Estimation of the size of drug-like chemical space based on GDB-17 data

By Pavel G. Polishchuk, Timur I. Madzhidov, Alexandre Varnek. 2013

586 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Physical and Theoretical Chemistry, Spectroscopy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Physical and Theoretical Chemistry

In Spectroscopy

Citations in the corpus

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation (2018, background): “For example, the range of drug-like molecules has been estimated to be between 10 23 and 10 60 [32].”
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules (2016, neutral): “− 6 Virtual libraries containing thousands to hundreds of millions of candidates can be assayed with ﬁ rst-principles simulations or statistical predictions based on learned proxy models, and only the most promising leads are selected and tested experimentally.”
Molecular generative model based on conditional variational autoencoder for de novo molecular design (2018, background): “For instance, 10(8) molecules have been synthesized [1], whereas it is estimated that there are 10(23)–10(60) drug-like molecules [2].”
GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation (2020, background): “The problem is very challenging, since the chemical space is discrete by nature, and the entire search space is huge, which is believed to be as large as 10 33 (Polishchuk et al., 2013).”
A 3D Generative Model for Structure-Based Drug Design (2022, background): “Searching for suitable molecule candidates in silico usually involves massive computational efforts because of the enormous space of synthetically feasible chemicals [22] and conformational degree of freedom of both compound and protein structures [11].”
MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design (2022, background): “On the other hand, the number of the drug-like molecules is large as estimated to be 10 60 [4] and it is computationally prohibitive to enumerate all the possible molecules.”
BERT Learns (and Teaches) Chemistry (2020, background): “In modern applications such as drug discovery, the search space is estimated to be in the range of 10 23 to 10 60 molecules [20]; however, functional groups and property-impacting substructures can greatly assist in restricting the size of this space, as they indicate the presence of speciﬁc…”
Molecular Generation with Recurrent Neural Networks (RNNs) (2017, background): “The number has been estimated to be between 1023 and 1060[1, 2, 3] and dwarfs the current largest databases of chemical compounds, such as ChemBL[4]: ~2*106, PubChem[5] ~90*106and ChemSpider[6] ~60*106.”
NeVAE: A Deep Generative Model for Molecular Graphs (2018, background): “In the context of computer-aided drug design [3], there is a great interest in developing automated, machine learning techniques to discover sizeable numbers of plausible, diverse, and novel candidate molecules with various desirable properties in the vast (10(23) − 10(60)) and unstructured molecula”