Deep Learning Applied to Ligand-Based De Novo Drug Design

Palazzesi, Ferruccio; Pozzan, Alfonso

doi:10.1007/978-1-0716-1787-8_12

Cited by 24 publications

(24 citation statements)

References 119 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Palazzesi and Pozzan recently reported a list of over 100 deep generative methods published in the literature between 2017 and 2020. 80 The methods are innovative and perform well in benchmark studies that measure the models’ ability to, for example, reproduce property distributions and generate valid, diverse, and novel molecules. 81 One may thus conclude that generative modeling is essentially a solved problem—–given a reward function, we now have the methods for generating molecules that satisfy it.…”

Section: Discussionmentioning

confidence: 99%

On the Value of Using 3D Shape and Electrostatic Similarities in Deep Generative Methods

Bolcato

Heid

Boström

2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Multiparameter optimization, the heart of drug design, is still an open challenge. Thus, improved methods for automated compound design with multiple controlled properties are desired. Here, we present a significant extension to our previously described fragment-based reinforcement learning method (DeepFMPO) for the generation of novel molecules with optimal properties. As before, the generative process outputs optimized molecules similar to the input structures, now with the improved feature of replacing parts of these molecules with fragments of similar three-dimensional (3D) shape and electrostatics. We developed and benchmarked a new python package, ESP-Sim, for the comparison of the electrostatic potential and the molecular shape, allowing the calculation of high-quality partial charges (e.g., RESP with B3LYP/6-31G**) obtained using the quantum chemistry program Psi4. By performing comparisons of 3D fragments, we can simulate 3D properties while overcoming the notoriously difficult step of accurately describing bioactive conformations. The new improved generative (DeepFMPO v3D) method is demonstrated with a scaffold-hopping exercise identifying CDK2 bioisosteres. The code is open-source and freely available.

show abstract

Section: Discussionmentioning

confidence: 99%

On the Value of Using 3D Shape and Electrostatic Similarities in Deep Generative Methods

Bolcato

Heid

Boström

2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Over the past few years, new discoveries in the field of de novo drug design have renewed interest in generating new molecules using machine learning. 6 − 9 RNNs have been used for generating libraries for HTS, hit-to-lead optimization, and fragment-based hit discovery. 15 , 83 − 87 A feature of these generative models is the ability to optimize multiple parameters such as the physicochemical properties or biological activity.…”

Section: Discussionmentioning

confidence: 99%

“…In recent years, generative models have become commonly used as part of the design–make–test cycle 4 to produce molecules de novo ( 5 , 6 ) and this field has been reviewed by many others. 7 − 9 These generative models have come from several different architectures [e.g., recurrent neural networks (RNNs), 6 variational autoencoder (VAE), 10 and generative adversarial networks (GAN)] 11 and have been shown to generate valid, novel molecules in the same chemical space as their training sets, with desirable physicochemical properties. 12 − 15 Molecular representation is varied in such generative models, including SMILES, and more recently molecule trees and SELFIES, both of which have enjoyed success in producing 100% valid molecule strings.…”

Section: Introductionmentioning

confidence: 99%

MegaSyn: Integrating Generative Molecular Design, Automated Analog Designer, and Synthetic Viability Prediction

Urbina

Lowden²,

Culberson³

et al. 2022

ACS Omega

View full text Add to dashboard Cite

Generative machine learning models have become widely adopted in drug discovery and other fields to produce new molecules and explore molecular space, with the goal of discovering novel compounds with optimized properties. These generative models are frequently combined with transfer learning or scoring of the physicochemical properties to steer generative design, yet often, they are not capable of addressing a wide variety of potential problems, as well as converge into similar molecular space when combined with a scoring function for the desired properties. In addition, these generated compounds may not be synthetically feasible, reducing their capabilities and limiting their usefulness in real-world scenarios. Here, we introduce a suite of automated tools called MegaSyn representing three components: a new hill-climb algorithm, which makes use of SMILES-based recurrent neural network (RNN) generative models, analog generation software, and retrosynthetic analysis coupled with fragment analysis to score molecules for their synthetic feasibility. We show that by deconstructing the targeted molecules and focusing on substructures, combined with an ensemble of generative models, MegaSyn generally performs well for the specific tasks of generating new scaffolds as well as targeted analogs, which are likely synthesizable and druglike. We now describe the development, benchmarking, and testing of this suite of tools and propose how they might be used to optimize molecules or prioritize promising lead compounds using these RNN examples provided by multiple test case examples.

show abstract

“…Recent reviews of structure-based SFs and deep learning for virtual screening are given by Li et al (2021b), Kimber et al (2021), and Rifaioglu et al (2019). Additionally, to narrow the scope of the review, we focus on structure-based deep-learning methods and we refer the reader interested in ligand-based methods to Tropsha (2010), Muratov et al (2020), Baskin (2020), and Palazzesi and Pozzan (2022). More general and broad reviews about the application of machine learning and deep learning in drug discovery are provided by Chen H. et al (2018), Vamathevan et al (2019), and .…”

Section: Introductionmentioning

confidence: 99%

Scoring Functions for Protein-Ligand Binding Affinity Prediction Using Structure-based Deep Learning: A Review

2022

View full text Add to dashboard Cite

The rapid and accurate in silico prediction of protein-ligand binding free energies or binding affinities has the potential to transform drug discovery. In recent years, there has been a rapid growth of interest in deep learning methods for the prediction of protein-ligand binding affinities based on the structural information of protein-ligand complexes. These structure-based scoring functions often obtain better results than classical scoring functions when applied within their applicability domain. Here we review structure-based scoring functions for binding affinity prediction based on deep learning, focussing on different types of architectures, featurization strategies, data sets, methods for training and evaluation, and the role of explainable artificial intelligence in building useful models for real drug-discovery applications.

show abstract

Deep Learning Applied to Ligand-Based De Novo Drug Design

Cited by 24 publications

References 119 publications

On the Value of Using 3D Shape and Electrostatic Similarities in Deep Generative Methods

On the Value of Using 3D Shape and Electrostatic Similarities in Deep Generative Methods

MegaSyn: Integrating Generative Molecular Design, Automated Analog Designer, and Synthetic Viability Prediction

Scoring Functions for Protein-Ligand Binding Affinity Prediction Using Structure-based Deep Learning: A Review

Contact Info

Product

Resources

About