De Novo Drug Design with Joint Transformers
- URL: http://arxiv.org/abs/2310.02066v3
- Date: Mon, 4 Dec 2023 08:34:48 GMT
- Title: De Novo Drug Design with Joint Transformers
- Authors: Adam Izdebski and Ewelina Weglarz-Tomczak and Ewa Szczurek and Jakub
M. Tomczak
- Abstract summary: De novo drug design requires simultaneously generating novel molecules outside of training data and predicting their target properties.
We propose Joint Transformer that combines a Transformer decoder, Transformer encoder, and a predictor in a joint generative model with shared weights.
We formulate a probabilistic black-box optimization algorithm that employs Joint Transformer to generate novel molecules with improved target properties.
- Score: 9.339914898177186
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: De novo drug design requires simultaneously generating novel molecules
outside of training data and predicting their target properties, making it a
hard task for generative models. To address this, we propose Joint Transformer
that combines a Transformer decoder, Transformer encoder, and a predictor in a
joint generative model with shared weights. We formulate a probabilistic
black-box optimization algorithm that employs Joint Transformer to generate
novel molecules with improved target properties and outperforms other
SMILES-based optimization methods in de novo drug design.
Related papers
- Permutation invariant multi-output Gaussian Processes for drug combination prediction in cancer [2.1145050293719745]
Dose-response prediction in cancer is an active application field in machine learning.
The goal is to develop accurate predictive models that can be used to guide experimental design or inform treatment decisions.
arXiv Detail & Related papers (2024-06-28T18:28:38Z) - DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model.
We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
arXiv Detail & Related papers (2024-03-07T02:53:40Z) - Dual-Space Optimization: Improved Molecule Sequence Design by Latent
Prompt Transformer [78.47949363282868]
We propose the Dual-Space Optimization (DSO) method that integrates latent space sampling and data space selection to solve this problem.
DSO iteratively updates a latent space generative model and a synthetic dataset in an optimization process that shifts the generative model and the synthetic data towards regions of desired property values.
Our experiments demonstrate effectiveness of the proposed method, which sets new performance benchmarks across single-objective, multi-objective and constrained molecule design tasks.
arXiv Detail & Related papers (2024-02-27T03:33:23Z) - Full Stack Optimization of Transformer Inference: a Survey [58.55475772110702]
Transformer models achieve superior accuracy across a wide range of applications.
The amount of compute and bandwidth required for inference of recent Transformer models is growing at a significant rate.
There has been an increased focus on making Transformer models more efficient.
arXiv Detail & Related papers (2023-02-27T18:18:13Z) - Effective Pre-Training Objectives for Transformer-based Autoencoders [97.99741848756302]
We study trade-offs between efficiency, cost and accuracy of Transformer encoders.
We combine features of common objectives and create new effective pre-training approaches.
arXiv Detail & Related papers (2022-10-24T18:39:44Z) - A Transformer-based Generative Model for De Novo Molecular Design [4.6782243206450325]
We propose a Transformer-based deep model for de novo target-specific molecular design.
The proposed method is capable of generating both drug-like compounds and target-specific compounds.
arXiv Detail & Related papers (2022-10-17T05:03:35Z) - Tailoring Molecules for Protein Pockets: a Transformer-based Generative
Solution for Structured-based Drug Design [133.1268990638971]
De novo drug design based on the structure of a target protein can provide novel drug candidates.
We present a generative solution named TamGent that can directly generate candidate drugs from scratch for a given target.
arXiv Detail & Related papers (2022-08-30T09:32:39Z) - Molecular Attributes Transfer from Non-Parallel Data [57.010952598634944]
We formulate molecular optimization as a style transfer problem and present a novel generative model that could automatically learn internal differences between two groups of non-parallel data.
Experiments on two molecular optimization tasks, toxicity modification and synthesizability improvement, demonstrate that our model significantly outperforms several state-of-the-art methods.
arXiv Detail & Related papers (2021-11-30T06:10:22Z) - Controlled Molecule Generator for Optimizing Multiple Chemical
Properties [9.10095508718581]
We propose a new optimized molecule generator model based on the Transformer with two constraint networks.
Experiments demonstrate that our proposed model outperforms state-of-the-art models by a significant margin for optimizing multiple properties simultaneously.
arXiv Detail & Related papers (2020-10-26T21:26:14Z)
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.