David Dao
Grad. Researcher at Broad Institute of MIT & Harvard
daviddao at broad.mit.edu
"I am interested in machine learning (especially deep learning) and its applications, including bioinformatics, computer vision, natural language understanding and information retrieval"
Picture

Grad. Researcher at Broad Institute of MIT and Harvard

Fall 2015

Deep Learning for high dimensional image-based data and cell profiling

Google Summer of Code Fellowship

Summer 2014

Coding on Interactive Data Visualization for the Web

Technical University of Munich: Master's Degree in Computer Science

Since 2014

Major in Computer Science. Focus on Machine Learning, Bioinformatics, and Computer Vision

Picture

Researcher at Heidelberg Institute for Theoretical Studies

2014 - 2015

Pattern Recognition in Computational Molecular Evolution

Location

Karlsruhe Institute of Technology: Bachelor's Degree in Computer Science

2010 - 2014

Major in Computer Science and Minor in Physics. Focus on AI, Machine Translation, and Machine Learning

Picture

62nd Lindau Nobel Laureate Forum Participant

Summer 2012

Meeting and discussion with Nobel Laureates in Physics

Visiting Student at CERN

Fall 2010

Machine Learning and Pattern Recognition in Particle Physics


Publications

Automated Plausibility Analysis of Large Phylogenies
Here, we develop an automated plausibility assessment approach and introduce the effective algorithm Plausibility-Check. We conducted experiments on simulated and real data sets using the STBase tree database that show that the overall running time of our algorithm on large phylogenies improves by five orders of magnitude compared to the naıve algorithm. Plausibility-Check is available as part of the RAxML open source code that is available for download at https://github.com/stamatak/standard-RAxML
D. Dao, T. Flouri, A. Stamatakis
Pattern Recognition in Computational Molecular Biology, Wiley & Sons, 2015
Anatomy of BioJS, an open source community for the life sciences
BioJS is an open source software project that develops visualization tools for different types of biological data. Here we report on the factors that influenced the growth of the BioJS user and developer community, and outline our strategy for building on this growth. The lessons we have learned on BioJS may also be relevant to other open source software projects
G. Yachdav, T. Goldberg, S. Wilzbach, D. Dao, I. Shih et al.
eLife 2015

Independent Projects

BioJS
BioJS is a community-based standard and repository of functional components to represent biological information on the web.
Deep Learning in Action
Deep Learning in Action is a regular speaker series in Munich with 350+ participants about Machine Learning (especially Deep Learning).
CellProfiler Analyst
Allows interactive exploration and analysis of data, particularly from high-throughput, image-based experiments. Included is a supervised machine learning system which can be trained to recognize complicated and subtle phenotypes, for automatic scoring of millions of cells.