2020
DOI: 10.1039/c9me00109c
|View full text |Cite
|
Sign up to set email alerts
|

Less may be more: an informed reflection on molecular descriptors for drug design and discovery

Abstract: The phenomenal advances of machine learning in the context of drug design have led to the development of a plethora of molecular descriptors. And yet, there might be value in using just a handful of them – inspired by our physical intuition.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
14
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8
1

Relationship

1
8

Authors

Journals

citations
Cited by 14 publications
(14 citation statements)
references
References 42 publications
0
14
0
Order By: Relevance
“…Modeling systems are now available to predict synergism within a drug or other molecular combinations. Such in silico tools are evolving fast and are recommended for screening purposes. Understanding the physicochemical attributes of encapsulable molecules based on molecular descriptors can be a facile way to estimate the encapsulability, solubility, stability, and intermolecular interactions. Some online tools to calculate molecular descriptors, such as the Swiss ADME, are freely available.…”
Section: Perspectivesmentioning
confidence: 99%
“…Modeling systems are now available to predict synergism within a drug or other molecular combinations. Such in silico tools are evolving fast and are recommended for screening purposes. Understanding the physicochemical attributes of encapsulable molecules based on molecular descriptors can be a facile way to estimate the encapsulability, solubility, stability, and intermolecular interactions. Some online tools to calculate molecular descriptors, such as the Swiss ADME, are freely available.…”
Section: Perspectivesmentioning
confidence: 99%
“…A regularly used strategy is to utilise as many descriptors as possible to make predictions, however this is fallacious as it increases the likelihood of overfitting. 22 One descriptor that has been proven to be sufficient in offering an accurate representation of any given molecular structure is the smooth overlap of atomic positions (SOAP) descriptor. 26 Even though its most commonly used form only encodes up to three-body correlations, 27 the SOAP descriptor has been gaining popularity given its impressive performance across a plethora of widely different classes of materials and problems ranging from hydrogen absorption of nanoclusters 28 to the development of bespoke interatomic potentials.…”
Section: Introductionmentioning
confidence: 99%
“…Examples that focus on the solid form engineering applications relevant to the case study presented in this work include crystallisation propensity, CC propensity, solubility, and even amorphous properties such as glass forming ability [10][11][12][13][14][15][16]. Descriptors represent tangible molecular properties that a user can readily translate into practical terms which can be controlled experimentally to affect the application's target [17]. This is not a perfect scenario; however, as searching vast multidimensional inputs can make it difficult to gather data sufficiently large to cover the search space as well as making identification of specific important properties a challenge.…”
Section: Introductionmentioning
confidence: 99%