当前位置:网站首页>ICML 2022 | 3dlinker: e (3) equal variation self encoder for molecular link design
ICML 2022 | 3dlinker: e (3) equal variation self encoder for molecular link design
2022-07-04 23:17:00 【Zhiyuan community】
Paper title: ICML2022|3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design
Paper link: https://arxiv.org/abs/2205.07309
Paper code: https://github.com/GraphPKU/3DLinker
Publication venue: ICML 2022 Long Presentation (118/5630)
Institution: Beijing Institute for General Artificial Intelligence, Tsinghua University, Peking University
Authors: Yinan Huang, Xingang Peng, Jianzhu Ma, Muhan Zhang
Research background and motivation
Machine learning plays an increasingly important role in drug design . among , Link design (linker design) It is a widely used drug design method . In link design , We have two called fragment The molecules of , these two items. fragment Generally, it has specific chemical functions ( such as , One fragment It can bind to the target protein , Another one fragment It can attract enzymes used to decompose target proteins ). Our goal is to generate a linker Molecules to link these two fragments, Making it a drug with multiple chemical functions at the same time .
Link design
The link design problem can be regarded as a conditional generation model : Given two fragments, Construct a ” completion “fragments The probability model of . here drug By inputting fragments And generated linker constitute . Once you have this generation model , Enter any two interested fragments, The model can sample a new sample , In this way, automatic 、 Efficient link design .
fragments and linker It is usually seen as a graph (Graph): Atoms as vertices , Chemical bonds act as edges . Thus, link design can be equivalent to training the conditional generation model of a graph . however , Retaining only the graph structure will lose 3D geometric information , This may lead to unrealistic 、 Physically unstable linker, Or it can't be directly used in downstream tasks that need three-dimensional coordinates . Previous work [1, 2] Can only be used very roughly fragment Three dimensional information ( For example, manually add distance Information or use an additional convolution network ) And cannot generate linker The space coordinates of .
Link design containing 3D geometric information
In this work , The author proposes a self coding model that can generate three-dimensional coordinates and graphs at the same time ,3DLinker, Used to model the following probability distribution :
here G Representative diagram ,X Represents spatial coordinates . The most important ,3DLinker It is equivalent to the transformation of coordinate system : When you type fragments Coordinates undergo any coordinate system transformation , Entire output drug The coordinates of will change accordingly , Simultaneous output drug The graph of remains unchanged . This means that the model can be trained and generalized in any coordinate system . in addition , This task can also be regarded as the pre training of the graph with three-dimensional coordinates : Randomly mask out some (linker) Graph and coordinates of , Learn how to learn from the rest (fragments) To reconstruct the original three-dimensional image .
Method
3DLinker The core of is an equivariant messaging (message passing) modular , be called MF-MP (Mixed-Features Message Passing). For a vertex in the graph ( In position ), It has invariable characteristics ( Unchanged under the transformation of coordinate system ), It also has equivariant characteristics ( Transform with the coordinate system ), Where and are channel Count . Every one of channel Is a number independent of the coordinate system , And every one of channel Is the three components of a three-dimensional vector ( Imagine an arrow with a direction ), Will change as the coordinate system changes . In the process of message transmission , These features will aggregate the messages of adjacent vertices while maintaining the invariance and equivariability of the features . Here's one MF-MP The process of message transmission . The detailed calculation process is shown in the paper Methodology part .
边栏推荐
- mamp下缺少pcntl扩展的解决办法,Fatal error: Call to undefined function pcntl_signal()
- Excel 快捷键-随时补充
- ScriptableObject
- 【taichi】用最少的修改将太极的pbf2d(基于位置的流体模拟)改为pbf3d
- Excel shortcut keys - always add
- Pict generate orthogonal test cases tutorial
- QT drawing network topology diagram (connecting database, recursive function, infinite drawing, dragging nodes)
- Blue sky nh55 series notebook memory reading and writing speed is extremely slow, solution process record
- 蓝天NH55系列笔记本内存读写速度奇慢解决过程记录
- Redis introduction complete tutorial: List explanation
猜你喜欢
JS 3D explosive fragment image switching JS special effect
Network namespace
P2181 diagonal and p1030 [noip2001 popularization group] arrange in order
QT addition calculator (simple case)
蓝天NH55系列笔记本内存读写速度奇慢解决过程记录
Redis getting started complete tutorial: Geo
Phpcms paid reading function Alipay payment
【图论】拓扑排序
[sword finger offer] questions 1-5
壁仞科技研究院前沿技术文章精选
随机推荐
ICML 2022 || 3DLinker: 用于分子链接设计的E(3)等变变分自编码器
[ODX studio edit PDX] - 0.2-how to compare two pdx/odx files of compare
推荐收藏:跨云数据仓库(data warehouse)环境搭建,这货特别干!
[graph theory] topological sorting
[odx Studio Edit pdx] - 0.2 - Comment comparer deux fichiers pdx / odx
Actual combat simulation │ JWT login authentication
高配笔记本使用CAD搬砖时卡死解决记录
【ODX Studio編輯PDX】-0.2-如何對比Compare兩個PDX/ODX文件
Mysql database backup and recovery -- mysqldump command
Qualcomm WLAN framework learning (30) -- components supporting dual sta
MariaDB的Galera集群应用场景--数据库多主多活
[try to hack] wide byte injection
Pagoda 7.9.2 pagoda control panel bypasses mobile phone binding authentication bypasses official authentication
Redis入门完整教程:集合详解
ScriptableObject
Application of machine learning in housing price prediction
A complete tutorial for getting started with redis: getting to know redis for the first time
Phpcms paid reading function Alipay payment
EditPlus--用法--快捷键/配置/背景色/字体大小
【图论】拓扑排序