Machine learning for predicting lifespan-extending chemical compounds

Abstract

Increasing age is a risk factor for many diseases; therefore developing pharmacological interventions that slow down ageing and consequently postpone the onset of many age-related diseases is highly desirable. In this work we analyse data from the DrugAge database, which contains chemical compounds and their effect on the lifespan of model organisms. Predictive models were built using the machine learning method random forests to predict whether or not a chemical compound will increase Caenorhabditis elegans’ lifespan, using as features Gene Ontology (GO) terms annotated for proteins targeted by the compounds and chemical descriptors calculated from each compound's chemical structure. The model with the best predictive accuracy used both biological and chemical features, achieving a prediction accuracy of 80%. The top 20 most important GO terms include those related to mitochondrial processes, to enzymatic and immunological processes, and terms related to metabolic and transport processes. We applied our best model to predict compounds which are more likely to increase C. elegans’ lifespan in the DGIdb database, where the effect of the compounds on an organism's lifespan is unknown. The top hit compounds can be broadly divided into four groups: compounds affecting mitochondria, compounds for cancer treatment, anti-inflammatories, and compounds for gonadotropin-releasing hormone therapies.

Human Ageing Genomic Resources: 2018 Update

“…This was recently demonstrated in one study where machine learning was used to predict whether a compound would increase lifespan in worms using data from DrugAge. The best model had 80% prediction accuracy and the top hit compounds could broadly be divided into compounds affecting mitochondria, inflammation, cancer, and gonadotropin-releasing hormone (37). These compounds could all be targets for experimental validation.…”

Studying the geroprotective effects of inhibitors suppressing aging -associated signaling cascades in model organisms

“…Thus, online services and commercial packages that carry out molecular docking through a wide range of mathematical methods are widely spread [7,19,31,34]. Another powerful tool for anti-aging therapy selection is a set of algorithms that implement machine learning on big data [5].…”

“…А new opportunity for predicting lifespan-extending chemical compounds provides the using of a computational tools and predictive machine learning methods [1,5].…”

Autophagy dark genes: Can we find them with machine learning?

“…This on-going endeavor is boosted in part by the growing interest in the role of autophagy in ageing regulation [13,14] and lifespan extension [15]. ATG genes have been used in supervised machine learning models applied to ageing research [16] and are among the top features in models for predicting lifespan-extending chemicals [17]. Numerous studies have used machine learning (ML) methods to infer gene-disease associations [18][19][20][21].…”