对DNA损伤结果的预测建模:使用增强机器学习技术对突变决定因素的分类
Surabhya Balasubramanian1,2, David Dayanidhi1,2, Harini Velmurugan1,2
1Advanced Materials Laboratory, CSIR-Central Leather Research Institute, Sardar Patel Road, Adyar, Chennai 600020, India.
Chemical research in toxicology
|October 14, 2025
概括
机器学习模型预测化学损伤导致的DNA突变结果. 一个新的引导变量自编码器 (BT-VAE) 框架提高了40%的预测准确性,帮助毒理学研究.
科学领域:
- 计算毒理学计算毒理学
- 分子生物学分子生物学
- 在生物信息学中的机器学习.
背景情况:
- 化学物质暴露导致的DNA损伤可能导致突变,受损伤结构,复制和修复机制的影响.
- 诸如 adduct 尺寸,侧面基和 DNA 聚合酶类型等因素对于确定突变结果至关重要.
- 现有的体外和体内研究强调了预测这些结果的复杂性.
研究的目的:
- 开发机器学习 (ML) 模型,用于预测聚合酶遇到的DNA添加物的突变结果.
- 确定影响DNA突变结果的关键参数.
- 通过生成网络方法和先进的分类器提高预测准确度.
主要方法:
- 训练后勤回归 (LR),决策树 (DT) 和支持矢量机器 (SVM) 模型使用DNA附加和基底站点的文献数据.
- 使用生成网络 (引导变量自编码器 - BT-VAE) 创建模拟现实世界DNA损伤场景的合成数据.
- 使用极端梯度增强分类器来确定影响突变结果的最有影响力的参数.
主要成果:
- 拟议的BT-VAE模型显著提高了分类器预测准确度的40%.
- 支持矢量机 (SVM) 模型在所有评估的分类指标中表现出卓越的性能.
- 该BT-VAE框架成功地预测了突变结果 (添加物的匹配/不匹配,基底部的腺因/非腺因),使用添加物大小,聚合酶和侧面基作为输入.
结论:
- 机器学习,特别是与SVM结合的BT-VAE框架,为预测DNA突变结果提供了强大的工具.
- 这种方法为体内和体外毒理学研究提供了宝贵的见解.
- 准确预测突变类型有助于理解化学突变发生和致癌的机制.
相关概念视频
Overview of DNA Repair
33.4K
In order to be passed through generations, genomic DNA must be undamaged and error-free. However, every day, DNA in a cell undergoes several thousand to a million damaging events by natural causes and external factors. Ionizing radiation such as UV rays, free radicals produced during cellular respiration, and hydrolytic damage from metabolic reactions can alter the structure of DNA. Damages caused include single-base alteration, base dimerization, chain breaks, and cross-linkage.
Chemically...
Chemically...
33.4K
Spontaneous and Induced Mutations
2.1K
Spontaneous mutations arise infrequently during DNA replication due to errors in the process. A key factor behind these errors is tautomeric shifts in nitrogenous bases, where bases transition from keto to enol forms or amino to imino forms. This shift can alter base-pairing rules, leading to mutations. Additionally, reactive oxygen species (ROS) arising from aerobic metabolism can damage DNA, resulting in depurination (loss of a purine base) or depyrimidination (loss of a pyrimidine base).
2.1K
Mismatch Repair
6.3K
Organisms are capable of detecting and fixing nucleotide mismatches that occur during DNA replication. This sophisticated process requires identifying the new strand and replacing the erroneous bases with correct nucleotides. Mismatch repair is coordinated by many proteins in both prokaryotes and eukaryotes.
The Mutator Protein Family Plays a Key Role in DNA Mismatch Repair
The human genome has more than 3 billion base pairs of DNA per cell. Prior to cell division, that vast amount of genetic...
The Mutator Protein Family Plays a Key Role in DNA Mismatch Repair
The human genome has more than 3 billion base pairs of DNA per cell. Prior to cell division, that vast amount of genetic...
6.3K
Mismatch Repair
43.5K
Overview
43.5K
Mutagenicity and Carcinogenicity
1.9K
Mutagenicity and carcinogenicity refer to the ability of drugs to cause genetic defects and induce cancer, respectively. The International Agency for Research on Cancer (IARC) classifies agents into four groups based on their carcinogenic potential. Group 1 agents are known human carcinogens; group 2A agents are probably carcinogenic to humans; group 3 agents lack data to support their role in carcinogenesis; and group 4 includes agents for which data support that they are not likely to be...
1.9K
Nucleotide Excision Repair
5.0K
DNA Distortion and Damage
Cells are regularly exposed to mutagens—factors in the environment that can damage DNA and generate mutations. UV radiation is one of the most common mutagens and is estimated to introduce a significant number of changes in DNA. These include bends or kinks in the structure, which can block DNA replication or transcription. If these errors are not fixed, the damage can cause mutations, which in turn can result in cancer or disease depending on which sequences are...
Cells are regularly exposed to mutagens—factors in the environment that can damage DNA and generate mutations. UV radiation is one of the most common mutagens and is estimated to introduce a significant number of changes in DNA. These include bends or kinks in the structure, which can block DNA replication or transcription. If these errors are not fixed, the damage can cause mutations, which in turn can result in cancer or disease depending on which sequences are...
5.0K


