The development of bispecific antibodies that bind at least two different targets relies on bringing together multiple binding domains with different binding properties and biophysical characteristics to produce a drug-like therapeutic. These buildin...
Michaelis constant (K) is one of essential parameters for enzymes kinetics in the fields of protein engineering, enzyme engineering, and synthetic biology. As overwhelming experimental measurements of K are difficult and time-consuming, prediction of...
Scientists and security experts are concerned that the increasing power of AI-assisted protein design and synthesis could be abused by various actors for terrorist or criminal purposes. [Image: see text]
Engineering new molecules with desirable functions and properties has the potential to extend our ability to engineer proteins beyond what nature has so far evolved. Advances in the so-called 'de novo' design problem have recently been brought forwar...
In recent years, generative protein sequence models have been developed to sample novel sequences. However, predicting whether generated proteins will fold and function remains challenging. We evaluate a set of 20 diverse computational metrics to ass...
Journal of chemical information and modeling
38630581
Protein engineering faces challenges in finding optimal mutants from a massive pool of candidate mutants. In this study, we introduce a deep-learning-based data-efficient fitness prediction tool to steer protein engineering. Our methodology establish...
To optimize proteins for particular traits holds great promise for industrial and pharmaceutical purposes. Machine Learning is increasingly applied in this field to predict properties of proteins, thereby guiding the experimental optimization process...
Sheng wu gong cheng xue bao = Chinese journal of biotechnology
38914488
Natural enzymes are often difficult to meet the needs of application and research in terms of activity, enantiomer selectivity or thermal stability. Therefore, it is an important task of enzyme engineering to explore efficient molecular modification ...
Proceedings of the National Academy of Sciences of the United States of America
38913893
Machine learning has been proposed as an alternative to theoretical modeling when dealing with complex problems in biological physics. However, in this perspective, we argue that a more successful approach is a proper combination of these two methodo...
Physical chemistry chemical physics : PCCP
38884162
Using machine learning, molecular dynamics simulations, and density functional theory calculations we gain insight into the selectivity patterns of substrate activation by the cytochromes P450. In nature, the reactions catalyzed by the P450s lead to ...