The superposition of small molecules is a standard technique in molecular modeling and for some more advanced in silico applications of drug discovery a critical prerequisite. The aims of superposing molecules are manifold. An assessment of the 3D similarity, an understanding of the SAR in a compound series, or ultimately an estimate of the likelihood of a compound to be active and selective against a target protein of interest. Considering so many objectives it is not surprising that new superpositioning methods are continuously developed and the overlay problem cannot be considered solved. We present 51 superposition methods with a focus on those published in the 21st century. For 36 methods that are currently available, we briefly describe and compare the respective pose generation and scoring processes. While the modeling community got a wealth of methods at hand, the scientific necessity of rigorous and comparable benchmarking becomes apparent. This article is categorized under: Data Science > Chemoinformatics Software > Molecular Modeling

Explainable and accurate predictions of bioactivity values are indispensable to accelerate drug design and reduce attrition during drug development. To enhance the accuracy of predictions, a new algorithmic approach was designed, which unites the advantages of matched molecular series and supervised machine learning (ML) techniques. This approach named Network Balance Scaling (NBS) employs convex optimization on matched molecular series networks enriched with ML data. By applying NBS, the performance of supervised ML methods can be improved, and predictions can be rationalized following the network of similar compounds. The approach was validated on the freely available MoleculeNet benchmark with respective ML models as well as on real-world targets and corresponding ML models provided by Merck KGaA. In all cases, when combining NBS with supervised ML models, we observe a substantial improvement in the different activity and physicochemical data sets and bioactivity-related application scenarios. The open-source code of NBS can be found freely available at https://github.com/rareylab/NetworkBalanceScaling.