Machine Learning and the Protein Folding Problem
The amazing results of DeepMind's AlphaFold2 in the last CASP experiment caused a huge stir in both the AI and biology fields, and this was of course widely reported in the general media. The claim is that the protein folding problem has finally been solved, but has it really? Not to spoil the ending, but of course not. In this talk I will not be talking (much) about AlphaFold2 itself, but instead what inspiration we can take from it about future directions we might want to take in protein structure bioinformatics research using modern AI techniques. Along the way, I'll illustrate my thoughts with some recent and current machine-learning-based projects from my own lab in the area of protein structure and folding.