关于真实验证分子生成模型的困难:对公开和专有数据的案例研究
Koichi Handa1,2, Morgan C Thomas3, Michiharu Kageyama4
1Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK. ko.handa@teijin.co.jp.
Journal of cheminformatics
|November 22, 2023
概括
生成模型努力从早期数据中重新发现中期/后期药物化合物. 对新分子设计的追溯验证具有挑战性,突出了算法设计和现实世界药物发现过程之间的差异.
科学领域:
- *计算化学和化学信息学.
- * 药物发现中的人工智能.
背景情况:
- * 验证深度生成模型用于de novo分子设计缺乏既定的最佳实践.
- * 追溯验证可能有偏见,而前性验证是昂贵的,并受到人类选择偏见的影响.
- *评估生成模型需要模仿现实世界药物设计过程的方法.
研究的目的:
- * 评估在早期阶段化合物上训练的生成模型是否可以重新生成中/后阶段化合物.
- *将追溯验证视为模仿人类药物设计的能力.
- * 在现实世界药物发现项目中研究生成模型的性能.
主要方法:
- *利用了来自五个公共和六个内部药物发现项目的实验数据.
- * 预处理的时间序列数据,以反映现实的合成扩展.
- *使用REINVENT,一种基于循环神经网络 (RNN) 的生成模型.
- * 分开数据集并对早期化合物进行训练 REINVENT.
主要成果:
- *与内部项目 (0.00%) 相比,公共项目中的中/后期复合物重新发现率明显高 (例如,前100个项目中的1.60%).
- *近邻相似性分析揭示了公共与内部项目的活性和非活性化合物之间的明显模式.
- *生成模型回收了很少的中期/后期化合物,这表明算法设计和实际药物发现之间存在差距.
结论:
- *生成模型从现实世界药物发现项目中恢复了有限数量的中期/后期化合物.
- *纯粹算法 de novo 设计与现实世界药物发现的复杂性之间存在着根本的区别.
- * 对新型复合物设计方法的回顾性评估目前很困难或可能是不可能的.
相关概念视频
Data Validation
5.1K
Data validation is an essential part of a comprehensive assessment. Validation is confirming or verifying and opening the door to gathering more assessment data as it clarifies vague or unclear data. The process of checking and verifying the collected information is called data validation. The primary purpose of data validation is to ensure data is as free from error, bias, and misinterpretation as possible.
Nursing assessment guides are generally based on holistic models rather than medical...
Nursing assessment guides are generally based on holistic models rather than medical...
5.1K
Pedigree Analysis
84.3K
Overview
84.3K
Evolutionary Relationships through Genome Comparisons
5.8K
Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
5.8K
Genetic Lingo
102.9K
Overview
102.9K
Genetic Variation
293
Genetic variation is the diversity in DNA sequences found among individuals of the same species. This diversity is crucial for a species' survival because it helps organisms adapt to environmental changes. Genetic variation begins with fertilization, where an egg and sperm cell merge. Each of these cells carries 23 chromosomes, up to 46 in the fertilized egg. Chromosomes are long DNA strands that contain genes, the basic units of heredity.
Genes exist in different versions called alleles,...
Genes exist in different versions called alleles,...
293
Genome Annotation and Assembly
18.9K
The genome refers to all of the genetic material in an organism. It can range from a few million base pairs in microbial cells to several billion base pairs in many eukaryotic organisms. Genome assembly refers to the process of taking the DNA sequencing data and putting it all back together in a correct order to create a close representation of the original genome. This is followed by the identification of functional elements on the newly assembled genome, a process called genome annotation.
18.9K


