Analysis of the uncharted, druglike property space by self-organizing maps

Takács, Gergely; Sándor, Márk; Szalai, Zoltán; Kiss, Robert S.; Balogh, György Tibor

doi:10.1007/s11030-021-10343-y

Cited by 5 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The drug-likeness is obtained through maximizing the general chemical properties associated with drugs according to the "Rule of 5" [35][36][37] . Indeed, easily calculated physicochemical descriptors, such as molecular weight (MW) and number of hydrogen bond donors and acceptors, have been found to correlate with the success rate of clinical trials 38 With mass being the MW of the molecule, natoms the number of atoms (including hydrogens), nhbd the number of hydrogen bond donors, and nhba the number of hydrogen bond acceptors. This formula has the advantage of being computationally cheap and requiring only a pass through the SMILES string.…”

Section: Performance Of Modelsmentioning

confidence: 99%

DrugSynthMC: an atom based generation of drug-like molecules with Monte Carlo Search

Roucairol,

Georgiou,

Cazenave

et al. 2024

Preprint

View full text Add to dashboard Cite

A growing number of Deep Learning (DL) methodologies have recently been developed to design novel compounds and expand the chemical space within virtual libraries. Most of these Neural Network approaches design molecules to specifically bind a target, based on its structural information and/or knowledge of previously identified binders. Fewer attempts have been made to develop approaches for de novo design of virtual libraries, as synthesizability of generated molecules remains a challenge. In this work, we developed a new Monte Carlo Search (MCS) algorithm, DrugSynthMC (Drug Synthetise using Monte Carlo), in conjunction with DL and statistical-based priors to generate thousands of interpretable chemical structures and novel drug-like molecules per second. DrugSynthMC produces drug-like compounds using an atom-based search model that builds molecules as SMILES, character by character. Designed molecules follow Lipinski’s “rule of 5”, show a high proportion of predicted-to-be synthesisable compounds and efficiently expand the chemical space within the libraries, without reliance on training datasets, synthesizability metrics or enforcing during SMILES generation. Our approach can function with or without an underlying Neural Network and is thus easily explainable and versatile. This ease in drug-like molecule generation allows for future integration of score functions aimed at different target- or job -oriented goals. Thus, DrugSynthMC is expected to enable the functional assessment of large compound libraries covering an extensive novel chemical space, overcoming the limitations of existing drug collections. The software is available at https://github.com/RoucairolMilo/DrugSynthMC

show abstract

Section: Performance Of Modelsmentioning

confidence: 99%

DrugSynthMC: an atom based generation of drug-like molecules with Monte Carlo Search

Roucairol,

Georgiou,

Cazenave

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Up to 8.8 million molecules from SMU-RUL 25 were converted into 32D vectors and used for the construction of the chemical space by using the SOM method 40 . The SOM size was 120 ×120.…”

Section: Chemical Space Constructionmentioning

confidence: 99%

Thinking like a structural biologist: A pocket-based 3D molecule generative model fueled by electron density

Wang

Bai

Shi

et al. 2022

Preprint

View full text Add to dashboard Cite

We report for the first time the use of experimental electron density (ED) as training data for the generation of drug-like three-dimensional molecules based on the structure of a target protein pocket. Similar to a structural biologist building molecules based on their ED, our model functions with two main components: a generative adversarial network (GAN) to generate the ligand ED in the input pocket and an ED interpretation module for molecule generation. The model was tested on three targets including kinase, protease, and nuclear receptor, and evaluated with a reference dataset composed of over 8,000 compounds that have their activities reported in the literature. The evaluation examined the chemical validity, chemical space distribution-based diversity, and similarity with reference active compounds concerning the molecular structure and pocket-binding mode. Our model can reproduce classical active compounds and can also generate novel molecules with similar binding modes as active compounds, making it a promising tool to generate a library for high-throughput virtual screening. Our model is available as an online service to academic users via https://edmg.stonewise.cn/#/create.

show abstract