lab “pizza” lunch

Here’s most of us having our a “pizza” lunch. We are saying farewell to Amy (again) and celebrating Gang and Dina’s projects. Obviously, this semester has been different. Still, I hope we’ve learned. It helped me to put our semester in perspective: Cambridge sent home its students in the 1660s, …

BADR codes and data

We have recently been working on classifying disordered regions for different functions and phenotypes using evolutionary signatures (and signatures comprised of “bulk” feature calculations from disordered sequences). The code and data related to this project currently lives at: https://github.com/taraneh-z/BADR! Check it out and let us know what you think. Hopefully …

Journal club pre-print “Molecular evolution across developmental time reveals rapid divergence in early embryogenesis” by Cutter, A. D., et al

In this pre-print, the authors characterized the transcriptome of C. elegans at 30 timepoints during development. They used fPCA to cluster 14 co-expression modules from 19,711 genes and then fitted a cubic function to the expression profile of each module. The authors then conducted hierarchical clustering on the parameter values …

Pi day

Shadi brought us a pie. I proposed to draw a circle with a diameter of 2R and have uniformly random knife cuts on the pie to estimate π with Monte Carlo method. My proposal was rejected.

Journal Club Review: “Mitigating Data Scarcity in Protein Binding Prediction using Meta-Learning”

In our recent journal club, we discussed the pre-print, “Mitigating Data Scarcity in Protein Binding Prediction using Meta-Learning”. Here, Luo et al. apply the recent trend of meta-learning to predicting phosphorylation sites for a poorly characterized kinase family. Meta-learning algorithms aim to discover models that generalize to new predictions with …