Better Informed Distance Geometry: Using What We Know To Improve Conformation Generation

By Sereina Riniker, Gregory A. Landrum. 2015

682 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Molecular Biology

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 Molecular Biology

Citations in the corpus

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (2022, methodology): “It takes as input a ligand molecular graph with a random associated unbound 3D conformer (e.g., generated using RDKit/ETKDG (Riniker & Landrum, 2015)), as well as a receptor-bound structure.”
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (2022, methodology): “We also test the classic RDK IT (Riniker & Landrum, 2015) method, which is arguably the most popular open-source software for conformation generation.”
Torsional Diffusion for Molecular Conformer Generation (2022, methodology): “Among cheminfor-matics methods, we evaluate RDKit ETKDG [Riniker and Landrum, 2015], the most established open-source package, and OMEGA [Hawkins et al., 2010, Hawkins and Nicholls, 2012], a commercial software in continuous development.”
Learning Gradient Fields for Molecular Conformation Generation (2021, background): “RDKit (Riniker & Landrum, 2015) is a classical Euclidean Distance Geometry-based approach.”
GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles (2021, methodology): “• G EO M OL processes drug-like molecules in seconds or less, being orders of magnitude faster than popular baselines (e.g. ETKDG/RDKit[Riniker and Landrum, 2015]), without sacriﬁcing quality.”
QMugs, quantum mechanical properties of drug-like molecules (2022, methodology): “The RDKit (http://www.rdkit.org) implementation of the Experimental-Torsion Knowledge Distance Geometry (ETKDG) method 44 was used to generate up to 100 conformers for each molecule, with a maximum of 1000 embedding attempts and an initial coordinate assignment using distance-matrix eigenvalues and…”
Predicting Molecular Conformation via Dynamic Graph Score Matching (2021, methodology): “GEOM-QM9 GEOM-Drugs COV (%, ↑) MAT (Å, ↓) COV (%, ↑) MAT (Å, ↓) Method Mean Median Mean Median Mean Median Mean Median RDKIT [28] 83.”
New prediction categories in CASP15 (2023, methodology): “38 Subsequently, the Mol objects are written to the MDL-formatted file, 33 which can be used as a ligand submission template.”
Learning Neural Generative Dynamics for Molecular Conformation Generation (2021, methodology): “This phenomenon is also consistent with the observations for RDKit.”
Uni-Mol: A Universal 3D Molecular Representation Learning Framework (2023, methodology): “To generate 3D conformations, we use ETKGD [41] with Merck Molecular Force Field [42] optimization in RDKit [43] to randomly generate 10 conformations for each molecule.”