Theofanis Karaletsos

Theofanis Karaletsos
Rätsch Research Group; Postdoc
Room: Z-695
Tel: +1 646 888 3394
Email: Theo mail
Mailing Address: MSKCC – Computational Biology Center
1275 York Avenue, Box # 357
New York, NY 10065
Express Mail/Street Address: Zuckerman Research Center
417 East 68th Street – 6th Floor (Z-677)
New York, NY 10065


Research Interests:

Theofanis worked on his PhD on generative models for biological images at the Max Planck Institute For Intelligent Systems supervised by Prof. Karsten Borgwardt and John Winn from Microsoft Research Cambridge. Theofanis’ research interests revolve around probabilistic generative latent variable models for structured data. Particular domains of application are: images, such as biological and pathology images; healthcare data, such as electronic healthcare records, clinical text and corresponding time-series. With respect to these subjects, Theofanis is interested in specifying interpretable models describing complex datasets and evaluating them quantitatively in terms of either biological or information theoretical quantities. Further interests are computational vision and natural image statistics, models of cancer evolution and models of text.

Selected Publications:

Journal Papers:

  1. T Karaletsos, O Stegle, C Dreyer, J Winn, K Borgwardt. ShapePheno: unsupervised extraction of shape phenotypes from biological image collections. Oxford University Press Bioinformatics. 2012

Workshop Papers:

  1. T Karaletsos, X Lou, K R Chan, C Crosbie, G Rätsch. Towards an integrated dynamic model of temporal structure of clinical text notes and interactions with genetic profiles. Extended abstract, NIPS Workshop on Machine Learning for Clinical Data Analysis in Healthcare. 2013.
  2. K R Chan, X Lou, T Karaletsos, C Crosbie, S Gardos, D Artz, G Rätsch. An Empricial Analysis of Topic Modeling for Mining Cancer Notes. ICDM Biological Data Mining and its Applications in Healthcare (ICDM-BioDM). 2013.
  3. T Karaletsos, O Stegle, J Winn, K Borgwardt. JigPheno: Semantic Feature Extraction In Biological Images.  Extended abstract (oral), NIPS Workshop on Machine Learning for Computational biology. 2010.

Working Papers:

  1. T Karaletsos, O Stegle, C Dreyer, J Winn, K Borgwardt. Inferring Visual Phenotypes For Genome-Wide Association Studies With Generative Image Models
  2. T Karaletsos, A. Fitzgibbon, J Winn. Learning Factor Graphs With Pointwise Mixture Models Applied to Generative Image Modeling.