Daniel Rademaker

TL;DR: It is shown that one single method is unlikely to predict the secondary structure of all protein sequences, with the exception of future deep learning methods based on very large neural networks, and suggested that some concepts pioneered by Oleg Ptitsyn and his group in the 70s of the previous century likely are today's best way forward in the protein secondary structure prediction field.

TL;DR: GradPose as mentioned in this paper uses gradient descent to optimally superimpose structures by optimizing rotation quaternions, and can handle insertions and deletions compared to the reference structure.

TL;DR: This study addresses the generalizability challenge of MHC-bound peptide predictions, revealing limitations in current sequence-based approaches, and employs structure-based methods leveraging geometric deep learning (GDL), yielding up to 8% improvement in generalizability across unseen MHC alleles.

Abstract: DeepRank2, a deep