Scalable Machine Learning for Big Data Biology
Number of units (credits): 3
Grading Basis: Letter Grade
Day/Time/Location: Biomedical Science Tower 3, Room 3081, Wed–Fri 1:30–3
Enrollment Capacity: 25
Machine learning (ML) has become an integral part of computational thinking in the era of big data biology. This course will focus on understanding the statistical structure of large-scale biological datasets using ML algorithms. We will cover the basics of ML and study their scalable versions for implementation on a distributed computing framework. We will pursue distributed ML algorithms for: matrix factorization, convex optimization, dimensionality reduction, clustering, classification, graph analytics and deep learning, among others.
The course will be project driven (3 to 4 mini projects) with source material from genomic sciences, structural biology, drug discovery, systems modeling and biological imaging. There will be one final project, along with a presentation.
Students will be expected to design, implement and test their ML solutions in Apache Spark.
No biological background is expected. The assignments will cover the necessary biology. Experience in programming and some software engineering is preferred. Knowledge of probability, statistics, linear algebra and algorithms is a bonus.
The class is open to senior-year undergraduates and graduate students.
Prof. Chakra Chennubhotla
Prof. David Koes
(Official White House Photo by Pete Souza)
The Frontiers Conference, taking place on October 13, will be cohosted by the University of Pittsburgh and Carnegie Mellon University to explore the future of innovation here and around the world
The Conference will include programming featuring five “Frontiers” of innovation:
- Personal frontiers in health care innovation and precision medicine;
- Local frontiers in building smart, inclusive communities, including through investments in open data and the Internet of things;
- National frontiers in harnessing the potential of artificial intelligence, including data science, machine learning, automation, and robotics to engage and benefit all Americans;
- Global frontiers in accelerating the clean energy revolution and developing advanced climate information, tools, services, and collaborations; and
- Interplanetary frontiers in space exploration, including our journey to Mars.
To learn more about the conference or to nominate an innovator, please visit: FrontiersConference.org.
The Xing lab published a research article in FEBS Letters.
miRNAs serve as crucial post-transcriptional regulators in a variety of essential cell fate decisions. However, the contribution of the mRNA-miRNA mutual regulation to bistability is not fully understood. Here, we built a set of mathematical models of mRNA-miRNA interactions and systematically analyzed the sensitivity of the response curves under various conditions. Our findings indicate that mRNA-miRNA reciprocal regulation could manifest ultrasensitivity to subserve the generation of bistability when equipped with a positive feedback loop. We also find that the region of bistability is expanded by a stronger competing endogenous mRNA (ceRNA). Interestingly, bistability can be generated without a feedback loop if multiple miRNA binding sites exist on a target mRNA. Thus, we demonstrate the importance of simple mRNA-miRNA reciprocal regulation in cell fate decisions.
This article is protected by copyright. All rights reserved.
Tian X-J, Zhang H, Zhang J, Xing J (2016) Reciprocal Regulation Between mRNA and miRNA Enables a Bistable Switch That Directs Cell Fate Decisions FEBS Letters doi: 10.1002/1873-3468.12379.