Machine Learning for Health: Learning to understand human disease

Machine learning is revolutionizing our understanding of many human health problems from obesity to cancer. With ever increasing amount of data coming from this domain, computational biology and medicine are also transforming the machine learning community by not only providing new applications but also inspiring new modeling frameworks and learning paradigms.

The goal of this workshop is to bring together machine learning scientists and computational biologists. We would like to showcase recent advances in this field and discuss challenges in computational methodology and biomedical application.

Call for submissions


Relevant submission topics include (but are not limited to):


Please submit one page summary plus references via Accepted submissions will be presented as contributed talks or posters.

Important Dates:

Keynote Speakers

Confirmed speakers include:

Olga Troyanskaya Princeton University
Laxmi Parida IBM Research
Itsik Pe'er Columbia University
Gunnar Rätsch ETH/MSKCC



Room: Enterprise I&II


08:50: Welcome and introduction
09:00: Inferring Past Demography from Shared Genomic Segments abstract Keynote: Itsik Pe'er
09:50: Using a Data-Driven Bayesian Approach to Predict the Targets of Small Molecules Neel S. Madhukar, Prashant Khade, Linda Huang, Kaitlyn Gayvert, Giuseppe Galleti, Martin Stogniew, Josh Allen, Paraskevi Giannakakou, Olivier Elemento
10:20: Coffee break
10:50: Deep Temporal Generative Models of EHR Data Rahul G. Krishnan, Uri Shalit, David Sontag
11:20: Drugs, Patients and Mutations: Data Science Approaches for Oncology Keynote: Gunnar Rätsch
12:10 Lunch break
14:10: Integrative machine learning for data-driven understanding of complex human disease abstract Keynote: Olga Troyanskaya
15:00: Poster spotlight session
15:30: Poster session
16:30: Watson for Genomics: a cognitive approach to clinical oncology abstract Keynote: Laxmi Parida
17:20 Why asking for miRNA-gene interactions is wrong: A new paradigm for miRNA target prediction with expression data Azim Dehghani Amirabad, Marcel H. Schulz
17:50 A deep learning ­based framework for cancer classification Feng Gao​, Xin Wang​
18:20: End



Parsing Wireless Electrocardiogram Signals with the CRF-CFG Model Thai Nguyen, Roy J. Adams, Annamalai Natarajan, Benjamin M. Marlin
Estimating Tolerated Genetic Variation in Gene Expression from Allelic Expression Data Pejman Mohammadi Stephane E. Castel, Heather E. Wheeler, Hae Kyung Im, GTEx Consortium, Tuuli Lappalainen
Probabilistic integration of multiple high-dimensional data sources in personalized cancer medicine Eemeli Leppäaho, Muhammad Ammad-ud-din, Suleiman A.Khan, Samuel Kaski
Diagnostic Prediction Using Discomfort Drawing with Multimodal Topic Model Cheng Zhang, Hedvig Kjellström, Bo C. Bertilson
Disease state prediction, knowledge representation, and heterogeneity decomposition for ALS Jonathan Gordon, Boaz Lerner
Cancelled A “moneyball” approach to predicting clinical trial toxicity events Kaitlyn Gayvert, Neel Madukhar, Olivier Elemento



Machine Learning for Health is hosted in conjunction with UAI 2016 at the Westin Jersey City Newport Hotel (located across the Hudson river from Manhattan) on June 29, 2016.


Ke Yuan is a Lecturer at School of Computing Science at University of Glasgow. He received MSc and PhD in Electronic/Electrical Engineering and Machine Learning from University of Southampton in 2008 and 2013. From 09/2012 to 04/2016, He was a postdoctoral fellow in the Cancer Research UK Cambridge Institute at University of Cambridge. He joins University of Glasgow in 05/2016.

Pejman Mohammadi is a postdoctoral fellow at New York Genome Center (NYGC), and Columbia University Medical Center. He received his Masters in computer science and bioinformatics from Aalto University in Helsinki in 2010, and his PhD from the department of biosystems science and engineering at ETH Zurich in 2014. Since 2015, he is a postdoctoral fellow at the functional genomics lab lead by Tuuli Lappalainen at NYGC.

Olivier Elemento is an Associate Professor at Weill Cornell Medicine, Associate Director of the Institute for Computational Biomedicine and Head of the Laboratory of Cancer Systems Biology. He holds a PhD in Computational Biology from CNRS/University of Montpellier. From 2003 to 2008, he was a postdoctoral research associate at the Lewis-Sigler Institute for Integrative Genomics at Princeton University. He joined the Weill Cornell Medicine in 2008.

Edoardo M Airoldi is an Associate Professor of Statistics at Harvard University. He received a Ph.D. from Carnegie Mellon University in 2007, Till December 2008, He was a postdoctoral fellow in the Lewis-Sigler Institute for Integrative Genomics and the Department of Computer Science at Princeton University working with Olga Troyanskaya and David Botstein. He joined the Statistics Department at Harvard University in 2009.

Florian Markowetz is a Senior Group Leader at the CRUK Cambridge Institute at the University of Cambridge. He holds degrees in Mathematics and Philosophy from University of Heidelberg and a PhD in Computational Biology from Free University Berlin. He was affiliated with the German Cancer Research Center (DKFZ) in Heidelberg and the Max Planck Institute for Molecular Genetics in Berlin. The Max Planck Society honoured his PhD thesis with an Otto-Hahn medal. He pursued postdoctoral research at Princeton University at the Lewis-Sigler Institute for Integrative Genomics. Since 01/2009 he is a group leader at the CRUK Cambridge Institute at the University of Cambridge. In 2014 he was promoted to tenured senior group leader.

Important Dates

  • Deadline: Extended to May 15
  • Notification: May 20
  • Workshop: June 29


Room: Enterprise I&II

The Conference on Uncertainty in Artificial Intelligence (UAI) 2016

Westin Jersey City Newport Hotel
New York City, NY, USA


Ke Yuan