Open-source platform to benchmark fingerprints for ligand-based virtual screening

By Sereina Riniker, Gregory A. Landrum. 2013

320 citations recorded by the source corpus.

Similarity-search methods using molecular fingerprints are an important tool for ligand-based virtual screening. A huge variety of fingerprints exist and their performance, usually assessed in retrospective benchmarking studies using data sets with known actives and known or assumed inactives, depends largely on the validation data sets used and the similarity measure used. Comparing new methods to existing ones in any systematic way is rather difficult due to the lack of standard data sets and evaluation procedures. Here, we present a standard platform for the benchmarking of 2D fingerprints. The open-source platform contains all source code, structural data for the actives and inactives used (drawn from three publicly available collections of data sets), and lists of randomly selected query molecules to be used for statistically valid comparisons of methods. This allows the exact reproduction and comparison of results for future studies. The results for 12 standard fingerprints together with two simple baseline fingerprints assessed by seven evaluation methods are shown together with the correlations between methods. High correlations were found between the 12 fingerprints and a careful statistical analysis showed that only the two baseline fingerprints were different from the others in a statistically significant way. High correlations were also found between six of the seven evaluation methods, indicating that despite their seeming differences, many of these methods are similar to each other.

Subfields: Computational Theory and Mathematics, Immunology, Materials Chemistry

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 Immunology

In Materials Chemistry

Citations in the corpus

Ligand biological activity predicted by cleaning positive and negative chemical correlations (2019, background): “…common strategies include using pharmacological intuitions (15– 17), enumerating all linear or circular fragments below a certain size around every atom (17, 18), or unsupervised learning (19)— a molecule has many motifs, but only a few are important for biological activity of a particular target.”
One molecular fingerprint to rule them all: drugs, biomolecules, and the metabolome (2020, methodology): “Schneider N, Sayle RA, Landrum GA (2015) Get your atoms in order—an open‑source implementation of a novel and robust molecular canonicaliza‑ tion algorithm.”
ROCS-derived features for virtual screening (2016, methodology): “To increase confidence in our results, we trained models using ROCS-derived features on two additional dataset collections: the maximum unbiased validation (MUV) datasets of [22] and a group of benchmarking datasets derived from ChEMBL [19, 20], both of which were specifically designed for the valid”
Artificial intelligence to deep learning: machine intelligence approach for drug discovery (2021, methodology): “…and tools have been developed for LBVS such as SwissSimilarity (http:// www. swiss simil arity. ch/) [198], METADOCK [199], Open-source platform [200], HybridSim-VS (http:// www. rcidm. org/ Hybri dSim-VS/) [201], PKRank [202], PyGOLD (http:// www. agkoch. de/) [203], BRUSELAS (http:// bio-hpc.…”
What Is High-Throughput Virtual Screening? A Perspective from Organic Materials Discovery (2015, unknown): “(19, 20)”
Comparing structural fingerprints using a literature-based similarity benchmark (2016, methodology): “The colours used correspond to those used by Riniker and Landrum [9] in their Fig.”
Molecular fingerprint similarity search in virtual screening. (2015, background): “There are open-source platforms to benchmark fingerprints for ligand-based virtual screening that have been tested with 14 2D fingerprints [28].”
Benchmarking platform for ligand-based virtual screening (2016, methodology): “The cornerstone of LBVS is the similar property prin ciple [6].”