van Dijk Lab @Yale

Computational Biology & Machine Learning
@Yale Medical School


Our Research

The mission of our lab is to provide machine learning tools that extract meaningful insight from high-throughput, high-dimensional biomedical data. We work with data such as: Single-Cell RNA sequencing, Gut microbiome sequencing, Biomedical imaging, and Electronic Health Records. We are part of Internal Medicine (Cardiology) as well as Computer Science, and are located in the Cardiovascular Research Center on the 7th floor of 300 George st.

Selected publications

Selected Projects



(Markov Affinity-based Graph Imputation of Cells)

Imputation and denoising of single-cell RNA-seq data using manifold learning. van Dijk, et al. Cell, 2018


Screen Shot 2019-04-08 at 9.49.31 AM.png

(Potential of Heat-diffusion for Affinity-based Transition Embedding)

Embedding high-dimensional data into low dimensions for visualization. link (in press at Nature. Biotech)


(Manifold Enhancement of Latent Dimensions)

Graph signal processing tool to analyze multiple scRNA-seq samples from two or more conditions. link (bioRxiv)

PET/CT scans


We’re developing tools to visualize, extract features, and predict clinical phenotypes in PET, SPECT, CT, ultrasound, and various other medical imaging data for large patient cohorts.


We use machine learning to accelerate biomedical discovery


We are recruiting at all levels

Are you excited about machine learning and do you want to make an impact in biology and medicine? The van Dijk Lab is recruiting interns, students, postdocs, programmers, and staff researchers. Background in CS, Math, or Engineering is preferred, no background in biology is required. You should be interested in working with real world data and interested in either developing new algorithms or applying existing ones to data, or both!

The van Dijk lab is part of Yale Internal Medicine (Cardiology) as well as Computer Science. We are located at the Yale Medical School, which allows us to work closely with clinicians and have access to the most exciting datasets. Our goal is to impact both biomedicine (e.g. publish in biological and medical journals) and computer science (e.g. publish at CS and Math conferences).

For more information, send an email to: david.vandijk (at)


Excited about Machine Learning and Biomedicine?

Join our Lab