Integrative Genomics of Ageing Group, Institute of Life Course and Medical Sciences, University of Liverpool, 6 West Derby St, Liverpool, L7 8TX, UK.
School of Computer Technologies and Controls, ITMO University, Kronverkskiy Prospekt 49, 197101, St Petersburg, Russia.
BMC Bioinformatics. 2022 Jan 4;23(1):10. doi: 10.1186/s12859-021-04523-8.
Dietary restriction (DR) is the most studied pro-longevity intervention; however, a complete understanding of its underlying mechanisms remains elusive, and new research directions may emerge from the identification of novel DR-related genes and DR-related genetic features.
This work used a Machine Learning (ML) approach to classify ageing-related genes as DR-related or NotDR-related using 9 different types of predictive features: PathDIP pathways, two types of features based on KEGG pathways, two types of Protein-Protein Interactions (PPI) features, Gene Ontology (GO) terms, Genotype Tissue Expression (GTEx) expression features, GeneFriends co-expression features and protein sequence descriptors. Our findings suggested that features biased towards curated knowledge (i.e. GO terms and biological pathways), had the greatest predictive power, while unbiased features (mainly gene expression and co-expression data) have the least predictive power. Moreover, a combination of all the feature types diminished the predictive power compared to predictions based on curated knowledge. Feature importance analysis on the two most predictive classifiers mostly corroborated existing knowledge and supported recent findings linking DR to the Nuclear Factor Erythroid 2-Related Factor 2 (NRF2) signalling pathway and G protein-coupled receptors (GPCR). We then used the two strongest combinations of feature type and ML algorithm to predict DR-relatedness among ageing-related genes currently lacking DR-related annotations in the data, resulting in a set of promising candidate DR-related genes (GOT2, GOT1, TSC1, CTH, GCLM, IRS2 and SESN2) whose predicted DR-relatedness remain to be validated in future wet-lab experiments.
This work demonstrated the strong potential of ML-based techniques to identify DR-associated features as our findings are consistent with literature and recent discoveries. Although the inference of new DR-related mechanistic findings based solely on GO terms and biological pathways was limited due to their knowledge-driven nature, the predictive power of these two features types remained useful as it allowed inferring new promising candidate DR-related genes.
饮食限制（DR）是研究最多的长寿干预措施；然而，其潜在机制仍难以理解，新的研究方向可能会从鉴定新的 DR 相关基因和 DR 相关遗传特征中出现。
本研究使用机器学习（ML）方法，使用 9 种不同类型的预测特征将与衰老相关的基因分类为 DR 相关或非 DR 相关：PathDIP 途径、两种基于 KEGG 途径的特征、两种蛋白质-蛋白质相互作用（PPI）特征、基因本体论（GO）术语、基因型组织表达（GTEx）表达特征、GeneFriends 共表达特征和蛋白质序列描述符。我们的研究结果表明，偏向于已审定知识（即 GO 术语和生物途径）的特征具有最大的预测能力，而无偏差的特征（主要是基因表达和共表达数据）的预测能力最小。此外，与基于已审定知识的预测相比，所有特征类型的组合降低了预测能力。对两个最具预测性的分类器的特征重要性分析主要证实了现有知识，并支持了最近的发现，即 DR 与核因子红细胞 2 相关因子 2（NRF2）信号通路和 G 蛋白偶联受体（GPCR）有关。然后，我们使用两种最强的特征类型和 ML 算法组合来预测当前数据中缺乏 DR 相关注释的与衰老相关基因的 DR 相关性，得出了一组有前途的候选 DR 相关基因（GOT2、GOT1、TSC1、CTH、GCLM、IRS2 和 SESN2），其预测的 DR 相关性仍有待未来的湿实验室实验验证。
这项工作证明了基于 ML 的技术识别 DR 相关特征的强大潜力，因为我们的研究结果与文献和最近的发现一致。尽管由于其知识驱动的性质，仅基于 GO 术语和生物途径推断新的 DR 相关机制发现的推断受到限制，但这两种特征类型的预测能力仍然很有用，因为它允许推断新的有前途的候选 DR 相关基因。
