Analysis and comparison of 2D fingerprints: insights into database screening performance using eight fingerprint methods

By J. Duan, G. Sastry, Steve Dixon, Jeffrey F. Lowrie, Woody Sherman. Journal of Cheminformatics, 2010

423 citations recorded by the source corpus.

Virtual screening is a widely used strategy in modern drug discovery and 2D fingerprint similarity is an important tool that has been successfully applied to retrieve active compounds from large datasets. However, it is not always straightforward to select an appropriate fingerprint method and associated settings for a given problem. Here, we applied eight different fingerprint methods, as implemented in the new cheminformatics package Canvas, on a well-validated dataset covering five targets. The fingerprint methods include Linear, Dendritic, Radial, MACCS, MOLPRINT2D, Pairwise, Triplet, and Torsion. We find that most fingerprints have similar retrieval rates on average; however, each has special characteristics that distinguish its performance on different query molecules and ligand sets. For example, some fingerprints exhibit a significant ligand size dependency whereas others are more robust with respect to variations in the query or active compounds. In cases where little information is known about the active ligands, MOLPRINT2D fingerprints produce the highest average retrieval actives. When multiple queries are available, we find that a fingerprint averaged over all query molecules is generally superior to fingerprints derived from single queries. Finally, a complementarity metric is proposed to determine which fingerprint methods can be combined to improve screening results.

Subfields: Computational Theory and Mathematics, Public Health, Environmental and Occupational Health, Spectroscopy

View Paper: https://www.semanticscholar.org/paper/05c4e426531906f365e3d2120e860a1116c479fa

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 Spectroscopy

Citations in the corpus

Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases (2018, methodology): “reported that no fingerprint method could outperform the others considering all targets and that different types of fingerprints are effective on different targets [65].”
Benchmarking platform for ligand-based virtual screening (2016, background): “Although some fin gerprints perform in general better than others, no fingerprint has been show to outperform others [6], [9].”
In silico evaluation of highly efficient organic light-emitting materials (2016, methodology): “To maximize both the model building and the analysis procedure, dendritic fingerprint [16-18] was used as a sole 2D-structure descriptor.”
Tuning hERG out: Antitarget QSAR Models for Drug Development (2014, methodology): “Molecular descriptors—Four different types of molecular fingerprints reflecting the absence (0) or presence (1) of substructural fragment for each compound [97] were utilized in this study.”
Comparing structural fingerprints using a literature-based similarity benchmark (2016, background): “However, on the Briem and Lessel benchmark dataset [19] (5 targets from the MDDR), Duan et al. [20] found that the same radial fingerprint (that is, from Sastry et al.) was best although Molprint2D was close in performance.”
D3R Grand Challenge 2: Blind Prediction of Protein-Ligand Poses, Affinity Rankings, and Relative Binding Free Energies (2017, background): “…of the challenge, the PDB included co-crystal structures of FXR with ligands similar to the benzimidazoles in the challenge set, as well as to ligands FXR 5 and 34 (Canvas Tanimoto coefficient of up to 0.94 [33, 34]), whereas the similarities were below 0.3 for the remaining ligands (Table S1).”
SuperPred: update on drug classification and target prediction (2014, background): “Among others, topological descriptors like 2D fingerprints (5) or BCUT descriptors (6) are often applied in similarity searching.”