Asymmetric clustering index in a case study of 5-HT1A receptor ligands

Pharmacoprint: A Combination of a Pharmacophore Fingerprint and Artificial Intelligence as a Tool for Computer-Aided Drug Design

Structural fingerprints and pharmacophore modeling are methodologies that have been used for at least 2 decades in various fields of cheminformatics, from similarity searching to machine learning (ML). Advances in in silico techniques consequently led to combining both these methodologies into a new approach known as the pharmacophore fingerprint. Herein, we propose a high-resolution, pharmacophore fingerprint called Pharmacoprint that encodes the presence, types, and relationships between pharmacophore features of a molecule. Pharmacoprint was evaluated in classification experiments by using ML algorithms (logistic regression, support vector machines, linear support vector machines, and neural networks) and outperformed other popular molecular fingerprints (i.e., ECFP4, Estate, MACCS, PubChem, Substructure, Klekota-Roth, CDK, Extended, and GraphOnly) and the ChemAxon pharmacophoric features fingerprint. Pharmacoprint consisted of 39 973 bits; several methods were applied for dimensionality reduction, and the best algorithm not only reduced the length of the bit string but also improved the efficiency of the ML tests. Further optimization allowed us to define the best parameter settings for using Pharmacoprint in discrimination tests and for maximizing statistical parameters. Finally, Pharmacoprint generated for three-dimensional (3D) structures with defined hydrogens as input data was applied to neural networks with a supervised autoencoder for selecting the most important bits and allowed us to maximize the Matthews correlation coefficient up to 0.962. The results show the potential of Pharmacoprint as a new, perspective tool for computer-aided drug design.

The Choice of an Appropriate Information Dissimilarity Measure for Hierarchical Clustering of River Streamflow Time Series, Based on Calculated Lyapunov Exponent and Kolmogorov Measures

The purpose of this paper was to choose an appropriate information dissimilarity measure for hierarchical clustering of daily streamflow discharge data, from twelve gauging stations on the Brazos River in Texas (USA), for the period 1989–2016. For that purpose, we selected and compared the average-linkage clustering hierarchical algorithm based on the compression-based dissimilarity measure (NCD), permutation distribution dissimilarity measure (PDDM), and Kolmogorov distance (KD). The algorithm was also compared with K-means clustering based on Kolmogorov complexity (KC), the highest value of Kolmogorov complexity spectrum (KCM), and the largest Lyapunov exponent (LLE). Using a dissimilarity matrix based on NCD, PDDM, and KD for daily streamflow, the agglomerative average-linkage hierarchical algorithm was applied. The key findings of this study are that: (i) The KD clustering algorithm is the most suitable among others; (ii) ANOVA analysis shows that there exist highly significant differences between mean values of four clusters, confirming that the choice of the number of clusters was suitably done; and (iii) from the clustering we found that the predictability of streamflow data of the Brazos River given by the Lyapunov time (LT), corrected for randomness by Kolmogorov time (KT) in days, lies in the interval from two to five days.

Average Information Content Maximization--A New Approach for Fingerprint Hybridization and Reduction

Fingerprints, bit representations of compound chemical structure, have been widely used in cheminformatics for many years. Although fingerprints with the highest resolution display satisfactory performance in virtual screening campaigns, the presence of a relatively high number of irrelevant bits introduces noise into data and makes their application more time-consuming. In this study, we present a new method of hybrid reduced fingerprint construction, the Average Information Content Maximization algorithm (AIC-Max algorithm), which selects the most informative bits from a collection of fingerprints. This methodology, applied to the ligands of five cognate serotonin receptors (5-HT2A, 5-HT2B, 5-HT2C, 5-HT5A, 5-HT6), proved that 100 bits selected from four non-hashed fingerprints reflect almost all structural information required for a successful in silico discrimination test. A classification experiment indicated that a reduced representation is able to achieve even slightly better performance than the state-of-the-art 10-times-longer fingerprints and in a significantly shorter time.

Clustered distribution of natural product leads of drugs in the chemical space as influenced by the privileged target-sites

Some natural product leads of drugs (NPLDs) have been found to congregate in the chemical space. The extent, detailed patterns, and mechanisms of this congregation phenomenon have not been fully investigated and their usefulness for NPLD discovery needs to be more extensively tested. In this work, we generated and evaluated the distribution patterns of 442 NPLDs of 749 pre-2013 approved and 263 clinical trial small molecule drugs in the chemical space represented by the molecular scaffold and fingerprint trees of 137,836 non-redundant natural products. In the molecular scaffold trees, 62.7% approved and 37.4% clinical trial NPLDs congregate in 62 drug-productive scaffolds/scaffold-branches. In the molecular fingerprint tree, 82.5% approved and 63.0% clinical trial NPLDs are clustered in 60 drug-productive clusters (DCs) partly due to their preferential binding to 45 privileged target-site classes. The distribution patterns of the NPLDs are distinguished from those of the bioactive natural products. 11.7% of the NPLDs in these DCs have remote-similarity relationship with the nearest NPLD in their own DC. The majority of the new NPLDs emerge from preexisting DCs. The usefulness of the derived knowledge for NPLD discovery was demonstrated by the recognition of the new NPLDs of 2013-2014 approved drugs.

CFam: a chemical families database based on iterative selection of functional seeds and seed-directed compound clustering

Similarity-based clustering and classification of compounds enable the search of drug leads and the structural and chemogenomic studies for facilitating chemical, biomedical, agricultural, material and other industrial applications. A database that organizes compounds into similarity-based as well as scaffold-based and property-based families is useful for facilitating these tasks. CFam Chemical Family database http://bidd2.cse.nus.edu.sg/cfam was developed to hierarchically cluster drugs, bioactive molecules, human metabolites, natural products, patented agents and other molecules into functional families, superfamilies and classes of structurally similar compounds based on the literature-reported high, intermediate and remote similarity measures. The compounds were represented by molecular fingerprint and molecular similarity was measured by Tanimoto coefficient. The functional seeds of CFam families were from hierarchically clustered drugs, bioactive molecules, human metabolites, natural products, patented agents, respectively, which were used to characterize families and cluster compounds into families, superfamilies and classes. CFam currently contains 11 643 classes, 34 880 superfamilies and 87 136 families of 490 279 compounds (1691 approved drugs, 1228 clinical trial drugs, 12 386 investigative drugs, 262 881 highly active molecules, 15 055 human metabolites, 80 255 ZINC-processed natural products and 116 783 patented agents). Efforts will be made to further expand CFam database and add more functional categories and families based on other types of molecular representations.