ETH-Zürich (@ETH_en) has put out a great summary of our DML technique and how it can help us develop more effective antibody therapies and vaccines against future variants of SARS-CoV-2. Read more about it here:

Researchers have developed a method to explore the possibilities of how the #pandemic #virus could evolve. Thanks to their work, it may be possible to develop #antibody #therapies and #vaccines that are more effective also against future variants. https://t.co/QxWQgM4FV0

Fantastic new tool developed by the team of Sai Reddy @ReddyLab_ETHZ: "#MachineLearning could support #antibody #drug development by enabling researchers to identify which antibodies have the potential to be most effective against current and future #Variant|s" @saireddy911

Proud to share our *finally* accepted paper. It was a wild ride, but we finally got there on my last day at @ETH_BSSE @ETH. Couldn't ask for a better way to finish my time in the @ReddyLab_ETHZ. https://t.co/eAz9AHZLq4

Some work lead by fellow platypus enthusiast @Roy_ehling from @ReddyLab_ETHZ. We profiled repertoire & functional properties of PCs in convalescent COVID19 patients Adds to our previous characterisation of VDJ & GEX of T and B cells in @flobdalabob et al https://t.co/ylttnVIET1

Protein engineers work wonders with machine learning, but generating data remains a bottleneck. Computer vision & NLP use data augmentation, but we lack such techniques for proteins. To address this, we develop nucleotide augmentation (NTA). A thread 🧵1/5

Highlighting our recent work from @ReddyLab_ETHZ involving the construction of combinatorial RBD libraries that were used to infer and validate ACE2 binding and escape from clinically relevant mAbs. Moving towards in silico prediction of escape for emerging variants🤓

Very happy to share our latest manuscript on rapid characterization of spike variants. This was a wonderful collaboration with @Kamyab_J and @IlyaFinkelstein. More to come in this space soon. https://t.co/oUBMTBkkdH

The lesson: individual mutations cannot predict the behavior of combinatorial mutations. Read more: https://t.co/S8DQPLLgib https://t.co/9ePpxdRGwo @ReddyLab_ETHZ

Why Deep Mutational Learning matters, a story in two press releases: https://t.co/9ePpxdRGwo

This looks interesting: Predictive profiling of SARS-CoV-2 variants by deep mutational learning Screening combinatorial RBD mutations and impact on ACE2 and antibody binding could help prospective profiling of variants https://t.co/5azBGthb1o

Another Omicron neutralization thread, this time about monoclonal antibodies. Once again, massive cred to @DannySheward, and everyone else from the previous data release. This time, we also need to especially thank @ReddyLab_ETHZ (1/n)

A brief draft with numbers and some technical details can be downloaded here: https://t.co/JrwgwvCuWA - but please expect this to change. Once again, thanks to @DannySheward @ReddyLab_ETHZ and everyone else involved (14/n)

Here, we establish deep mutational learning (#DML), integrating experimental yeast display screening of RBD mutagenesis libraries with deep sequencing and machine learning.

Predictive profiling of SARS-CoV-2 variants by deep mutational learning https://t.co/NNAeZFDfrT #bioRxiv

It has been 2 years since the 1st detection of #SARSCoV2 and yet the #pandemic shows little signs of slowing down, as seen most recently through the emergence of #omicron and its surprisingly large No. of mutations. How surprising is that though? A thread.