Discovery of Personalized Medicine and Nutrition Approaches for improved Disease Management with the Human Phenotype Project

The group of Professor Eran Segal is a multi-disciplinary team of data scientists, biologists, experimental scientists, medical doctors, and nutritionists working in the area of Computational and Systems biology. The group’s research focuses on Genomics, Proteomics, microbiome, Immune System, Gene Regulation and Nutrition, and their effect on health, disease and aging. The overarching goal of the group is to develop personalized medicine and personalized nutrition using machine learning, computational biology, and analysis of heterogeneous high-throughput omics and clinical data. 

The Human Phenotype Project: In 2018, the group of Prof. Segal initiated the human phenotype project (https://humanphenotypeproject.org) in Israel, a large-scale prospective longitudinal cohort and biobank, aimed at developing prediction models for disease onset and progression and identification of novel molecular markers with a diagnostic, prognostic and therapeutic value. To date the cohort consists of >13,000 individuals recruited ages 40-70 year. Each participant undergoes biannual deep profiling of diverse modalities including imaging (e.g., liver and cardiac ultrasound), time-series (e.g., ECG, CGM), multi-omics (e.g., transcriptome, metabolome, genetics, proteomics), tabular (blood tests: ALT, AST, lipids and extensive hormone profiling), and questionnaire and APP data types (e.g., sleep monitoring, nutrition, lifestyle, medical history, medication changes, and lifestyle factors). Initially focused on Israeli participants, the HPP leverages Israel’s diverse population for broad applicability, with findings validated in other cohorts (Lifelines, UKBiobank, Metacardis). In 2025, HPP expanded to Japan and the UAE, increasing diversity. The HPP also includes 12 disease cohorts with 1,700 patients covering conditions like diabetes, heart disease, and fatty liver. The cohort includes many common disease states such as hypertension, prediabetes and hyperlipidemia, migraine, gynecological, gastrointestinal disorders and longitudinal data of new incidences of disease. 

Analyses of the HPP data thus far have provided novel insights into potential drivers of obesity, diabetes, and heart disease, and identified hundreds of novel markers at the microbiome, metabolite, and immune system level. For example, using the continuous glucose monitor (CGM) data that we collected, we showed that plasma fasting glucose levels that are commonly used to diagnose prediabetes and diabetes result in misclassification due to substantial intrapersonal variability that exists and revealed by the CGM (Shilo et al., Nature Medicine 2023). We also unraveled novel human genetic associations with traits that were not previously studied (Levine et al., Med 2024). In other work, we used the HPP to study human aging. We devised machine learning models of chronological age and computed biological aging scores that represent diverse physiological systems and revealed different aging patterns among sexes (Reicher et al., Nature Aging, 2024). Finally, foundation AI models (Lusker et al., Nature 2025) that we developed provide novel representations of the diverse modalities that we measured on the cohort and achieve state-of-the-art performance in predicting future onset of disease and trajectories of disease risk factors.