Alert button
Picture for Zekun Ni

Zekun Ni

Alert button

ChemiRise: a data-driven retrosynthesis engine

Aug 09, 2021
Xiangyan Sun, Ke Liu, Yuquan Lin, Lingjie Wu, Haoming Xing, Minghong Gao, Ji Liu, Suocheng Tan, Zekun Ni, Qi Han, Junqiu Wu, Jie Fan

Figure 1 for ChemiRise: a data-driven retrosynthesis engine
Figure 2 for ChemiRise: a data-driven retrosynthesis engine
Figure 3 for ChemiRise: a data-driven retrosynthesis engine
Figure 4 for ChemiRise: a data-driven retrosynthesis engine

We have developed an end-to-end, retrosynthesis system, named ChemiRise, that can propose complete retrosynthesis routes for organic compounds rapidly and reliably. The system was trained on a processed patent database of over 3 million organic reactions. Experimental reactions were atom-mapped, clustered, and extracted into reaction templates. We then trained a graph convolutional neural network-based one-step reaction proposer using template embeddings and developed a guiding algorithm on the directed acyclic graph (DAG) of chemical compounds to find the best candidate to explore. The atom-mapping algorithm and the one-step reaction proposer were benchmarked against previous studies and showed better results. The final product was demonstrated by retrosynthesis routes reviewed and rated by human experts, showing satisfying functionality and a potential productivity boost in real-life use cases.

Viaarxiv icon

Molecular modeling with machine-learned universal potential functions

Mar 06, 2021
Ke Liu, Zekun Ni, Zhenyu Zhou, Suocheng Tan, Xun Zou, Haoming Xing, Xiangyan Sun, Qi Han, Junqiu Wu, Jie Fan

Figure 1 for Molecular modeling with machine-learned universal potential functions
Figure 2 for Molecular modeling with machine-learned universal potential functions
Figure 3 for Molecular modeling with machine-learned universal potential functions
Figure 4 for Molecular modeling with machine-learned universal potential functions

Molecular modeling is an important topic in drug discovery. Decades of research have led to the development of high quality scalable molecular force fields. In this paper, we show that neural networks can be used to train an universal approximator for energy potential functions. By incorporating a fully automated training process we have been able to train smooth, differentiable, and predictive potential functions on large scale crystal structures. A variety of tests have also performed to show the superiority and versatility of the machine-learned model.

Viaarxiv icon

DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

Feb 02, 2018
Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, Yuheng Zou

Figure 1 for DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Figure 2 for DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Figure 3 for DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Figure 4 for DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

We propose DoReFa-Net, a method to train convolutional neural networks that have low bitwidth weights and activations using low bitwidth parameter gradients. In particular, during backward pass, parameter gradients are stochastically quantized to low bitwidth numbers before being propagated to convolutional layers. As convolutions during forward/backward passes can now operate on low bitwidth weights and activations/gradients respectively, DoReFa-Net can use bit convolution kernels to accelerate both training and inference. Moreover, as bit convolutions can be efficiently implemented on CPU, FPGA, ASIC and GPU, DoReFa-Net opens the way to accelerate training of low bitwidth neural network on these hardware. Our experiments on SVHN and ImageNet datasets prove that DoReFa-Net can achieve comparable prediction accuracy as 32-bit counterparts. For example, a DoReFa-Net derived from AlexNet that has 1-bit weights, 2-bit activations, can be trained from scratch using 6-bit gradients to get 46.1\% top-1 accuracy on ImageNet validation set. The DoReFa-Net AlexNet model is released publicly.

Viaarxiv icon