Research and Information Systems, LLC, 1620 E. 72nd ST., Indianapolis, IN, 46240, USA.
Physics Department, Indiana University Purdue University Indianapolis, Indianapolis, IN, 46202, USA.
Hum Genomics. 2024 Aug 27;18(1):89. doi: 10.1186/s40246-024-00655-z.
We describe the machine learning tool that we applied in the CAGI 6 experiment to predict whether single residue mutations in proteins are deleterious or benign. This tool was trained using only single sequences, i.e., without multiple sequence alignments or structural information. Instead, we used global characterizations of the protein sequence. Training and testing data for human gene mutations was obtained from ClinVar (ncbi.nlm.nih.gov/pub/ClinVar/), and for non-human gene mutations from Uniprot (www.uniprot.org). Testing was done on post-training data from ClinVar. This testing yielded high AUC and Matthews correlation coefficient (MCC) for well trained examples but low generalizability. For genes with either sparse or unbalanced training data, the prediction accuracy is poor. The resulting prediction server is available online at http://www.mamiris.com/Shoni.cagi6.
我们描述了在 CAGI 6 实验中应用的机器学习工具，用于预测蛋白质中的单个残基突变是有害的还是良性的。该工具仅使用单个序列进行训练，即不使用多序列比对或结构信息。相反，我们使用了蛋白质序列的全局特征。人类基因突变的训练和测试数据来自 ClinVar（ncbi.nlm.nih.gov/pub/ClinVar/），非人类基因突变的数据来自 Uniprot（www.uniprot.org）。测试是在 ClinVar 的培训后数据上进行的。对于训练有素的示例，该测试产生了较高的 AUC 和马修斯相关系数（MCC），但通用性较低。对于训练数据稀疏或不平衡的基因，预测准确性较差。生成的预测服务器可在线获得，网址为 http://www.mamiris.com/Shoni.cagi6。
