navvyeanand

This is old news.

Amazing job!

This is very true. However, I wonder how much of this can be mitigated by using training data from other open-source models like Olmo3 for textual data, Emu3.5 for vision?

imo, comments are quite good for junior developers. docstrings are much preferred though.

Become a founder. It's the easiest way to make something people want and get paid a moderately decent salary while you're doing it!

Precisely. I think almost everyone who applies has a 1500+ SAT score and ~3.8-4.0 GPA

I don't know where you're getting your data from, you're probably referring to the Harvard lawsuit.

Caltech in particular is race-blind, and the majority of people attending Caltech are Asian.

Understanding protein-ligand binding affinity is crucial for drug discovery, enabling the identification of promising drug candidates efficiently. We introduce PLAPT, a novel model leveraging transfer learning from pre-trained transformers like ProtBERT and ChemBERTa to predict binding affinities with high accuracy. Our method processes one-dimensional protein and ligand sequences, leveraging a branching neural network architecture for feature integration and affinity estimation. We demonstrate PLAPT's superior performance through validation on multiple datasets, achieving state-of-the-art results while requiring significantly less computational resources for training compared to existing models. Our findings indicate that PLAPT offers a highly effective and accessible approach for accelerating drug discovery efforts.