Chemical space

By P. Kirkpatrick, C. Ellis. 2004

How researchers see this paper

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

Citations in the corpus

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation (2018, background): “Additionally, chemical space is discrete, and molecular properties are highly sensitive to small changes in the molecular structure [21].”
Virtual Screening with AutoDock: Theory and Practice (2010, background): “Several sets of guidelines have been proposed to improve the sampling of the available chemical space, which has been estimated to include 10 60 unique compounds [30].”
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. (2015, background): “Unfortunately, the number of potentially interesting small molecules is too large for exhaustive screening [1– 3], even when relying on automated synthesis and combinatorial high-throughput “click-chemistry” [4, 5].”
Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error. (2017, background): “64 Furthermore, ML models for predicting properties of molecules in non-equilibrium or strained conﬁgurations might require substantially more training data.”
Exploring chemical compound space with quantum-based machine learning (2019, background): “molecules and materials [1, 2], and the combinatorially many ways for them to undergo chemical transformations, our understanding of chemistry requires a firstprinciples approach with proper roots in quantum mechanics (QM) and statistical mechanics (SM).”
Development and Benchmarking of Open Force Field 2.0.0: The Sage Small Molecule Force Field (2023, unknown): “3,10,13 As the space of potential drug-like molecules is combinatorially large, 35,36 a small molecule force ﬁeld should be able to model a diverse set of molecules with high accuracy.”
Large-scale chemical language representations capture molecular structure and properties (2021, background): “Label annotation of molecules is typically expensive and this problem is compounded by the fact that the size of the space consisting of plausible chemicals in need of annotation is astronomically large (10 60 to 10 100 ) 22 .”
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models (2018, background): “It has been estimated that the number of pharmacologically-sensible molecules is in the order of 10 23 to 10 80 compounds [3, 4].”