Using human in vitro transcriptome analysis to build trustworthy machine learning models for prediction of animal drug toxicity

Abstract

During the development of new drugs or compounds there is a requirement for preclinical trials, commonly involving animal tests, to ascertain the safety of the compound prior to human trials. Machine learning techniques could provide an in-silico alternative to animal models for assessing drug toxicity, thus reducing expensive and invasive animal testing during clinical trials, for drugs that are most likely to fail safety tests. Here we present a machine learning model to predict kidney dysfunction, as a proxy for drug induced renal toxicity, in rats. To achieve this, we use inexpensive transcriptomic profiles derived from human cell lines after chemical compound treatment to train our models combined with compound chemical structure information. Genomics data due to its sparse, high-dimensional and noisy nature presents significant challenges in building trustworthy and transparent machine learning models. Here we address these issues by judiciously building feature sets from heterogenous sources and coupling them with measures of model uncertainty achieved through Gaussian Process based Bayesian models. We combine the use of insight into the feature-wise contributions to our predictions with the use of predictive uncertainties recovered from the Gaussian Process to improve the transparency and trustworthiness of the model.

Machine learning in the prediction of cancer therapy

“…Thus, a comprehensive method is needed that will not only determine drug synergy but also incorporate the adverse effect of drug combinations. Knowledge of safe and unsafe combinations of drugs was used to build a linear regression prediction model [152] , [153] , [154] . However, the model did not incorporate any biological data to elucidate patient-specific side effects.…”

Artificial intelligence methods to repurpose and discover new drugs to fight the Coronavirus disease-2019 pandemic

“…Another example is empirical scoring functions, which predict the binding affinity of ligands in docking simulations by adjusting experimentally calculated parameters ( Ashtawy and Mahapatra, 2018 , Guedes et al, 2014 ). Besides the applications mentioned above, ML can also be used to estimate an array of relevant quantitative parameters in drug discovery, including solubility, toxicity prediction, and plasma membrane permeability ( Boobier et al, 2020 , Feinberg et al, 2018 , Gardiner et al, 2020 , Mayr et al, 2016 ).…”

Interpreting machine learning models to investigate circadian regulation and facilitate exploration of clock function

“…Explainable AI was used to rank and select omic features as suggested by [75,76] and we investigated the explanations of the predictions for the DNA sequence-based ML model. Firstly, based on the best LightGBM model for the Arabidopsis Col-0 dataset from [8] on which the model was trained (i.e.…”