Bayesian Sequential Stacking Algorithm for Concurrently Designing
Molecules and Synthetic Reaction Networks
- URL: http://arxiv.org/abs/2204.01847v1
- Date: Tue, 1 Mar 2022 14:55:32 GMT
- Title: Bayesian Sequential Stacking Algorithm for Concurrently Designing
Molecules and Synthetic Reaction Networks
- Authors: Qi Zhang, Chang Liu, Stephen Wu and Ryo Yoshida
- Abstract summary: We present a powerful sequential Monte Carlo algorithm that sequentially designs a synthetic reaction network by building up single-step reactions.
In a case study of designing drug-like molecules based on commercially available compounds, the proposed method shows overwhelming performance in terms of computational efficiency and coverage.
- Score: 11.787915018281897
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In the last few years, de novo molecular design using machine learning has
made great technical progress but its practical deployment has not been as
successful. This is mostly owing to the cost and technical difficulty of
synthesizing such computationally designed molecules. To overcome such
barriers, various methods for synthetic route design using deep neural networks
have been studied intensively in recent years. However, little progress has
been made in designing molecules and their synthetic routes simultaneously.
Here, we formulate the problem of simultaneously designing molecules with the
desired set of properties and their synthetic routes within the framework of
Bayesian inference. The design variables consist of a set of reactants in a
reaction network and its network topology. The design space is extremely large
because it consists of all combinations of purchasable reactants, often in the
order of millions or more. In addition, the designed reaction networks can
adopt any topology beyond simple multistep linear reaction routes. To solve
this hard combinatorial problem, we present a powerful sequential Monte Carlo
algorithm that recursively designs a synthetic reaction network by sequentially
building up single-step reactions. In a case study of designing drug-like
molecules based on commercially available compounds, compared with heuristic
combinatorial search methods, the proposed method shows overwhelming
performance in terms of computational efficiency and coverage and novelty with
respect to existing compounds.
Related papers
- Finding Optimal Pathways in Chemical Reaction Networks Using Ising
Machines [0.40792653193642503]
Finding optimal pathways in chemical reaction networks is essential for elucidating and designing chemical processes.
Due to explosion, the time required to find an optimal pathway increases exponentially with the network size.
We present the first Ising/quantum computing application for chemical pathway-finding problems.
arXiv Detail & Related papers (2023-08-08T19:22:54Z) - Flowsheet synthesis through hierarchical reinforcement learning and
graph neural networks [0.4588028371034406]
We propose a reinforcement learning algorithm for chemical process design based on actor-critic logic.
Our proposed algorithm represents chemical processes as graphs and uses graph convolutional neural networks to learn from process graphs.
arXiv Detail & Related papers (2022-07-25T10:42:15Z) - Optimizing Tensor Network Contraction Using Reinforcement Learning [86.05566365115729]
We propose a Reinforcement Learning (RL) approach combined with Graph Neural Networks (GNN) to address the contraction ordering problem.
The problem is extremely challenging due to the huge search space, the heavy-tailed reward distribution, and the challenging credit assignment.
We show how a carefully implemented RL-agent that uses a GNN as the basic policy construct can address these challenges.
arXiv Detail & Related papers (2022-04-18T21:45:13Z) - Simulation Paths for Quantum Circuit Simulation with Decision Diagrams [72.03286471602073]
We study the importance of the path that is chosen when simulating quantum circuits using decision diagrams.
We propose an open-source framework that allows to investigate dedicated simulation paths.
arXiv Detail & Related papers (2022-03-01T19:00:11Z) - Amortized Tree Generation for Bottom-up Synthesis Planning and
Synthesizable Molecular Design [2.17167311150369]
We report an amortized approach to generate synthetic pathways as a Markov decision process conditioned on a target molecular embedding.
This approach allows us to conduct synthesis planning in a bottom-up manner and design synthesizable molecules by decoding from optimized conditional codes.
arXiv Detail & Related papers (2021-10-12T22:43:25Z) - Self-Improved Retrosynthetic Planning [66.5397931294144]
Retrosynthetic planning is a fundamental problem in chemistry for finding a pathway of reactions to synthesize a target molecule.
Recent search algorithms have shown promising results for solving this problem by using deep neural networks (DNNs)
We propose an end-to-end framework for directly training the DNNs towards generating reaction pathways with the desirable properties.
arXiv Detail & Related papers (2021-06-09T08:03:57Z) - RetroXpert: Decompose Retrosynthesis Prediction like a Chemist [60.463900712314754]
We devise a novel template-free algorithm for automatic retrosynthetic expansion.
Our method disassembles retrosynthesis into two steps.
While outperforming the state-of-the-art baselines, our model also provides chemically reasonable interpretation.
arXiv Detail & Related papers (2020-11-04T04:35:34Z) - Learning To Navigate The Synthetically Accessible Chemical Space Using
Reinforcement Learning [75.95376096628135]
We propose a novel forward synthesis framework powered by reinforcement learning (RL) for de novo drug design.
In this setup, the agent learns to navigate through the immense synthetically accessible chemical space.
We describe how the end-to-end training in this study represents an important paradigm in radically expanding the synthesizable chemical space.
arXiv Detail & Related papers (2020-04-26T21:40:03Z) - Deep Molecular Programming: A Natural Implementation of Binary-Weight
ReLU Neural Networks [7.700240949386079]
We show how a BinaryConnect neural network trained in silico can be compiled to an equivalent chemical reaction network.
Our work sets the stage for rich knowledge transfer between neural network and molecular programming communities.
arXiv Detail & Related papers (2020-03-30T18:12:11Z) - A Bayesian algorithm for retrosynthesis [3.1092085121563526]
This study is to discover synthetic routes backwardly from a given desired molecule to commercially available compounds.
A deep neural network is trained that forwardly predicts a product of the given reactants with a high level of accuracy.
Using the backward model, a diverse set of highly probable reaction sequences ending with a given synthetic target is exhaustively explored using a Monte Carlo search.
arXiv Detail & Related papers (2020-03-06T13:30:30Z) - Retrosynthesis Prediction with Conditional Graph Logic Network [118.70437805407728]
Computer-aided retrosynthesis is finding renewed interest from both chemistry and computer science communities.
We propose a new approach to this task using the Conditional Graph Logic Network, a conditional graphical model built upon graph neural networks.
arXiv Detail & Related papers (2020-01-06T05:36:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.