Marinka Zitnik
Marinka Zitnik, PhD
Assistant Professor of Biomedical Informatics, Harvard Medical School

Marinka Zitnik investigates machine learning for science and medicine. Her methods leverage biomedical data at the scale of billions of interactions among millions of entities, blend machine learning with statistics and data science, and infuse biomedical knowledge into deep learning. Problems she investigates are motivated by network biology and medicine, genomics, drug discovery, and health.

Dr. Zitnik's research vision is that in the future data science and artificial intelligence will be routinely used to give clinicians diagnostic recommendations; give scientists testable hypotheses they can confirm experimentally and offer them insights into safe and precise treatments; and give patients guidance on self-care, e.g., how to lead a healthy lifestyle and recognize disease early. To realize this vision, Dr. Zitnik develops methods to reason over rich interconnected data and translates the methods into solutions for biomedical problems.

Before joining Harvard, Dr. Zitnik was a postdoctoral fellow in Computer Science at Stanford University and was involved in projects at Chan Zuckerberg Biohub. She received her Ph.D. in Computer Science from University of Ljubljana while also researching at Imperial College London, University of Toronto, Baylor College of Medicine, and Stanford University. 

DBMI Research Areas
Current Postdoctoral Fellowship Opportunities
Leveraging the Cell Ontology to classify unseen cell types.
Authors: Wang S, Pisco AO, McGeever A, Brbic M, Zitnik M, Darmanis S, Leskovec J, Karkanias J, Altman RB.
Nat Commun
View full abstract on Pubmed
Quantifying the variation in neonatal transport referral patterns using network analysis.
Authors: Kunz SN, Helkey D, Zitnik M, Phibbs CS, Rigdon J, Zupancic JAF, Profit J.
J Perinatol
View full abstract on Pubmed
Network medicine framework for identifying drug-repurposing opportunities for COVID-19.
Authors: Morselli Gysi D, do Valle Í, Zitnik M, Ameli A, Gan X, Varol O, Ghiassian SD, Patten JJ, Davey RA, Loscalzo J, Barabási AL.
Proc Natl Acad Sci U S A
View full abstract on Pubmed
Multidose evaluation of 6,710 drug repurposing library identifies potent SARS-CoV-2 infection inhibitors In Vitro and In Vivo.
Authors: Patten JJ, Keiser PT, Gysi D, Menichetti G, Mori H, Donahue CJ, Gan X, Do Valle I, Geoghegan-Barek K, Anantpadma M, Berrigan JL, Jalloh S, Ayazika T, Wagner F, Zitnik M, Ayehunie S, Anderson D, Loscalzo J, Gummuluru S, Namchuk MN, Barabasi AL, Davey RA.
bioRxiv
View full abstract on Pubmed
DeepPurpose: a deep learning library for drug-target interaction prediction.
Authors: Huang K, Fu T, Glass LM, Zitnik M, Xiao C, Sun J.
Bioinformatics
View full abstract on Pubmed
Identification of disease treatment mechanisms through the multiscale interactome.
Authors: Ruiz C, Zitnik M, Leskovec J.
Nat Commun
View full abstract on Pubmed
Contrastive Learning Improves Critical Event Prediction in COVID-19 Patients.
Authors: Wanyan T, Honarvar H, Jaladanki SK, Zang C, Naik N, Somani S, Freitas JK, Paranjpe I, Vaid A, Miotto R, Nadkarni GN, Zitnik M, Wang F, Ding Y, Glicksberg BS.
ArXiv
View full abstract on Pubmed
SkipGNN: predicting molecular interactions with skip-graph networks.
Authors: Huang K, Xiao C, Glass LM, Zitnik M, Sun J.
Sci Rep
View full abstract on Pubmed
MARS: discovering novel cell types across heterogeneous single-cell experiments.
Authors: Brbic M, Zitnik M, Wang S, Pisco AO, Altman RB, Darmanis S, Leskovec J.
Nat Methods
View full abstract on Pubmed
Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19.
Authors: Gysi DM, Do Valle Í, Zitnik M, Ameli A, Gan X, Varol O, Sanchez H, Baron RM, Ghiassian D, Loscalzo J, Barabási AL.
ArXiv
View full abstract on Pubmed