The fundamental goal of generative drug design is to propose optimized molecules that meet predefined activity, selectivity, and pharmacokinetic criteria. Despite recent progress, we argue that existing generative methods are limited in their ability to favourably shift the distributions of molecular properties during optimization. We instead propose a novel Reinforcement Learning framework for molecular design in which an agent learns to directly optimize through a space of synthetically-accessible drug-like molecules. This becomes possible by defining transitions in our Markov Decision Process as chemical reactions, and allows us to leverage synthetic routes as an inductive bias. We validate our method by demonstrating that it outperforms existing state-of the art approaches in the optimization of pharmacologically-relevant objectives, while results on multi-objective optimization tasks suggest increased scalability to realistic pharmaceutical design problems.
andBeyond（99andBeyond）；Clemson University（克莱姆森大学）；IIIT Hyderabad（海得拉巴国际信息技术学院）；University of Delaware（特拉华大学）；University of Montreal（蒙特利尔大学）；Mila - Quebec AI Institute（Mila - 魁北克人工智能研究所）；HEC Montréal（蒙特利尔高等商学院）
Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models. However, current generative approaches exhibit a significant challenge as they do not ensure that the proposed molecular structures can be feasibly synthesized nor do they provide the synthesis routes of the proposed small molecules, thereby seriously limiting their practical applicability. In this work, we propose a novel forward synthesis framework powered by reinforcement learning (RL) for de novo drug design, Policy Gradient for Forward…
Transition metal chromophores with earth-abundant transition metals are an important design target for their applications in lighting and non-toxic bioimaging, but their design is challenged by the scarcity of complexes that simultaneously have optimal target absorption energies in the visible region as well as well-defined ground states. Machine learning (ML) accelerated discovery could overcome such challenges by enabling screening of a larger space, but is limited by the fidelity of the data used in ML model training, which is typically from a single approximate density functional. To addre…
The size and quality of chemical libraries to the drug discovery pipeline are crucial for developing new drugs or repurposing existing drugs. Existing techniques such as combinatorial organic synthesis and High-Throughput Screening usually make the process extraordinarily tough and complicated since the search space of synthetically feasible drugs is exorbitantly huge. While reinforcement learning has been mostly exploited in the literature for generating novel compounds, the requirement of designing a reward function that succinctly represents the learning objective could prove daunting in ce…
Generating readily synthesizable small molecule fluorophore scaffolds with reinforcement learning
Department of Computer Science, Stanford University（计算机科学系，斯坦福大学）；Department of Molecular and Cellular Physiology, Stanford University（分子与细胞生理学系，斯坦福大学）；Department of Physics, Stanford University（物理系，斯坦福大学）；Department of Biomedical Data Science, Stanford University（生物医学数据科学系，斯坦福大学）；Department of Biochemistry and Molecular Genetics, University of Colorado Anschutz Medical Campus（生物化学与分子遗传学系，科罗拉多大学安舒茨医学校区）；Department of Pharmacology, University of Colorado Anschutz Medical Campus（药理学系，科罗拉多大学安舒茨医学校区）；Department of Pharmaceutical Sciences, Skaggs School of Pharmacy, University of Colorado Anschutz Medical Campus（药学系，斯克格斯药学院，科罗拉多大学安舒茨医学校区）；BioFrontiers Institute, University of Colorado Boulder（生物前沿研究院，科罗拉多大学波德分校）；Greenstone Biosciences（Greenstone 生物科技公司）；Stanford University（斯坦福大学）
SynTwins: A Retrosynthesis-Guided Framework for Synthesizable Molecular Analog Generation
Seoul National University（首尔大学）；University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（向量人工智能研究院）；Canadian Institute for Advanced Research（加拿大高等研究院）
Generative Chemical Language Models for Energetic Materials Discovery
Theoretical Division, Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室理论部）；Weapon Stockpile Modernization Division, Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室武器库存现代化部）；Computing and Artificial Intelligence Division, Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室计算与人工智能部）
Due to its favorable computational efficiency time-dependent (TD) density functional theory (DFT) enables the prediction of electronic spectra in a high-throughput manner across chemical space. Its predictions, however, can be quite inaccurate. We resolve this issue with machine learning models trained on deviations of reference second-order approximate coupled-cluster singles and doubles (CC2) spectra from TDDFT counterparts, or even from DFT gap. We applied this approach to low-lying singlet-singlet vertical electronic spectra of over 20 thousand synthetically feasible small organic molecule…
The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amount of data amenable to intelligent data analysis for the identification of meaningful, novel, and predictive structure-property relationships. Such relationships enable high-throughput screening for relevant properties in an exponentially growing pool of virtual compounds that are synthetically accessible. Here, we present a machine learning (ML) model, trained on a data base of \textit{ab initio} calculation results for thousands of organic molecules, that simultaneously predicts m…
QSAR-Guided Generative Framework for the Discovery of Synthetically Viable Odorants
Biomedical Engineering Research Group, School of Engineering, University of Leicester（利兹大学工程学院生物医学工程研究组）；School of Clinical Medicine, University of Cambridge（剑桥大学临床医学学院）
To accelerate exploration of chemical space, it is necessary to identify the compounds that will provide the most additional information or value. A large-scale analysis of mononuclear octahedral transition metal complexes deposited in an experimental database confirms an under-representation of lower-symmetry complexes. From a set of around 1000 previously studied Fe(II) complexes, we show that the theoretical space of synthetically accessible complexes formed from the relatively small number of unique ligands is significantly (ca. 816k) larger. For the properties of these complexes, we valid…
I propose a novel approach to balancing equations that is applicable to all chemical-reaction equations; it is readily accessible to students via scientific calculators and basic computer spreadsheets that have a matrix-inversion application. The new approach utilizes the familiar matrix-inversion operation in an unfamiliar and innovative way; its purpose is not to identify undetermined coefficients as usual, but, instead, to compute a matrix null space (or matrix kernel). The null space then provides the coefficients that balance the equation. Indeed, the null space contains everything there …
We show that products of the isotopic substitution reactions in experimentally accessible molecules such as NaK, RbCs, and SrF are cold according to their translational energy below hundreds of mK. For these chemical reactions, molecular products may occupy only the lowest rotational states. We also discuss the possibility of controlling the chemical reactions by the electric field in ultracold mixtures of molecules and atoms with low kinetic energy release, where one of the constituent atoms of colliding molecule is replaced by its isotope. This letter opens new avenues in investigating the b…
