A Transformer-based Generative Model for De Novo Molecular Design
- URL: http://arxiv.org/abs/2210.08749v1
- Date: Mon, 17 Oct 2022 05:03:35 GMT
- Title: A Transformer-based Generative Model for De Novo Molecular Design
- Authors: Wenlu Wang, Ye Wang, Honggang Zhao and Simone Sciabola
- Abstract summary: 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.
- Score: 4.6782243206450325
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Deep learning draws a lot of attention as a new way of generating unseen
structures for drug discovery. 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. The latter
are generated by enforcing different keys and values of the multi-head
attention for each target. We allow the generation of SMILES strings to be
conditional on the specified target. The sampled compounds largely occupy the
real target-specific data's chemical space and also cover a significant
fraction of novel compounds.
Related papers
- Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization [147.7899503829411]
We propose a novel and general alignment framework to align pretrained target diffusion models with preferred functional properties, named AliDiff.
AliDiff shifts the target-conditioned chemical distribution towards regions with higher binding affinity and structural rationality, specified by user-defined reward functions.
We show that AliDiff can generate molecules with state-of-the-art binding energies with up to -7.07 Avg. Vina Score, while maintaining strong molecular properties.
arXiv Detail & Related papers (2024-07-01T06:10:29Z) - 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) - Target Specific De Novo Design of Drug Candidate Molecules with Graph
Transformer-based Generative Adversarial Networks [0.0]
We propose DrugGEN, for the de novo design of drug candidate molecules that interact with selected target proteins.
DrugGEN is trained using a large dataset of compounds from ChEMBL and target-specific bioactive molecules.
arXiv Detail & Related papers (2023-02-15T18:59:27Z) - 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) - 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) - Diversifying Design of Nucleic Acid Aptamers Using Unsupervised Machine
Learning [54.247560894146105]
Inverse design of short single-stranded RNA and DNA sequences (aptamers) is the task of finding sequences that satisfy a set of desired criteria.
We propose to use an unsupervised machine learning model known as the Potts model to discover new, useful sequences with controllable sequence diversity.
arXiv Detail & Related papers (2022-08-10T13:30:58Z) - Target-aware Molecular Graph Generation [37.937378787812264]
We propose SiamFlow, which forces the flow to fit the distribution of target sequence embeddings in latent space.
Specifically, we employ an alignment loss and a uniform loss to bring target sequence embeddings and drug graph embeddings into agreements.
Experiments quantitatively show that our proposed method learns meaningful representations in the latent space toward the target-aware molecular graph generation.
arXiv Detail & Related papers (2022-02-10T04:31:14Z) - Scaffold-constrained molecular generation [0.0]
We build on the well-known SMILES-based Recurrent Neural Network (RNN) generative model, with a modified sampling procedure to achieve scaffold-constrained generation.
We showcase the method's ability to perform scaffold-constrained generation on various tasks.
arXiv Detail & Related papers (2020-09-15T15:41:18Z) - CogMol: Target-Specific and Selective Drug Design for COVID-19 Using
Deep Generative Models [74.58583689523999]
We propose an end-to-end framework, named CogMol, for designing new drug-like small molecules targeting novel viral proteins.
CogMol combines adaptive pre-training of a molecular SMILES Variational Autoencoder (VAE) and an efficient multi-attribute controlled sampling scheme.
CogMol handles multi-constraint design of synthesizable, low-toxic, drug-like molecules with high target specificity and selectivity.
arXiv Detail & Related papers (2020-04-02T18:17:20Z)
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.