J.B. Poline, The Brain Imaging Center - Berkeley Neuroscience
Brainspell is the first open, human-curated, classification of the neuroimaging literature. Brain imaging generates on the order of thousands of articles per year, and it is likely that a majority of these are not well-powered, leading to possible replication issues. To confirm results, a standard strategy is to perform meta-analyses using the results of similar studies to decide on the veracity of a specific result. A meta-analysis, therefore, requires gathering a collection of articles with similar protocols and co-analyzing their results. These article collections need to be manually curated by one or a few individuals, generally in the same laboratory. However, this process is faster when realized by a group of distributed curators, and the curation benefits from discussions and a consensus decision, which is most efficiently done in a distributed manner through the web. We present Brainspell-neo, an evolution of the Brainspell software initially developed by R. Toro at the Pasteur Institute. Both versions leverage the Neurosynth database  and allow users to add new articles and curate existing literature. Brainspell-neo takes three directions: 1) a more modern software architecture, 2) an extension of functionalities for the curation of collections of articles, and 3) the use of a new front-end framework.
View their research paper here
Mapping Alzheimer Disease with Computer Vision
Maryana Alegro / Jessica Kudlacek, UCSF Grinberg Lab
This project works with neuropathology for researching Alzheimer's disease. Although we are a neuroscience lab, our current project is actually focused on computer vision. We have a big project for mapping TAU (protein associated with Alzheimer's disease) in the whole human brain and using these maps to validate PET scan tracers (imaging TAU in a living human brain would be a huge breakthrough in AD diagnosis and many pharmaceutical companies are working on that. A big problem is those traces are usually very unspecific and bind to other proteins besides TAU). In order to do so, we have built our own brightfield microscope scanner. We are scanning entire human brain tissue that yields several Gigabytes of data. TAU segmentation is performed using Deep Learning.
MRI Brain Imaging
Maryam Vareth, UCSF Surbeck Laboratory for Advanced Imaging
Seeking students with programming skills mostly python, and some experience with CNN (Convolution Neural Network) and tensorflow platform, experience in imaging and medical images are a plus. Along with someone with less experience as long as they are interested in task of “cleaning data” first, and meanwhile gaining experiences to join the group for more heavily programming tasks
Cryptography of the Unknown Regions of Genomes
Ciera Martinez, BIDS/MCB
We are approaching this problem from a computational perspective by mapping known characteristics of DNA and doing comparative analysis across ~25 different species of Drosophila (fruit fly). The first part of the project will be data wrangling, which consists of annotating and organizing the DNA data (long strings of letters). We will then create workflows to map features onto these sequences, combine existing datasets, and with the end goal of feeding the data into machine learning algorithms to predict function in non-coding regions of DNA.