Sarvesh Nikumbh
- __Open to work__ - Machine Learning, Data Science and/or Computational Biology roles
- Ex-MSD (Merck Sharp & Dohme), Visiting Researcher@Imperial College London & MRC LMS
- firstname [dot] lastname [at] gmail [dot] com (_remove spaces_)
Hi there, I am Sarvesh. I am a machine learning and data science researcher with ~15 years interdisciplinary research experience. I enjoy developing and applying interpretable and scalable machine learning methods to solve problems in diverse domains. So far I have worked in NLP and biology/health.
Most recently, I was a Senior Research Scientist at MSD (Merck Sharp & Dohme) in the UK where I worked closely with neuroscientists on target identification, and on various other computational/data sciency aspects of the drug discovery pipeline. Before that I was a Postdoctoral Research Scientist at the Institute of Clinical Sciences, Faculty of Medicine, Imperial College London and MRC Laboratory of Medical Sciences (MRC LMS).
As a computational biologist, my general research interests are in machine learning methods, their interpretability and using them as tools towards understanding cellular biology better, more specifically, the regulatory aspects of the genome. Almost always, the choice of method and approach is governed by the roblem at hand.
I did my PhD in Machine Learning and Computational Biology at the Max Planck Institute for Informatics (MPI-INF) and Saarland University, Saarbrücken, Germany. My doctoral thesis was titled “Interpretable machine learning methods for prediction and analysis of genome regulation in 3D”.
Upcoming Events
Recent News
Selected Publications[Top]
- Identification of transcription factor co-binding patterns with non-negative matrix factorization, Nucleic Acids Research. Ieva Rauluseviciute, Timothée Launay, Guido Barzaghi, Sarvesh Nikumbh, Boris Lenhard, Arnaud Regis Krebs, Jaime A Castro-Mondragon, Anthony Mathelier
- Core promoterome of barley embryo, Computational and Structural Biotechnology Journal. Simon Pavlu, Sarvesh Nikumbh, Martin Kovacik, Tadaichi An, Boris Lenhard, Hana Simkova, Pavla Navratilova
- Identifying promoter sequence architectures via a chunking-based algorithm using non-negative matrix factorisation, PLoS Computational Biology. [code] Sarvesh Nikumbh and Boris Lenhard
- All Fingers Are Not the Same: Handling Variable-Length Sequences in a Discriminative Setting Using Conformal Multi-Instance Kernels, Proceedings of the 17th International Workshop on Algorithms in Bioinformatics (WABI 2017). Sarvesh Nikumbh, Peter Ebert and Nico Pfeifer
- Genetic sequence-based prediction of long-range chromatin interactions suggests a potential role of short tandem repeat sequences in genome organization, BMC Bioinformatics. Sarvesh Nikumbh and Nico Pfeifer
Academic Degrees
-
Ph.D. (Machine Learning & Computational Biology)
Year(s): 2013–2019
Institution: MPI for Informatics, Germany
Thesis title: Interpretable Machine Learning Methods for Prediction and Analysis of Genome Regulation in 3D
-
M.Tech. (Mathematical Modeling and Simulation)
Year(s): 2010–2012
Institution: Centre for Modeling and Simulation, Savitribai Phule Pune University
Thesis title: Classification of Promoters by Chromatin Features
-
B.E. (Computer Engineering)
Year(s): 2004–2008
Institution: St. Francis Institute of Technology, Mumbai University
Thesis title: <a href="https://arxiv.org/abs/1109.6838" target="_blank">Distributed Air Traffic Control: A Human Safety Perspective</a>
Awards & Honors
- IMPRS-CS PhD Fellowship, MPI for Informatics, 2013
- Microsoft Research India Travel Grant, 2012
- Indian Association for Research in Computing Science (IARCS) Travel Grant, 2012
- Travel award by Dept. of Biotechnology, Govt. of India (Declined), 2012
- Travel grant for 19th Machine Learning Summer School in La Palma, Spain, 2012
-
French Government Scholarship,
2011
Awarded by the French Ministry of Foreign Affairs for pursuing a summer internship at INRIA Grenoble