Résumé
@#In recent years, artificial intelligence (AI) has developed rapidly, with improved computing power and algorithms, which has greatly facilitated the collection and processing of biological, chemical information and clinical data, injecting new vitality into the research and development of new drugs.In this review, we began with a brief overview of the development and the main algorithms of AI in drug discovery.Then we elaborated through several specific cases on the various scenarios of AI application, including target identification, protein structure prediction, hit generation and optimization etc.Finally, we focused on a recent example to discuss the high efficiency of "end-to-end" application of AI.
Résumé
Objective To design a good scoring function for predicting the tertiary structures of proteins. Methods A scoring function,which was composed of simple sum of pairwise distance-dependent potentials of C?-C?,N-N,C′-C′ and backbone dihedral angle-dependent potentials,was proposed in this paper. Results The performance of the scoring function was verified with experiment to be improved. Conclusion The proposed scoring function is effective and valid in predicting the tertiary structures of proteins.
Résumé
Physical principles determining the protein structure and protein folding are reviewed: (i) the molecular theory of protein secondary structure and the method of its prediction based on this theory; (ii) the existence of a limited set of thermodynamically favourable folding patterns of α- and ß-regions in a compact globule which does not depend on the details of the amino acid sequence; (iii) the moderns approaches to the prediction of the folding patterns of α- and ß-regions in concrete proteins; (iv) experimental approaches to the mechanism of protein folding. The review reflects theoretical and experimental works of the author and his collaborators as well as those of other groups.