Some initial results from the #CASP15 competition and we see that #Alphafold2 has become a fertile ground for experimentation by several research groups around the world. Facebook's ESM protein language models (pLMs) are the top non-MSA based methods. 
Another slide showing some of the experimentation taking place: increase the number of models, recycles, get more diversity using dropout (how would that work?), subsample MSAs.
How quickly things progress: we are now treating naive AF2-Multimer as the starting point onto which we make improvements.
Here showing some of the remaining challenges for AF2-Multimer, including Antibody & nanobody completes and Mutation-induced changes.
On the topic of folding predictions for Antibodies, we got lots of great data for SARS-CoV-2 in the last couple of years. Some example predictions on these here.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
