Structure-based de novo design and identification of D816V mutant-selective c-KIT inhibitors

2014 ◽  
Vol 12 (26) ◽  
pp. 4644-4655 ◽  
Author(s):  
Hwangseo Park ◽  
Soyoung Lee ◽  
Suhyun Lee ◽  
Sungwoo Hong
Keyword(s):  
Free Energy ◽  
Inhibitory Activity ◽  
High Selectivity ◽  
De Novo ◽  
Scoring Function ◽  
Solvation Free Energy ◽  
De Novo Design ◽  
Gain Of Function

New 7-azaindole-based c-KIT inhibitors with nanomolar inhibitory activity and high selectivity for the gain-of-function D816V mutant were identified through the structure-based de novo design using the scoring function improved by implementing an accurate solvation free energy.

scholarly journals Evaluation of Inhibitory Activity In Silico of In-House Thiomorpholine Compounds between the ACE2 Receptor and S1 Subunit of SARS-CoV-2 Spike

Pathogens ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 1208
Author(s):  
Victor H. Vázquez-Valadez ◽  
Alejandro Hernández-Serda ◽  
Ma. Fernanda Jiménez-Cabiedes ◽  
Pablo Aguirre-Vidal ◽  
Ingrid González-Tapia ◽  
...  
Keyword(s):  
Inhibitory Activity ◽  
In Silico ◽  
De Novo ◽  
Computational Study ◽  
Antiviral Agents ◽  
Antihypertensive Agents ◽  
De Novo Design ◽  
Target Cells ◽  
Research Groups ◽  
International Scientific Community

At the end of 2019, the world was struck by the COVID-19 pandemic, which resulted in dire repercussions of unimaginable proportions. From the beginning, the international scientific community employed several strategies to tackle the spread of this disease. Most notably, these consisted of the development of a COVID-19 vaccine and the discovery of antiviral agents through the repositioning of already known drugs with methods such as de novo design. Previously, methylthiomorphic compounds, designed by our group as antihypertensive agents, have been shown to display an affinity with the ACE2 (angiotensin converting enzyme) receptor, a key mechanism required for SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) entry into target cells. Therefore, the objective of this work consists of evaluating, in silico, the inhibitory activity of these compounds between the ACE2 receptor and the S1 subunit of the SARS-CoV-2 spike protein. Supported by the advances of different research groups on the structure of the coronavirus spike and the interaction of the latter with its receptor, ACE2, we carried out a computational study that examined the effect of in-house designed compounds on the inhibition of said interaction. Our results indicate that the polyphenol LQM322 is one of the candidates that should be considered as a possible anti-COVID-19 agent.

scholarly journals Memory-Assisted Reinforcement Learning for Diverse Molecular De Novo Design

2020 ◽  
Author(s):  
Thomas Blaschke ◽  
Ola Engkvist ◽  
Jürgen Bajorath ◽  
Hongming Chen
Keyword(s):  
Reinforcement Learning ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Scoring Function ◽  
De Novo Design ◽  
Memory Unit ◽  
Chemical Structures ◽  
Low Diversity ◽  
De Novo Molecular Design

<div><div><div><p>In de novo molecular design, recurrent neural networks (RNN) have been shown to be effective methods for sampling and generating novel chemical structures. Using a technique called reinforcement learning (RL), an RNN can be tuned to target a particular section of chemical space with optimized desirable properties using a scoring function. However, ligands generated by current RL methods so far tend to have relatively low diversity, and sometimes even result in duplicate structures when optimizing towards particular properties. Here, we propose a new method to address the low diversity issue in RL. Memory-assisted RL is an extension of the known RL, with the introduction of a so-called memory unit.</p></div></div></div>

scholarly journals Memory-Assisted Reinforcement Learning for Diverse Molecular De Novo Design

2020 ◽  
Author(s):  
Thomas Blaschke ◽  
Ola Engkvist ◽  
Jürgen Bajorath ◽  
Hongming Chen
Keyword(s):  
Reinforcement Learning ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Scoring Function ◽  
De Novo Design ◽  
Memory Unit ◽  
Chemical Structures ◽  
Low Diversity ◽  
De Novo Molecular Design

<div><div><div><p>In de novo molecular design, recurrent neural networks (RNN) have been shown to be effective methods for sampling and generating novel chemical structures. Using a technique called reinforcement learning (RL), an RNN can be tuned to target a particular section of chemical space with optimized desirable properties using a scoring function. However, ligands generated by current RL methods so far tend to have relatively low diversity, and sometimes even result in duplicate structures when optimizing towards particular properties. Here, we propose a new method to address the low diversity issue in RL. Memory-assisted RL is an extension of the known RL, with the introduction of a so-called memory unit.</p></div></div></div>

Sign in / Sign up

Export Citation Format

Share Document