Alex A. Zhavoronkov

The paper introduces LongevityBench, a benchmark to evaluate LLMs' ability to understand aging biology and predict age-related outcomes from biodata.

This paper introduces a platform for disease-specific target identification using multi-omics data and evaluates models with a benchmarking system to improve drug development efficiency.

The paper introduces Longevity-LLM, a foundation model fine-tuned on aging-related data, achieving high performance in age prediction and proteomic profile generation across multiple modalities.

This study identifies polyploid cardiomyocytes as disease-specific transcriptional states in the mammalian heart and suggests targeting them for heart failure treatment.

The paper uses AI and causal genetics to identify shared therapeutic targets for aging and 12 age-related diseases across four disease areas.

The paper develops an AI-driven toolset to study IPF and aging, showing IPF as a dysregulation of aging processes rather than just accelerated aging.

The paper maps the proteostasis network of membraneless organelles, revealing the role of anabolic components and molecular chaperones in regulating protein conformations.

DORA AI Scientist automates scientific research tasks and report generation using multi-agent AI systems and LLMs, reducing manuscript preparation time and enabling more focus on discovery.

This paper uses computational methods to design a multi-serotype Dengue virus vaccine by predicting epitopes and validating safety, offering a novel approach for broad-spectrum immunity.

This study compares endoxifen, tamoxifen, and fulvestrant using omics data to identify their distinct mechanisms of action in breast cancer, revealing differences in pathway effects and potential therapeutic implications.

This paper introduces P3GPT, a multimodal transformer model for aging research and drug discovery that performs multiple tasks across species, tissues, and omics data.

The paper develops a deep learning model to predict human biological age from gut microbiome data and identifies key microbial biomarkers associated with aging.

The paper develops a deep-learned age predictor from transcriptomic data and shows that batch effects can obscure age-related changes.

The paper develops a deep learning pipeline to predict clinical trial outcomes using transcriptomic data, achieving 83% cross-validated accuracy and outperforming gene-based classifiers.