Discovering Highly Potent Molecules from an Initial Set of Inactives Using Iterative Screening

Abstract

The versatility of similarity searching and quantitative structure-activity relationships to model the activity of compound sets within given bioactivity ranges (i.e., interpolation) is well established. However, their relative performance in the common scenario in early stage drug discovery where lots of inactive data but no active data points are available (i.e., extrapolation from the low-activity to the high-activity range) has not been thoroughly examined yet. To this aim, we have designed an iterative virtual screening strategy which was evaluated on 25 diverse bioactivity data sets from ChEMBL. We benchmark the efficiency of random forest (RF), multiple linear regression, ridge regression, similarity searching, and random selection of compounds to identify a highly active molecule in the test set among a large number of low-potency compounds. We use the number of iterations required to find this active molecule to evaluate the performance of each experimental setup. We show that linear and ridge regression often outperform RF and similarity searching, reducing the number of iterations to find an active compound by a factor of 2 or more. Even simple regression methods seem better able to extrapolate to high-bioactivity ranges than RF, which only provides output values in the range covered by the training set. In addition, examination of the scaffold diversity in the data sets used shows that in some cases similarity searching and RF require two times as many iterations as random selection depending on the chemical space covered in the initial training data. Lastly, we show using bioactivity data for COX-1 and COX-2 that our framework can be extended to multitarget drug discovery, where compounds are selected by concomitantly considering their activity against multiple targets. Overall, this study provides an approach for iterative screening where only inactive data are present in early stages of drug discovery in order to discover highly potent compounds and the best experimental set up in which to do so.

Reply to “Missed opportunities in large scale comparison of QSAR and conformal prediction methods and their applications in drug discovery”

“…We are also happy to clarify that the errors bars in Figs. 3 and 4, and the ± values indicated in the text or in the tables all correspond to the standard deviation over the relevant population, consistent with standard practice [5, 6].…”

Reliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout

“…We firstly compared the performance on the test set of DNN, using dropout probabilities in all layers of either 0.1, 0.25 or 0.5, and RF models ( Figure 2 in line with models reported in the literature for similar data sets 38 . Hence, the models obtained here are likely approaching the upper performance limit which can be obtained for the datasets used, which is also a likely factor behind the very similar performance obtained across methods.…”

Novel natural and synthetic inhibitors of solute carriers SGLT1 and SGLT2

“…Hence, the model is used to identify data points that lead to the highest information gain (exploration) as opposed to identify newly active data points (exploitation). Previously this approach was shown to lead to a quick improvement in biological activity . Accordingly, using the current and a public dataset, a first PCM SGLT1 screening model was developed that effectively predicted moderately active SGLT1 inhibitors outside the chemical space of the training set .…”