Speaker：Zhang Jiangguo (章将国) Yan Han (颜寒) Zhao Xinyuan (赵心源) Mei Wenbin (梅文彬)

Abstract:

In machine learning, a convolutional neural network (CNN, or ConvNet) is a class of deep, feed-forward artificial neural networks that has successfully been applied to analyzing visual imagery, video analysis, etc.

Convolutional networks were inspired by biological processes in which the connectivity pattern between neurons is inspired by the organization of the animal visual cortex. Individual cortical neurons respond to stimuli only in a restricted region of the visual field known as the receptive field. The receptive fields of different neurons partially overlap such that they cover the entire visual field.

CNNs have been used in drug discovery and clinical diagnosis like CVDs. Predicting the interaction between molecules and biological proteins can identify potential treatments. In 2015, Atomwise introduced AtomNet, the first deep learning neural network for structure-based rational drug design. The system trains directly on 3-dimensional representations of chemical interactions. Similar to how image recognition networks learn to compose smaller, spatially proximate features into larger, complex structures, AtomNet discovers chemical features, such as aromaticity, sp3 carbons and hydrogen bonding. Subsequently, AtomNet was used to predict novel candidate biomolecules for multiple disease targets, most notably treatments for the Ebola virus and multiple sclerosis

Guest information:

1. Xu Youjun (PKU)

http://mdl.ipc.pku.edu.cn/mdlweb/member-cn.php

2. Dr. Deng Minghua (PKU)

http://cqb.pku.edu.cn/kxdw/zxjs/dmh/253402.shtml

3. Dr. Tao Letian (PKU)

http://cqb.pku.edu.cn/kxdw/zxjs/tlt/253415.shtml

Recommend Literatures：

Review:

Pastur-Romay L A, Cedrón F, Pazos A, et al. Deep artificial neural networks and neuromorphic chips for big data analysis: pharmaceutical and bioinformatics applications[J]. International journal of molecular sciences, 2016, 17(8): 1313.

Link：http://www.mdpi.com/1422-0067/17/8/1313/htm

Papers:

1.Gómez-Bombarelli R, Wei J N, Duvenaud D, et al. Automatic chemical design using a data-driven continuous representation of molecules[J]. ACS Central Science, 2016.

Link: https://pubs.acs.org/doi/abs/10.1021/acscentsci.7b00572

2.Kermany D S, Goldbaum M, Cai W, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]. Cell, 2018, 172(5): 1122-1131. e9.

Link: https://www.sciencedirect.com/science/article/pii/S0092867418301545