To efficiently develop smart medicines such as vaccines and antibody drugs, we present our recent study concerning gene mutation rate estimation and gene structure evolving prediction by developing mutual information and Ewens sampling based convolutional neural network (CNN) and machine learning algorithms. More precisely, we develop a systematic methodology through constructing a CNN. In the meanwhile, we develop codon-based machine learning algorithms to study protein production with target gene sequences and protein structures. The core of the CNN and machine learning approach is to optimally coordinate the consistency between the given input DNA sequences and the given (or optimally computed) target ones through controlling their intermediate gene mutation rates. The purposes in doing so are aimed to conduct gene editing and protein structure prediction to further build efficient medicines through world model and physical AI. For example, after the gene mutation rates are estimated, the computing complexity of protein structure prediction will be reduced to a reasonable degree. Our developed CNN numerical optimization scheme consists of two newly designed machine learning algorithms. The stochastic gradients for the two algorithms are designed and justified according to the Kuhn-Tucker conditions with boundary constraints and with the support of Ewens sampling, multi-input multi-output (MIMO) mutual information, and codon optimization techniques. To illustrate the usage of our study, we also conduct a real-world data implementation.

Wanyang Dai is a Distinguished Professor in Nanjing University, Chief Scientist in Su Xia Control Technology. He is the President & CEO of International (Blockchain & Quantum-Computing) SIR Forum, Director of Jiangsu BigData-Blockchain and Smart Information Special Committee, Supervisor Board Chairman of Jiangsu Applied Statistics Society, (past and currently honorable) President of Jiangsu Probability and Statistics Society. He received his Ph.D. in mathematics and systems & industrial engineering from Georgia Institute of Technology in USA. He was an MTS and principal investigator in U.S. based AT&T Bell Labs (currently Nokia Bell Labs) with some project won “Technology Transfer” now called big model smart AI agents cloud system. He holds one “Invention Patent”. He published numerous influential papers in big name journals including Journal of Applied Statistics, Mathematics, Probability in the Engineering and Informational Sciences, Quantum Information Processing, Operations Research, Operational Research, Queueing Systems, Computers & Mathematics with Applications, Communications in Mathematical Sciences, Journal of Computational and Applied Mathematics, Mathematical and Computer Modelling of Dynamical Systems. He received various academic awards and has presented over 80 keynote/plenary speeches in IEEE/ACM, power and energy system, big data and cloud computing, artificial intelligence and robot, quantum computing and communication technology, computational and applied mathematics, biomedical engineering, mathematics & statistics, and other international conferences. He has been serving as IEEE/ACM conference chairs, editors-in-chief and editorial board members for various international journals ranging from artificial intelligence, quantum computing, machine learning, data science, wireless communication, pure mathematics & statistics to their applications. He is an Editor of AIMS Mathematics, the Guest Editor of MDPI Mathematics Special Issue of Probability Statistics, a Guest Editor of (Springer Journal) Mobile Networks and Applications, an Associate Editor of (Elsevier Journal) Results in Applied Mathematics, and an Associate Editor of Quantum Research.