Biomedical Data Science Lab
Computational Biology & Precision Medicine
We develop computational methods for biomedical data analysis — from single-cell transcriptomics and tumor microenvironment characterization to machine learning for clinical decision-making.
Technion – Israel Institute of Technology
Research Areas
Our work spans computational biology, immunology, and clinical AI
Computational Methods for Cellular Heterogeneity
We develop computational tools that characterize cellular heterogeneity across data modalities and scales. From deconvolving bulk tissue data (xCell, xCell 2.0) to annotating single-cell transcriptomes (SingleR, CellMentor) and exploring spatial tissue organization (Gaudi), our methods are used by tens of thousands of researchers worldwide to extract biological insights from complex genomic data.
Cellular Dynamics in Health & Disease
We apply single-cell RNA sequencing and spatial transcriptomics to understand how cells behave and interact in disease contexts. Using our in-house biology lab equipped with a 10x Genomics Chromium system, we profile fresh surgical samples to map tumor microenvironment changes during immunotherapy, investigate metastatic dissemination, and characterize neuroimmunological responses.
Clinical Decision-Making through AI
We develop machine learning frameworks that translate computational insights into clinical applications — from transformer-based models for electronic health records and LLM-powered neurological assessment tools to real-world evidence studies that have informed treatment guidelines in oncology, immunotherapy, and public health.
xCell
Cell type enrichment analysis from gene expression data for 64 immune and stromal cell types.
20,000+ users worldwide
xCell 2.0
Next-generation robust algorithm for cell type proportion estimation. Predicts response to immune checkpoint blockade.
SingleR
Reference-based single-cell RNA-seq cell type annotation using pure transcriptomic data.
10,000+ users worldwide
Featured Publications
Highlights from our 63+ published papers
Deep Learning on Histopathological Images to Predict Breast Cancer Recurrence Risk and Chemotherapy Benefit
G Shamai, S Cohen, Y Binenbaum et al.
View paper →CellMentor: Cell-Type Aware Dimensionality Reduction for Single-cell RNA-Sequencing Data
O Hevdeli, E Petrenko, D Aran
View paper →xCell 2.0: Robust Algorithm for Cell Type Proportion Estimation Predicts Response to Immune Checkpoint Blockade
A Angel, L Naom, S Nabet-Levy et al.
View paper →Recent News
Latest updates from the lab
Dvir Aran promoted to Associate Professor with tenure
New paper in Lancet Oncology on deep learning for breast cancer recurrence prediction
Almog Angel wins Faculty Best Paper Award for xCell 2.0
Join Our Team
We're looking for motivated PhD students, MSc students, and postdoctoral researchers with backgrounds in bioinformatics, computational biology, or machine learning.
Learn More