Machine learning to navigate fitness landscapes for protein engineering
CR Freschlin, SA Fahlberg, PA Romero - Current opinion in biotechnology, 2022 - Elsevier
Machine learning (ML) is revolutionizing our ability to understand and predict the complex
relationships between protein sequence, structure, and function. Predictive sequence …
relationships between protein sequence, structure, and function. Predictive sequence …
Neural networks to learn protein sequence–function relationships from deep mutational scanning data
S Gelman, SA Fahlberg… - Proceedings of the …, 2021 - National Acad Sciences
The mapping from protein sequence to function is highly complex, making it challenging to
predict how sequence changes will affect a protein's behavior and properties. We present a …
predict how sequence changes will affect a protein's behavior and properties. We present a …
PyPEF—an integrated framework for data-driven protein engineering
NE Siedhoff, AM Illig, U Schwaneberg… - Journal of Chemical …, 2021 - ACS Publications
Data-driven strategies are gaining increased attention in protein engineering due to recent
advances in access to large experimental databanks of proteins, next-generation …
advances in access to large experimental databanks of proteins, next-generation …
[HTML][HTML] Biophysics-based protein language models for protein engineering
Protein language models trained on evolutionary data have emerged as powerful tools for
predictive problems involving protein sequence, structure, and function. However, these …
predictive problems involving protein sequence, structure, and function. However, these …
Random embeddings and linear regression can predict protein function
Large self-supervised models pretrained on millions of protein sequences have recently
gained popularity in generating embeddings of protein sequences for protein function …
gained popularity in generating embeddings of protein sequences for protein function …