Selected Research

A view of Estimation of Distribution Algorithms through the lens of Expectation-Maximization

David H. Brookes, Akosua Busia, Clara Fannjiang, Kevin Murphy, Jennifer Listgarten
arXiv 2019

We show that under mild conditions, Estimation of Distribution Algorithms (EDAs) can be written as variational Expectation-Maximization (EM) that uses a mixture of weighted particles as the approximate posterior. In the infinite particle limit, EDAs can be viewed as exact EM. Because EM sits on a rigorous statistical foundation and has been thoroughly analyzed, this connection provides a coherent framework with which to reason about EDAs. Importantly, the connection also suggests avenues for possible improvements to EDAs owing to our ability to leverage both general, and EM-specific statistical tools and generalizations.

Read More

A deep learning approach to pattern recognition for short DNA sequences

Akosua Busia, George E. Dahl, Clara Fannjiang, David H. Alexander, Elizabeth Dorfman, Ryan Poplin, Cory Y. McLean, Pi-Chuan Chang, Mark DePristo
bioRxiv 2019, under review

Inferring properties of biological sequences--such as determining the species-of-origin of a DNA sequence or the function of an amino-acid sequence--is a core task in many bioinformatics applications. These tasks are often solved using string-matching to map query sequences to labeled database sequences or via Hidden Markov Model-like pattern matching. In the current work we describe and assess an deep learning approach which trains a deep neural network (DNN) to predict database-derived labels directly from query sequences. We demonstrate this DNN performs at state-of-the-art or above levels on a difficult, practically important problem: predicting species-of-origin from short reads of 16S ribosomal DNA.

Read More

Next-Step Conditioned Deep Convolutional Neural Networks Improve Protein Secondary Structure Prediction

Akosua Busia, Navdeep Jaitly
Joint 25th Annual International Conference on Intelligent Systems for Molecular Biology (ISMB) and 16th European Conference on Computational Biology (ECCB) 2017, Poster

Recently developed deep learning techniques have significantly improved the accuracy of various speech and image recognition systems. We adapt some of these techniques to create a chained convolutional architecture with next-step conditioning for improving performance on protein sequence prediction problems.

See More

Around the Web

GoogleAI Logo

Google Brain Residency Program - 7 months in and looking ahead

Stanford Firestone Thesis Award

Stanford seniors’ thesis projects garner university medals

Dean Richard Saller, Percy Chirinos, Akosua Busia, and Russ Altman at Sterling Award Ceremony

Congratulations to Sterling Award winners