SDEGen: learning to evolve molecular conformations from thermodynamic noise for conformation generation

Abstract

Generation of representative conformations for small molecules is a fundamental task in cheminformatics and computer-aided drug discovery, but capturing the complex distribution of conformations that contains multiple low energy minima...

Small-Molecule Conformer Generators: Evaluation of Traditional Methods and AI Models on High-Quality Data Sets

“…The rest parameters were kept to their default values. The DMCG model does not participate in the fine-tuning test, because many molecules encountered a fatal error during optimizations, which has been discussed in the previous work …”

“…Being the first AI model to consistently outperform the OMEGA in generating ensembles, its developers have demonstrated its advantage on the GEOM-drugs data set, even with a reduced number of denoising steps. Our group also has proposed a novel model, SDEGen, 38 which relies on stochastic partial differential equations. Its performance is comparable to that of the torsional diffusion model, yet with the utilization of only 20% of the training data.…”

Infinite Physical Monkey: Do Deep Learning Methods Really Perform Better in Conformation Generation?

“…However, since it's not a one-to-one mapping, the recovering process would compromise the plausibility of binding poses. Thus physical refinement is often required to polish these conformations 15 . A more physical model, DiffDock 16 , has been designed to operate on the internal coordinate space with the popular and powerful diffusion model, achieving the state-ofthe-art (SOTA) performance among all the deep learning (DL)-based methods.…”

“…A more physical model, DiffDock 16 , has been designed to operate on the internal coordinate space with the popular and powerful diffusion model, achieving the state-ofthe-art (SOTA) performance among all the deep learning (DL)-based methods. The foundation of these rapid developments is from the molecular conformation generation methods, like GeoDiff 17 for directly generating Cartesian coordinates, CGCF 18 and SDEGen 15 for constructing 3D geometries from extensive 2D distances, and torsional diffusion 19 for operating search in torsional angle space.…”

“…"By revising the MCG setting in many DL-based methods, we suggest the community rethink the benchmark in the current MCG, and focus on the end applications in various MCG-related downstream applications in the future" 21 , what they have suggested have long been adopted among most of the molecular conformation generation works. For example, in GraphDG 22 , ConfGF 23 , and GeoDiff 17 , the difference between the thermodynamic properties of the generated conformations and quantumcomputed conformations was compared; in DMCG 24 , it is demonstrated that the docking success rate was improved when the model-generated conformations were taken for downstream docking tasks; in SDEGen 15 , not only the generated conformations were compared with the crystal conformations, but the free energy profile was also plotted by molecular dynamics to qualitatively compare the coverage area of the model-generated conformations with that of the RDKitgenerated conformations. Table 1 lists the evaluation methods involved in each model in the field of molecular conformation generation, emphasizing that there are a variety of metrics adopted for evaluating conformation generation models.…”