Mohammed AlQuraishi is an Assistant Professor in the Department of Systems Biology at Columbia University. He is one of the leaders of the OpenFold consortium (https://openfold.io).
Thanks for reaching out about this.
With regards to additions, one piece from my own work is the RGN paper (https://www.sciencedirect.com/science/article/pii/S2405471219300766),
which was the first paper to do end-to-end differentiable learning of protein structure, and the first to show that a protein can be folded implicitly using a neural network. This ended up being the approach that AlphaFold2 ultimately took (with many more additions and elaborations on top of course).
Outside of my own work, this paper (https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1005324)
from Jinbo Xu anticipated much of what comprised AlphaFold1, and came out before. It was arguably the first paper to show that deep learning can really move the needle on protein structure prediction.
Another interesting paper is this one (https://openreview.net/forum?id=Byg3y3C9Km),
from John Ingraham, which did differentiable protein simulation,
and this one (https://www.mit.edu/~vgarg/GenerativeModelsForProteinDesign.pdf),
which introduced some primitives that were used in AlphaFold2.
Hope this is of some help.