Dear Undergrads,
My lab has a number of projects available in computational biology and machine learning that may be of interest. These projects are available immediately, and can be carried out for research credit or for pay. Interested students should send a cover letter, transcript, and resume to Dr. Ritambhara Singh <
rsingh7@uw.edu>. Descriptions of the projects are below:
Hi-C Projects
Data Description: Studying the three-dimensional (3D) organization of the human genome is vital for understanding cellular functions. The spatial organization of the genome can directly or indirectly affect the regulation of genes that, in turn, can decide the fate of the cell. Various high-throughput experimental techniques, such as Hi-C, are used to study higher-order chromatin structure at different scales. The Hi-C assay uses high-throughput sequencing to measure 3D genome structure, where each read pair corresponds to an observed 3D contact between two genomic loci. Data from a Hi-C assay is typically coalesced into a matrix in which rows and columns correspond to fixed-width windows (“bins”) tiled along the genomic axis, and values in the matrix are counts of read pairs that fall into the corresponding bins.
Project #1: Automatic Resolution Selection for Hi-C Data
-
Project Description: Typical Hi-C analysis is done using bin sizes of 40 kb or 100 kb, which might not be the optimal bin size to gain useful biological insights from the data. The goal of this project is to produce a lightweight Python package that automatically selects an appropriate fixed-width bin size for a given set of Hi-C reads. The current implementation splits the Hi-C reads from a dataset into “train” and “test” sets and then varies the train set bin size, using the test set to evaluate how similar the two sets are. The bin size that gives the highest similarity score is recommended as the optimal resolution for that dataset. The project requires this implementation to be converted into an easy-to-use, fast and efficient package, with proper documentation, that will be widely used by the research community.
[1] Cameron, Christopher JF, Josee Dostie, and Mathieu Blanchette. “Estimating DNA-DNA interaction frequency from Hi-C data at restriction-fragment resolution.” bioRxiv (2018): 377523.
Project #2: Improving Hi-C Resolution using Graph Convolutional Networks (GCNs)
-
Project Description: Due to the high sequencing costs, Hi-C experiments can result in low read coverage and high data sparsity. To analyze such datasets, researchers use large (100kb) fixed-width bin sizes to reduce noise in the data. While this approach may give insights into the global interactions within and among chromosomes, it is hard to locate finer interactions among regulatory elements of the DNA. In order to improve the Hi-C resolution for better downstream analysis, this project proposes the use of deep neural networks to predict high-resolution Hi-C maps from low-resolution ones. Specifically, we will use graph convolution networks (GCNs), in which we treat the Hi-C map as an undirected graph G, with nodes V being the different genomic loci and the number of contacts between them representing as weighted edges E. Thus, the Hi-C resolution improvement task can be viewed as link prediction for missing links (or edges) in the graph G. The project requires implementation of novel model architectures involving GCNs and extensive hyperparameter tuning to achieve state-of-the-art performance on this prediction task.
[1] Zhang, Yan, et al. “Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus.” Nature Communications 9.1 (2018): 750.
[2] Kipf, Thomas N., and Max Welling. “Semi-supervised classification with graph convolutional networks.” arXiv preprint arXiv:1609.02907 (2016).
Manifold Alignment Project
Project #3: Learning Manifold Alignment for Two Distinct Datasets
-
Project Description: This project involves learning correspondences across datasets from different domains. For example, for a given population of cells, one can obtain two different sets of measurements from different experiments. If these experiments are performed on disjoint but similar subsets of cells, then it may be necessary to embed the two populations into a latent space in such a way that the two populations are distributed similarly. Recently, a Gromov-Wasserstein distance-based framework has been shown to successfully learn the cross-domain correspondence among languages, and the goal of this project is to use this framework in the biological setting described above. Therefore, the project requires an efficient implementation of Gromov-Wasserstein distance-based framework that learns correspondence between features from different biological experiments and aligns them in a common latent space.
[1] Alvarez-Melis, David, and Tommi S. Jaakkola. “Gromov-Wasserstein Alignment of Word Embedding Spaces.” arXiv preprint arXiv:1809.00013 (2018).
Bill Noble
Professor, Genome Sciences
Adjunct Professor, Computer Science
December 18, 2018
Why Robotics & RISS?
Robotics-related technologies are becoming ubiquitous and are dominating national headlines due to innovations such as driverless cars, service robots, surgical robots, and aerial vehicles. Robots and the knowledge required to create, operate, and interact with them will become increasingly important to society.
The Robotics Institute Summer Scholars (RISS) program is designed to immerse students in the world of robotics. Through RISS, students perform research under the mentorship of top scientists in robotics and intelligent systems at Carnegie Mellon University’s Robotics Institute. RISS has access to over 50 research mentors representing a broad range of robotics research (e.g. field robotics, computer vision, machine learning, artificial intelligence, autonomy, machine learning, graphics, human-robot interaction, and space robotics).
The RISS-guided research experience is coupled with powerful professional development and hands-on robotics experiences with industry leaders in a nurturing global community and culminates in August with an annual research poster session and the publication of the RISS Working Papers Journal. Many students continue to collaborate with RISS mentors, labs, and cohort members.
Applications are OPEN:
· Applications will be accepted through January 15 at riss.ri.cmu.edu.
· Program dates are June 1 to August 15.
· Funding and support is available for both U.S. and international students.
More information about the program, including 2018 research posters and papers (2018 the RISS Working Papers Journal) can be found here riss.ri.cmu.edu/research.
Carnegie Mellon University
The Robotics Institute
Questions? Contact Riss-info@andrew.cmu.edu
December 17, 2018
Get a free professional profile photo!
Dubshot Photography Club is an on-campus, nonprofit RSO at UW. Dubshot is co-hosting with another RSO, Frameworld to offer a free LinkedIn Photo Shooting opportunity for students. See below for details.
We believe professional profile photos are extremely beneficial as students are stepping into their workplace. In the previous school year, Dubshot took professional photos for members of ACM-W, a student org for computer science major. Students can attend either one of two sessions:
1) 5-7 pm, Nov. 29 at SAV 264 on 11/29
2) 5-7 pm at BAG 261 on 11/30
Please remind the participants to bring their outfits, and there’s no need to sign up. Again, we appreciate your support.
Best,
Dubshot PR Team
November 27, 2018
The Allen School Student Advisory Council’s aim is to equip you with the resources you need to be successful, but we need your help! Our upcoming Town Hall meeting will be held on November 29th and will be your chance to share suggestions, thoughts, or concerns for the Allen School.
With finals quickly approaching, another quarter is coming to a close. Therefore, this is an ideal time for all of us to reflect on the last 10 weeks and understand how we can make next quarter even better.
What do we need from you? Great question! Please come with your honest opinions and any suggestions or other feedback you may have. From there, the SAC team will advocate on your behalf to the Allen school faculty and staff.
This event is specifically focused on undergraduate and 5th year masters students.
This is a great opportunity for you to make a real impact on your school and your Allen School experience, so we urge you to consider attending. Please RSVP using the link below.
Topic: Town Hall
Date: Thursday, November 29th
Time: 5:30 – 7:00pm
Location: Gates Commons
Food Provided: YES
RSVP link:
https://tinyurl.com/sactownhall
November 27, 2018
The Allen School Student Advisory Council’s aim is to equip you with the resources you need to be successful, but we need your help! Our upcoming Town Hall meeting will be held on November 29th and will be your chance to share suggestions, thoughts, or concerns for the Allen School.
With finals quickly approaching, another quarter is coming to a close. Therefore, this is an ideal time for all of us to reflect on the last 10 weeks and understand how we can make next quarter even better.
What do we need from you? Great question! Please come with your honest opinions and any suggestions or other feedback you may have. From there, the SAC team will advocate on your behalf to the Allen school faculty and staff.
This event is specifically focused on undergraduate and 5th year masters students.
This is a great opportunity for you to make a real impact on your school and your Allen School experience, so we urge you to consider attending. Please RSVP using the link below.
Topic: Town Hall
Date: Thursday, November 29th
Time: 5:30 – 7:00pm
Location: Gates Commons
Food Provided: YES
RSVP link:
https://tinyurl.com/sactownhall
November 20, 2018
HuskyTech is partnering with Expedia to present our next event: Prototype With The Pro’s! Come design unique travel solutions from a software perspective and pitch your prototype idea to Expedia designers and engineers. Expedia will award prizes to groups who present the best prototypes and pitches.
RSVP: https://tinyurl.com/HTxExpedia
WHEN: Tuesday, November 13th 4:30 PM – 6:30 PM
WHERE: HUB 332
November 13, 2018
Apply now for The Impact Fellowship!
The Impact Fellowship is a 2-week program in NYC for tech students who want to build a better world! Fellows will team up and create their own social startups that address the UN Sustainable Development Goals. The program will also feature workshops with advanced software engineers, speakers from the social impact arena, and a pitch competition at the culmination of the fellowship! Learn more and apply at www.impactlabs.io/fellowship
The fellowship runs from January 2nd-16th in NYC, it’s completely free for students, and applications are open to CS majors of any year.
November 7, 2018
Just a few notes for winter quarter:
*We will not be giving any add codes out to overload courses, please do not come to Quick Questions for that reason
*Please sign up on ‘notify’ and make sure your MyPlans are up to date so we can try to do a better job of forecasting interest in advance
*Yes, courses are going to fill fast, but keep in mind students tend to ‘hoard’ courses and then drop them the first week. After the first week there was space in just about every course this fall. We don’t like this any more than you folks do, but please be patient and most students get the courses they need. (And, please don’t hoard courses)
*There will be an extra large offering of Machine Learning in the spring, so we should be able to accommodate a lot of you by the end of the year.
*We try to adjust courses with more space as needed when possible. There are a lot of restrictions, but I promise we’ll be doing the best we can.
*We will open capstone space as it comes available in the next couple of weeks.
Thank you for your patience!
~CSE Advising: Crystal, Jenifer, Maggie, Chloe, Leslie and Kim
November 5, 2018
Hey everyone!
We hope midterm season is going well 🙂
We are a new RSO on campus that aims to connect computer science students with meaningful projects that work towards social good. For now, we get our projects from Microsoft Hack For Good (yearly hackathon for Microsoft employees where they develop for non-profits). Not only do we make a significant impact in the community by filling crucial technology gaps in charitable and governmental organizations, we provide talented UW undergraduates with relevant experience in their field so they can have a jumpstart on their careers. Our teams were invited to the yearly Microsoft wide hackathon last year (over 10,000 engineers showed up!) and we also won a $5000 grant for exceptional work on a long standing project from Microsoft Philanthropies earlier this year. This truly is a great way to get involved in your community while expanding your network and gaining amazing engineering experience. Please look at the attached flyer for more information about us!
We have several potential projects in store for you guys, so if you’re interested, please come out to one of our info sessions next week! We’ll talk about the projects, more about our club and how you can get involved (Snacks will be provided of course :)).
The Info Sessions will be on:
-
Monday, November 5th at 5:30-6:30 pm
-
Thursday, November 8th at 5:30-6:30 pm
-
Location TBD
Both info sessions will be identical, come to the one that best fits your schedule.
Please RSVP at the below links so we can get an expectation of how many people will attend:
https://tinyurl.com/impact-infosesh-monday
https://tinyurl.com/impact-infosesh-thursday
If you are unable to make it to an info session and/ or have any questions, please reach out to us at udubimpact@gmail.com!
See you next week.
Impact++
November 2, 2018
With a degree in CS, you could be a Software Engineer, or…. you can come to Unconventional Careers in CSE and learn about the endless other career paths you could take! Hosted by the Student Advisory Council, Unconventional Careers in CSE will be an in-depth look at many of the overlooked opportunities you have as a future CS grad. Hear from speakers working in non-profits, start-ups, research, and more! Explore different career options like being a Program Manager or Researcher.
Join the SAC on November 8th from 5:30-7pm as we bring leaders from across industries to speak about their experiences in choosing an “unconventional” career path. You will have a chance to learn and ask questions. There will also be free food and drinks! RSVP here with your CSE email: https://goo.gl/forms/BUf1DW4KCx7VSDs53.
This event is intended to highlight leaders in our field who deviated from the standard software engineering career path and give students a chance to explore different career opportunities and ask questions one-on-one with leaders who have successfully branched out from the typical Software Engineering role.
Event:Unconventional Careers in CSE
Where: CSE 305
When: November 8th 5:30-7pm
Contact csesac@cs.uw.edu for any questions
October 30, 2018
