an intuitive example of how CNN works
Zhou, J. and Troyanskaya, O.G. (2015). Predicting effects of noncoding variants with deep learning–based sequence model. Nature Methods, 12, 931–934.
Predicting (& prioritizing) effects of noncoding variants w. [DeepSEA] #DeepLearning…model
https://www.Nature.com/nmeth/journal/v12/n10/full/nmeth.3547.html Trained w #ENCODE data
#Network Analysis [highlighting #modularity change]: Animation shows how divided Congress has become over…60 yrs https://www.YouTube.com/watch?v=tEczkhfLwqM
Big changes right next store, on Science Hill @Yale
https://www.YouTube.com/watch?v=hbMwpS7JKSQ #Timelapse video of the demolition of the Gibbs Building
I recently had to complete my 2016 Faculty Activity Report (FAR), summarizing key lab “activities” of the past year.
* Here are dump directories with some excerpts:
* A full updated CV describing my lab’s activities (in too much detail):
The CV is based on :
– Compiling the people in the lab, viz:
– A dump up to the end of ’16 of all of our scientific papers and our “other writings” too.
– There’s also an update on lectures in ’16:
* Finally, I’ve done little write up of some highlights, viz:
During 2016 the lab had a number of research highlights. We have published three interlinked tools: Stress, Frustration, and
Intensification, for assessing the impact of rare genomic variants using knowledge of molecular structure. The tools are of particular interest to the medical genetics community because as they can help explain various cancer mutations as well as variants associated with genetic diseases. Another highlight is our publishing a framework for quantifying privacy risks as a result of linking clinical and phenotype variables. This paper is a timely work given the ongoing debate on data sharing. Apart from these works, we have a few research papers on topics in genomics, such as analyzing allele-specific binding and gene expression analysis, and several review articles on the role of non-coding variants, network comparison, and the cost of sequencing.
Regarding service, I worked on further developing the computational biology program at Yale. In particular, I co-chaired a committee about moving toward a Center for Biomedical Data Science at the Medical School. My lab served the research community in participating in many consortiums, such as PCAWG (the Pan-Cancer Analysis Working Group), the ENCODE consortium, PsychENCODE, 1000 Genomes’ structural variation group (and its follow-ons), and the Extracellular RNA Communication Consortium. In 2016, I gave talks and participated in many meetings, including an important data-science education forum at the Cold Spring Harbor Laboratory.
Regarding teaching, I further developed my course in Bioinformatics by including more practical hands-on materials. For example, we introduced a collaborative programming assignment utilizing the GitHub site.
(Private link, with authentication only for my reference:
For reference, this involved updating a variety of places on the wiki, viz: