SynFlowNet: Towards Molecule Design with Guaranteed Synthesis Pathways
- URL: http://arxiv.org/abs/2405.01155v1
- Date: Thu, 2 May 2024 10:15:59 GMT
- Title: SynFlowNet: Towards Molecule Design with Guaranteed Synthesis Pathways
- Authors: Miruna Cretu, Charles Harris, Julien Roy, Emmanuel Bengio, Pietro LiĆ²,
- Abstract summary: We introduce SynFlowNet, a GFlowNet model whose action space uses chemically validated reactions and reactants to sequentially build new molecules.
We evaluate our approach using synthetic accessibility scores and an independent retrosynthesis tool.
We compare molecules designed with SynFlowNet to experimentally validated actives, and find that they show comparable properties of interest, such as molecular weight, SA score and predicted protein binding affinity.
- Score: 17.704264588418035
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent breakthroughs in generative modelling have led to a number of works proposing molecular generation models for drug discovery. While these models perform well at capturing drug-like motifs, they are known to often produce synthetically inaccessible molecules. This is because they are trained to compose atoms or fragments in a way that approximates the training distribution, but they are not explicitly aware of the synthesis constraints that come with making molecules in the lab. To address this issue, we introduce SynFlowNet, a GFlowNet model whose action space uses chemically validated reactions and reactants to sequentially build new molecules. We evaluate our approach using synthetic accessibility scores and an independent retrosynthesis tool. SynFlowNet consistently samples synthetically feasible molecules, while still being able to find diverse and high-utility candidates. Furthermore, we compare molecules designed with SynFlowNet to experimentally validated actives, and find that they show comparable properties of interest, such as molecular weight, SA score and predicted protein binding affinity.
Related papers
- RGFN: Synthesizable Molecular Generation Using GFlowNets [51.33672611338754]
We propose Reaction-GFlowNet, an extension of the GFlowNet framework that operates directly in the space of chemical reactions.
RGFN allows out-of-the-box synthesizability while maintaining comparable quality of generated candidates.
We demonstrate the effectiveness of the proposed approach across a range of oracle models, including pretrained proxy models and GPU-accelerated docking.
arXiv Detail & Related papers (2024-06-01T13:11:11Z) - Hybrid Quantum Generative Adversarial Networks for Molecular Simulation
and Drug Discovery [13.544339314714902]
Current classical computational power falls inadequate to simulate any more than small molecules.
Tens of billions of dollars are spent every year in these research experiments.
Deep generative models for graph-structured data provide fresh perspective on the issue of chemical synthesis.
arXiv Detail & Related papers (2022-12-15T13:36:35Z) - Retrieval-based Controllable Molecule Generation [63.44583084888342]
We propose a new retrieval-based framework for controllable molecule generation.
We use a small set of molecules to steer the pre-trained generative model towards synthesizing molecules that satisfy the given design criteria.
Our approach is agnostic to the choice of generative models and requires no task-specific fine-tuning.
arXiv Detail & Related papers (2022-08-23T17:01:16Z) - Barking up the right tree: an approach to search over molecule synthesis
DAGs [28.13323960125482]
Current deep generative models for molecules ignore synthesizability.
We propose a deep generative model that better represents the real world process.
We show that our approach is able to model chemical space well, producing a wide range of diverse molecules.
arXiv Detail & Related papers (2020-12-21T17:35:06Z) - RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De
Novo Drug Design [75.14290780116002]
We train deep graph neural networks to approximate the outputs of a retrosynthesis planning software.
Our approach finds molecules predicted to be more likely to be antibiotics while maintaining good drug-like properties and being easily synthesizable.
arXiv Detail & Related papers (2020-11-25T22:04:16Z) - 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 Latent Space Energy-Based Prior Model for Molecule Generation [59.875533935578375]
We learn latent space energy-based prior model with SMILES representation for molecule modeling.
Our method is able to generate molecules with validity and uniqueness competitive with state-of-the-art models.
arXiv Detail & Related papers (2020-10-19T09:34:20Z) - Learning Graph Models for Retrosynthesis Prediction [90.15523831087269]
Retrosynthesis prediction is a fundamental problem in organic synthesis.
This paper introduces a graph-based approach that capitalizes on the idea that the graph topology of precursor molecules is largely unaltered during a chemical reaction.
Our model achieves a top-1 accuracy of $53.7%$, outperforming previous template-free and semi-template-based methods.
arXiv Detail & Related papers (2020-06-12T09:40:42Z) - The Synthesizability of Molecules Proposed by Generative Models [3.032184156362992]
Discovery of functional molecules is an expensive and time-consuming process.
One class of techniques of growing interest for early-stage drug discovery is de novo molecular generation and optimization.
These techniques can suggest novel molecular structures intended to maximize a multi-objective function.
However, the utility of these approaches is stymied by ignorance of synthesizability.
arXiv Detail & Related papers (2020-02-17T15:41:28Z)
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.