相关实验视频

Updated: Feb 23, 2026

Predictive Immune Modeling of Solid Tumors

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

针对DNA编码库的可通用预测模型

Vasanthanathan Poongavanam¹, S Pauliina Turunen², Kristian Sandberg²

¹Drug Discovery and Development Platform, Science for Life Laboratory, Department of Medicinal Chemistry, BMC, Uppsala University, Box 574, SE-751 23 Uppsala, Sweden.

Drug discovery today

|February 21, 2026

概括

用DNA编码的库 (DEL) 和机器学习 (ML) 加快了药物发现,但也面临着挑战. 本综述强调了噪音数据和模型过拟合的问题,并提出了更强大的化学空间探索的解决方案.

科学领域:

药物发现药物发现药物发现
计算化学计算化学
生物技术是生物技术.

背景情况:

与机器学习 (ML) 结合的DNA编码库 (DEL) 为药物发现中成功识别提供了强大的方法.
来自DEL的测序数据可能会噪音和偏差,导致ML模型过度适应特定的化学库.

研究的目的:

批判性地评估DEL-ML在命中识别方面的能力和局限性.
用 Aurora Kinase A (AURKA) 亲和力选择数据来说明DEL-ML中的挑战.
提出构建强大的DEL-ML模型的策略.

主要方法:

审查现有的DEL-ML方法.
对光激酶A (AURKA) DEL亲和力选择数据的分析.
评估消除噪音的策略和领域适应技术.

主要成果:

由于特定于图书馆的结构约束,标准的ML模型往往无法将其推广到新的化学空间.
噪音和偏差测序数据显著影响了DEL-ML模型的性能.
结合式库中的特定结构约束限制了模型的概括性.

结论:

严格的否认策略对于有效的DEL-ML是必不可少的.
像域调整这样的技术可以帮助减轻局限性并提高模型的稳定性.
提出了一份路线图,用于开发能够有效探索各种化学空间的DEL-ML模型.

关键词:

阿尔卡奥尔卡 (AURKA AURKA) 是一个一个DNA编码的图书馆.化学空间化学空间域名适应域名适应可以概括的概括性.机器学习是机器学习.

更多相关视频

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay EMSA and DNA-affinity Precipitation Assay DAPA

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay EMSA and DNA-affinity Precipitation Assay DAPA

Published on: August 21, 2016

Automated Gel Size Selection to Improve the Quality of Next-generation Sequencing Libraries Prepared from Environmental Water Samples

Automated Gel Size Selection to Improve the Quality of Next-generation Sequencing Libraries Prepared from Environmental Water Samples

Published on: April 17, 2015

相关概念视频

Evolutionary Relationships through Genome Comparisons

Evolutionary Relationships through Genome Comparisons

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...