Krishna YerramsettyinKrishna YerramsettyMulti-Modal Protein Language Models: Protein Function PredictionA simple implementation using amino-acid sequence and catalytic site informationJul 10Jul 10
Krishna YerramsettyinKrishna YerramsettyFinetuning Protein Language Models?In this post, I want to share some results and thoughts on finetuning protein language models. Finetuning is a powerful technique to get…Jun 17Jun 17
Krishna YerramsettyinKrishna YerramsettyContext Specific Positional Encoding (CoPE) for Protein Language ModelsIt took me a while to grok the concept of positional encoding/embeddings in transformer attention modules. In a nutshell, the positional…Jun 10Jun 10
Krishna YerramsettyinThe StartupPyTorch DataSet & DataLoaderThere are a plethora of options for someone to get started with NLP models. And frameworks like AllenNLP, and Fast.ai have made it…Sep 28, 20201Sep 28, 20201
Krishna YerramsettyinThe StartupMulti-Logistic Regression With Probabilistic ProgrammingThere is an interesting dichotomy in the world of data science between machine learning practitioners (increasingly synonymous with deep…Sep 2, 20201Sep 2, 20201
Krishna YerramsettyAmazon Sagemaker: A Short GuideSpend less time building workflows, and more time developing modelsJan 29, 20201Jan 29, 20201
Krishna YerramsettyinTowards Data ScienceRelative vs Absolute: How to Do Compositional Data Analyses. Part — 2This is a continuation of my earlier post on compositional data analyses where I showed the pitfalls of treating compositional data as…Jul 25, 20191Jul 25, 20191
Krishna YerramsettyinTowards Data ScienceRelative vs Absolute: Understanding Compositional Data with SimulationsOne of the things I am constantly asked to do at my work is to compare NGS data across samples. These could be replicates or could be…Jun 17, 20193Jun 17, 20193
Krishna YerramsettyFun with Twitter Bots: Part -3Creating a twitter app, storing tweets, and analyzing tweets:May 18, 2019May 18, 2019