Publications by authors named "Ming-Hua Hou"
Article Synopsis
- Artificial intelligence has greatly advanced protein structure prediction, notably through DeepMind's AlphaFold2, which can accurately predict 3D structures of proteins comparable to experimental methods.
- This progress allows for a deeper understanding of proteins, enhancing drug discovery and various biological applications.
- However, challenges remain in areas like predicting complex protein structures and their folding pathways, highlighting the need for continued improvements in the field.
Motivation: With the breakthrough of AlphaFold2, the protein structure prediction problem has made remarkable progress through deep learning end-to-end techniques, in which correct folds could be built for nearly all single-domain proteins. However, the full-chain modelling appears to be lower on average accuracy than that for the constituent domains and requires higher demand on computing hardware, indicating the performance of full-chain modelling still needs to be improved. In this study, we investigate whether the predicted accuracy of the full-chain model can be further improved by domain assembly assisted by deep learning.
View Article and Find Full Text PDF