Leave-Cluster-Out Cross-Validation Is Appropriate for Scoring Functions Derived from Diverse Protein Data Sets

102 citations recorded by the source corpus.

How researchers see this paper

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

PotentialNet for Molecular Property Prediction (2018, background): “…hierarchical clustering based on pairwise structural and sequence ∗ EF ( R ) χ values may therefore exceed 1.0, since this means that the χ percentage of top predicted molecules have an average standard deviation of more than 1.0 above the mean. homology of the proteins as distance metrics 45,46 .”
AGL-Score: Algebraic Graph Learning Score for Protein-Ligand Binding Scoring, Ranking, Docking, and Screening (2019, background): “62 Recently, Wang and Zhang have generated their own training sets (unfortunately, these useful training sets are not publicly available) to show that machine learning models can do very well in docking and screening tests.”
Latest developments in molecular docking: 2010–2011 in review (2013, methodology): “Kramer and Gedeck [102] used the RF-score of Ballester and Mitchell and showed that the presence of the same protein families within the training and test sets (may) lead to scoring function performance looking better than it really is.”
Artificial intelligence in drug discovery: recent advances and future perspectives (2021, background): “Alternatives such as scaffold-based [100] or time-based splits [101], which try to approximate the course of a lead optimization project, are potentially more informative.”