The function for much of the 3 billion letters in the human genome remain to be understood. Advances in DNA sequencing technology have generated enormous amount of data, yet we don’t have the tool to extract rules of how the genome works. Deep learning holds great potential in decoding the genome, in particular due to the digital nature of DNA sequences and the ability to handle large data sets. However, like many other applications, the interpretability of deep learning models hampers its ability to help understand the genome. We are developing deep learning architectures embedded with the principles of gene regulation and we will be leveraging billions of existing measurements of gene activity to learn a mechanistic model of gene regulation in human cells.

Continue reading

This project will be focused on creating a deep learning framework for tracking individual molecules and proteins as they move within a cell under various conditions. Using total internal reflection (TIRF) microscopy, we have accumulated more than 10 million trajectories over dozens of experimental preparations with differences in both the imaging approaches as well as the biological context. In our experiments we have captured particles under a wide variety of conditions including increased protein expression level, and a range of drug concentrations. Our biggest challenge is being able to stably track the movement of a particle as it passes by other particles or groups of particles, and to do this in a way that generalizes over novel conditions. The Data Science Institute Scholar chosen for this project would work with scientists in the Javitch laboratory and others across the Columbia campus to conceive of an approach for efficiently and effectively tracking particles. The resulting work would be of great interest to an increasing number of scientists working in this field who currently rely on methods based on feature engineering that are often inaccurate or inflexible compared to modern deep learning methods.

Continue reading

Big data with temporal dependence brings unique challenges in effective prediction and data analysis. The complex high-dimensional interactions between observations in such data brings unique challenges which standard off-the-shelf machine learning algorithms cannot handle. Even basic tasks of clustering, visualization and identification of recurring patterns are difficult.

Continue reading

The ocean significantly mitigates climate change by absorbing fossil fuel carbon from the atmosphere. Cumulatively since the preindustrial times, the ocean has absorbed 40% of emissions. To understand past changes, diagnose ongoing changes, and to predict the future behavior of the ocean carbon sink, we must understand its spatial and temporal variability. However, the ocean is poorly sampled and so we cannot do this from direct measurements.

Continue reading

The introduction of a new technology provides individuals and organizations with a large, unowned, and limitless space for communication and organization. How do individuals use or misuse this space in their decision making? Using online discussion platforms, we will analyze what types of discussions thrive - those with depth of discussion or topical complexity or those with cohesive contours? We’ll ask, are there high status actors who are particularly good at recognizing topic gaps which need new conversations? Using social psychological theories with a large-scale archival dataset, we’ll learn more about the impact of new technologies on group decision-making processes.

Continue reading

The amount of video content that is being distributed over the Internet is increasing. Video providers rely on HTTP adaptive streaming approaches to deliver video clips to users. Complementary to the video provider, the service provider must determine the priority of each network stream. As part of the project, students will explore wireless network assisted strategies for http adaptive streaming by use of TOS/DSCP. This includes using machine-learning tools to analyze network video traffic and the design of reinforcement learning algorithms to improve users' video Quality of Experience.

Continue reading

We are constantly exposed to inputs from the outside world, but we do not perceive everything we are exposed to. Some inputs are rather weak: we might perceive them at one point in time, but not at another. The state of our brains right before we receive such sensory inputs influences whether or not we perceive them. Brain oscillations are proposed to play a key role in setting these brain states; however, how exactly these brain rhythms influence our perception remains a topic of active research.

Continue reading