools intended for lncRNAs, and excluded lncRNAs lacking significant differential localization between the cytoplasm and nucleus. In order to overcome these shortcomings, a method has been developed for predicting cytoplasm-associated lncRNAs in 15 human cell-lines, identifying which lncRNAs are more abundant in the cytoplasm compared to the nucleus.

A pilot study to evaluate the feasibility and acceptability of a mobile phone counselling intervention for perinatal women living with HIV and depression in India.

Pregnant and postpartum women living with Human Immunodeficiency Virus (HIV) are at high risk for perinatal depression, which can significantly undermine HIV care engagement and treatment outcomes. Despite this, depression often remains unidentified and untreated. This pilot study evaluated the feasibility, fidelity, acceptability and preliminary effects of a mobile phone counselling intervention among perinatal women living with HIV and depression in India.

Clinico-genomic study reveals association of dengue virus genome high frequency mutations with dengue disease severity.

Transmission of the dengue virus (DENV) places a huge burden on public health in several endemic regions. Like other RNA viruses, mutations in the DENV genome greatly governs its virulence, transmissibility, and interaction with the host immune system. Present study focuses on integrated analysis of mutation and clinical data accompanied at the onset of dengue fever.