RESUMEN

Computational approaches are widely applied in drug discovery to explore properties related to bioactivity, physiochemistry, and toxicology. Over at least the last 20 years, the exploitation of machine learning on molecular data sets has been used to understand the structure-activity relationships that exist between biomolecules and druggable targets. More recently, these methods have also seen application for phenotypic screening data for neglected diseases such as tuberculosis and malaria. Herein, we apply machine learning to build quantum Quantitative Structure Activity Relationship models from antimalarial data sets. There is a continual need for new antimalarials to address drug resistance, and the readily available in vitro data sets could be utilized with newer machine learning approaches as these develop. Furthermore, quantum machine learning is a relatively new method that uses a quantum computer to perform the calculations. First, we present a classical-quantum hybrid computational approach by building a Latent Bernoulli Autoencoder machine learning model for compressing bit-vector descriptors to a size that can be adapted to quantum computers for classification tasks with limited loss of embedded information. Second, we apply our method for feature map compression to quantum classification algorithms, including a completely novel machine learning algorithm with no analogy in classical computers: the Quantum Fourier Transform Classifier. We apply both these approaches to build quantum machine learning models for small-molecule antimalarials with quantum simulation software and then benchmark these quantum models against classical machine learning approaches. While there are many challenges currently facing the development of reliable quantum computers, our results demonstrate that there is potential for the use of this technology in the field of drug discovery.

Asunto(s)

RESUMEN

Colloidal particles with anisotropic shapes and interactions display rich phase behavior and have potential as structural bases for materials with controllable properties. In this paper, we explore the self-assembling characteristics of a new class of particles that have been shown experimentally to form reconfigurable structures: microscopic cube-shaped colloids with a magnetic dipole that is transversely offset from the particle's center of mass. We have performed in silico simulations of the dynamics of large numbers of dipolar squares in two-dimensions using discontinuous molecular dynamics (DMD). We use a coarse-grain method where the dipolar microcubes are represented by a group of four hard circles bonded together to create a rigid square in two-dimensions and two opposite charges are embedded within the square to represent a magnetic dipole. Annealing, or "slow-cooling", simulations are conducted to determine the equilibrium structures. Systems of dipolar squares tend to assemble into one of two different types of conformations: either single- or double-stranded assemblies, each with unique structures and phase diagrams in the temperature-density plane. Single-stranded assemblies form highly interconnected percolated, or gel-like, networks. In contrast, double stranded assemblies tend to form globally-aligned nematic states at high densities, although this is not seen consistently in all runs. The phase behavior of systems of dipolar squares depends not only on the system's temperature and density, but also on the type of dipole embedded within the square and on the relative number of squares with an opposite "handedness" that are present within the system.