Machine Learning for Medicine and Science


Open positions

The Zitnik Lab opened doors in December 2019!

Based in Harvard’s Department of Biomedical Informatics, we investigate applied machine learning with a current focus on large interconnected data in science and medicine—i.e., networks of interactions between entities like proteins, drugs, diseases, and patients. We leverage data at the scale of billions of interactions and invent new methods that blend machine learning with data science and statistics.

We use our methods to answer questions in biology, such as how Darwinian evolution changes molecular networks, and how data-driven algorithms can accelerate and automate scientific discovery. We use the methods to solve high-impact problems in medicine, such as what drugs and combinations of drugs are safe for patients, what molecules will treat what diseases, and how newborns are transferred between hospitals and how these transfers influence outcomes.

Our big bet for the future

Our world is interconnected, from the molecular level to the level of connections between diseases in a person, and all the way to the societal level encompassing human interactions within a society. These interactions at different levels give rise to a bewildering degree of complexity.

To disentangle the complexity, science inextricably relies on the existence of scientific instruments. While in the past science used physical instruments to facilitate the discoveries, modern science needs the new kind of instruments, which will, we postulate, in a vital way be optimized for learning and reasoning from networked data.

The overarching goal of our research is to develop the next generation of machine learning for data in medicine and science. Our research realizes an end-to-end scientific approach in which we:

  1. Invent ways to combine rich, heterogeneous data in their broadest sense to reduce redundancy and uncertainty and to make them amenable to comprehensive analyses.
  2. Develop methods for reasoning over rich, interconnected data, and design architectures for learning actionable representations.
  3. Translate machine learning research into innovative applications and solutions for burning biomedical questions.

Our research proves that this approach not only opens up new avenues for understanding nature, analyzing health, and developing new medicines to help people but can impact the way predictive modeling is performed today at the fundamental level.

Read about our research. . .

Latest News

Jul 2020:   Podcast on ML for Drug Development

Tune in to the podcast with Marinka about machine learning to drug development. The discussion focuses on open research questions in the field, including how to limit the search space of high-throughput screens, design drugs entirely from scratch, and identify likely side-effects of combining drugs in novel ways.

Jul 2020:   Postdoctoral Research Fellowship

We have a new opening for a postdoctoral research fellow in novel machine learning methods to combat COVID-19! Submit your application by September 1, 2020.

Jul 2020:   DeepPurpose Library

DeepPurpose is a deep learning library for drug-target interaction prediction and applications to drug repurposing and virtual screening.

Jun 2020:   Subgraph Neural Networks

Subgraph neural networks learn powerful subgraph representations that create fundamentally new opportunities for predictions beyond nodes, edges, and entire graphs.

Jun 2020:   Defense Against Adversarial Attacks

GNNGuard can defend graph neural networks against a variety of training-time attacks. Remarkably, GNNGuard can restore state-of-the-art performance of any GNN in the face of adversarial attacks.

Jun 2020:   Graph Meta Learning via Subgraphs

G-Meta is a meta-learning approach for graphs that quickly adapts to new prediction tasks using only a handful of data points. G-Meta works in most challenging, few-shot learning settings and scales to massive interactomics data as we show on our new Networks of Life dataset comprising of 1,840 networks.

May 2020:   The Open Graph Benchmark

A new paper introducing the Open Graph Benchmark, a diverse set of challenging and realistic benchmark datasets for graph machine learning.

May 2020:   Special Issue on AI for COVID-19

Marinka is co-editing a special issue of IEEE Big Data on AI for COVID-19. In light of the urgent need for data-driven solutions to mitigate the COVID-19 pandemic, the special issue will aim for a fast-track peer review.

May 2020:   Multiscale Interactome

May 2020:   Molecular Interaction Networks

A new preprint describing a graph neural network approach for the prediction of molecular interactions, including drug-drug, drug-target, protein-protein, and gene-disease interactions.

Apr 2020:   Submit to PhD Forum at ECML

The call for ECML-PKDD 2020 PhD Forum Track is now online. If you are a PhD student, submit your work on machine learning and knowledge discovery.

Apr 2020:   Drug Repurposing for COVID-19

We are excited to share our latest results on how networks and graph machine-learning help us search for a cure for COVID-19.

Mar 2020:   AI Cures

We are joining AI Cures initiative at MIT! We will develop machine learning methods for finding promising antiviral molecules for COVID-19 and other emerging pathogens.

Mar 2020:   COVID-19 Task Force

We are excited to be working with László Barabási and his amazing team of scientists as we search for a cure for COVID-19.

Mar 2020:   Graph ML Workshop at ICML 2020

We will co-organize a workshop on Graph Representation Learning and Beyond at ICML 2020. Submit your finest work!

Mar 2020:   Accepted Tutorial at IJCAI!

We will present a tutorial on Machine Learning for Drug Development at IJCAI 2020! Stay tuned for details.

Mar 2020:   Welcome New Students!

Haoxin, Michelle, and Xiang joined the lab. Welcome! We look forward to seeing you all in the lab!

Feb 2020:   Meta Learning for Single-cell Biology

A new preprint on meta learning for identifying and naming cell types, even cell types that have never been seen before and do not exist in the training data. Check it out!

Dec 2019:   Pre-training Graph Neural Networks

Dec 2019:   Deep Learning for Network Biology

Marinka is co-editing a special issue of ACM/IEEE TCBB on Deep learning and graph embeddings for network biology. Submit your finest work!

Zitnik Lab  ·  Harvard  ·  Department of Biomedical Informatics