Multiobjective de novo drug design with recurrent neural networks and nondominated sorting

Research productivity in the pharmaceutical industry has declined significantly in recent decades, with higher costs, longer timelines, and lower success rates of drug candidates in clinical trials. This has prioritized the scalability and multiobjectivity of drug discovery and design. De novo drug...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of cheminformatics Ročník 12; číslo 1; s. 14 - 9
Hlavní autor: Yasonik, Jacob
Médium: Journal Article
Jazyk:angličtina
Vydáno: Cham Springer International Publishing 18.02.2020
Springer Nature B.V
BMC
Témata:
Chemistry
Chemistry and Materials Science
Classification
Clinical trials
Computational Biology/Bioinformatics
Computer Applications in Chemistry
De novo drug design
Deep learning
Design
Documentation and Information in Chemistry
Drug development
Handwriting
Hydrogen bonds
Molecular weight
Multiobjective optimization
Multiple objective analysis
Neural networks
Octanol-water partition coefficients
Optimization
Pharmaceutical industry
Recurrent neural networks
Research Article
Sorting algorithms
Theoretical and Computational Chemistry
Transfer learning
Deep learning
De novo drug design
Multiobjective optimization
ISSN:1758-2946, 1758-2946
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Research productivity in the pharmaceutical industry has declined significantly in recent decades, with higher costs, longer timelines, and lower success rates of drug candidates in clinical trials. This has prioritized the scalability and multiobjectivity of drug discovery and design. De novo drug design has emerged as a promising approach; molecules are generated from scratch, thus reducing the reliance on trial and error and premade molecular repositories. However, optimizing for molecular traits remains challenging, impeding the implementation of de novo methods. In this work, we propose a de novo approach capable of optimizing multiple traits collectively. A recurrent neural network was used to generate molecules which were then ranked based on multiple properties by a nondominated sorting algorithm. The best of the molecules generated were selected and used to fine-tune the recurrent neural network through transfer learning, creating a cycle that mimics the traditional design–synthesis–test cycle. We demonstrate the efficacy of this approach through a proof of concept, optimizing for constraints on molecular weight, octanol-water partition coefficient, the number of rotatable bonds, hydrogen bond donors, and hydrogen bond acceptors simultaneously. Analysis of the molecules generated after five iterations of the cycle revealed a 14-fold improvement in the quality of generated molecules, along with improvements to the accuracy of the recurrent neural network and the structural diversity of the molecules generated. This cycle notably does not require large amounts of training data nor any handwritten scoring functions. Altogether, this approach uniquely combines scalable generation with multiobjective optimization of molecules.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1758-2946
1758-2946
DOI:10.1186/s13321-020-00419-6