Postdoctoral Positions in the Lab of Marinka Zitnik
Areas of Focus
- Artificial Intelligence for Cancer Drug Discovery
- Representation learning and embeddings for biomedical networks and knowledge graphs
Artificial Intelligence for Cancer Drug Discovery
Prof. Marinka Zitnik invites applications for a Postdoctoral Research Fellowship position at Harvard University. The fellow will lead the design, development, and implementation of novel AI methods for the analysis of clinical and biomarker data in oncology.
Immuno-oncology therapies are revolutionary in the treatment of cancer. However, there is much that is not understood about the drivers of efficacy, response, and resistance. The fellow will develop novel approaches in deep learning, graph AI, and transfer learning that will have multiple applications, including cancer biomarker discovery, target identification, selection of drug combination partners, patient enrichment, and disease characterization.
Harvard offers an exceedingly rich environment for education and career development, with opportunities for collaboration and learning not only within the Harvard Medical School but also at many other Harvard schools, institutes, and centers.
Additionally, the fellow will benefit from close collaboration and mentorship by Roche computational and biomarker scientists through the “Roche Access to Distinguished Scientists Programme”. Roche is the world’s largest biotech company and has over 20 immunotherapy molecules in development. This collaboration opens the door to applying newly developed methods to patient data from ongoing clinical trials. Our vision is to combine machine learning research with unique clinical data assets to generate novel insights ensuring the right treatment for the right patient at the right time.
We seek highly-motivated applicants with background in one or more of the following areas: deep learning, computational biology, therapeutic science, cancer data science, and network science. Successful applicants will be critical thinkers and problem solvers with the drive and demonstrated ability to translate ideas to action and complete projects effectively.
Applicants must possess a PhD degree or equivalent or be nearing the date of their thesis defense in computational biology, biomedical informatics, computer science, statistics or a closely related field. Strong programming skills and experience with deep learning frameworks and its biomedical applications are required.
We value diligence, ingenuity, initiative, collegiality, and integrity. We are looking for applicants with demonstrably strong research skills, ideally, with multiple publications in top venues in data science, machine learning and computational biology. Strong analytical and oral communication skills and an ability to work both independently and as a cooperative member of a team are required. While accomplished candidates with expertise in various aspects of biomedical AI will be considered, those with a background in cancer data science or therapeutic science are especially encouraged to apply. A competitive salary and excellent benefits package are available.
The position is available immediately and can be renewed annually. Interested applicants should submit the following documents via email to Prof. Zitnik and use the subject line “Postdoctoral Fellowship in AI for Cancer Drug Discovery”:
- Cover letter describing your interest in the position, relevant experience, and career goals
- Curriculum Vitae (include link to your academic webpage and links to software you developed)
- Two representative publications (e.g., published or unpublished manuscripts)
- Names and email addresses of three references
We are currently reviewing applications for this position. Interested candidates are encouraged to submit their applications as soon as possible.
Faculty and mentors
Dr. Marinka Zitnik is an Assistant Professor at Harvard with appointments in the Department of Biomedical Informatics, Broad Institute of MIT and Harvard, and Harvard Data Science. Dr. Zitnik has published extensively in top ML venues and leading scientific journals. She has organized conferences and workshops in graph representation learning, drug discovery, and precision medicine at leading conferences (NeurIPS, ICLR, ICML, ISMB, AAAI, WWW), where she is also on the organizing committees. She is an ELLIS Scholar in the European Laboratory for Learning and Intelligent Systems (ELLIS) Society and a member of the Science Working Group at NASA Space Biology. Her research won paper and research awards from the International Society for Computational Biology, Bayer Early Excellence in Science, Amazon Faculty Research, Roche Alliance with Distinguished Scientists, Rising Star Award in Electrical Engineering and Computer Science, and Next Generation in Biomedicine Recognition, being the only young scientist with such recognition in both EECS and Biomedicine. She co-founded Therapeutics Data Commons and the AI for Science initiatives. Dr. Zitnik is the recipient of the 2022 Young Mentor Award at Harvard Medical School—this most prestigious award acknowledges her mentorship of the next generation of scientists who conduct research on artificial intelligence and biology.
Dr. Daniel Marbach, a computational biologist and Principal Scientist Bioinformatics at Roche, will serve as mentor for the fellow, together with his team of scientists. Dr. Marbach has long been engaged in open science collaborations involving academia and industry as an organizer of multiple DREAM Challenges, which included hundreds of participating teams and were published in leading journals. Dr. Marbach is an expert in computational network biology and advanced analytics in drug discovery.
Harvard is an Equal Opportunity/Affirmative Action Employer. Women and minorities are especially encouraged to apply.
Representation learning and embeddings for biomedical networks and knowledge graphs
The Department of Biomedical Informatics (DBMI) at Harvard Medical School and the Zitnik Lab are looking for a Postdoctoral Fellow for research in novel biomedical machine learning and data science methods. Biomedical data involve rich interactions that span from the molecular level to the level of connections between diseases in a patient and to the societal level encompassing all human interactions. These interactions at different levels give rise to a bewildering degree of complexity, which is only likely to be fully understood through data-driven and computationally enabled study. We are investigating machine learning for biomedical sciences, focusing on new methods for learning and reasoning over rich interaction data and on translation of these methods into solutions for biomedical problems. This scientific approach not only opens up new avenues for understanding nature, analyzing health, and developing medicines to help people but can impact on the way predictive modeling is performed today at the fundamental level.
Among others, possible research projects include:
- Representation learning for biomedicine in an effort to set sights on new frontiers in genomics, drug discovery, and precision health beyond classic applications of neural networks on image and sequence data.
- Network embedding methods in an effort to bridge the divide between basic science and patient data.
- Fusion of diverse data into knowledge graphs in an effort to combine biomedical data in their broadest sense to reduce redundancy and uncertainty and make them amenable to analyses.
- Next-generation algorithms for networks, focusing on large networks of interactions between biomedical entities and their applications to network biology and medicine.
- Contextually adaptive AI in an effort to advance algorithms to train more with less data and reason about never-before-seen phenomena as algorithms encounter new patients, diseases, or cell types.
We seek a highly-motivated candidate with strong research skills and background in machine learning and/or applications in bioinformatics and computational medicine. Candidates must have a Ph.D. or equivalent degree in a field relevant to biomedical data science, such as computer science, statistics, engineering, biomedical informatics or computational biology. Strong programming skills and experience with large-scale data analysis and deep learning frameworks are a plus.
The position is available immediately and can be renewed annually.
How to apply
Submit your application with a letter indicating your research interests and experience, a CV, names and email addresses of 2-3 references, and copies of two representative publications via email to firstname.lastname@example.org. We encourage applicants also to include links to any software they have developed.
Harvard Medical School is an Equal Opportunity/Affirmative Action Employer. Women and minorities are especially encouraged to apply.