Rational drug design often starts from specific scaffolds to which side chains/substituents are added or modified due to the large drug-like chemical space available to search for novel drug-like... Show moreRational drug design often starts from specific scaffolds to which side chains/substituents are added or modified due to the large drug-like chemical space available to search for novel drug-like molecules. With the rapid growth of deep learning in drug discovery, a variety of effective approaches have been developed for de novo drug design. In previous work we proposed a method named DrugEx, which can be applied in polypharmacology based on multi-objective deep reinforcement learning. However, the previous version is trained under fixed objectives and does not allow users to input any prior information (i.e. a desired scaffold). In order to improve the general applicability, we updated DrugEx to design drug molecules based on scaffolds which consist of multiple fragments provided by users. Here, a Transformer model was employed to generate molecular structures. The Transformer is a multi-head self-attention deep learning model containing an encoder to receive scaffolds as input and a decoder to generate molecules as output. In order to deal with the graph representation of molecules a novel positional encoding for each atom and bond based on an adjacency matrix was proposed, extending the architecture of the Transformer. The graph Transformer model contains growing and connecting procedures for molecule generation starting from a given scaffold based on fragments. Moreover, the generator was trained under a reinforcement learning framework to increase the number of desired ligands. As a proof of concept, the method was applied to design ligands for the adenosine A2A receptor (A2AAR) and compared with SMILES-based methods. The results show that 100% of the generated molecules are valid and most of them had a high predicted affinity value towards A2AAR with given scaffolds. Show less
Winter, R. de; Bronkhorst, P.; Stein, B. van; Bäck, T.H.W. 2022
This paper proposes the Self-Adaptive algorithm for Multi-Objective Constrained Optimization by using Radial Basis Function Approximations, SAMO-COBRA. This algorithm automatically determines the... Show moreThis paper proposes the Self-Adaptive algorithm for Multi-Objective Constrained Optimization by using Radial Basis Function Approximations, SAMO-COBRA. This algorithm automatically determines the best Radial Basis Function-fit as surrogates for the objectives as well as the constraints, to find new feasible Pareto-optimal solutions. SAMO-COBRA is compared to a wide set of other state-of-the-art algorithms (IC-SA-NSGA-II, SA-NSGA-II, NSGA-II, NSGA-III, CEGO, SMES-RBF) on 18 constrained multi-objective problems. In the first experiment, SAMO-COBRA outperforms the other algorithms in terms of achieved Hypervolume (HV) after being given a fixed small evaluation budget on the majority of test functions. In the second experiment, SAMO-COBRA outperforms the majority of competitors in terms of required function evaluations to achieve 95% of the maximum achievable Hypervolume. In addition to academic test functions, SAMO-COBRA has been applied on a real-world ship design optimization problem with three objectives, two complex constraints, and five decision variables. Show less
Staalduinen, J.H. van; Tetteroo, J.; Gawehns, D.; Baratchi, M. 2021
How do we make sure that all citizens in a city have access to enough green space? An increasing part of the world’s population lives in urban areas, where contact with nature is largely reduced to... Show moreHow do we make sure that all citizens in a city have access to enough green space? An increasing part of the world’s population lives in urban areas, where contact with nature is largely reduced to street trees and parks. As optional tree planting sites and financial resources are limited, determining the best planting site can be formulated as an optimization problem with constraints. Can we locate these sites based on the popularity of nearby venues? How can we ensure that we include groups of people who tend to spend time in tree deprived areas?Currently, tree location sites are chosen based on criteria from spatial-visual, physical and biological, and functional categories. As these criteria do not give any insights into which citizens are benefiting from the tree placement, we propose new data-driven tree planting policies that take socio-cultural aspects as represented by the citizens’ behavior into account. We combine a Location Based Social Network (LBSN) mobility data set with tree location data sets, both of New York City and Paris, as a case study. The effect of four different policies is evaluated on simulated movement data and assessed on the average, overall exposure to trees as well as on how much inequality in tree exposure is mitigated. Show less