Jan M. Kriegl

Machine learning techniques for in silico modeling of drug metabolism.

The computational assessment of drug metabolism has gained considerable interest in pharmaceutical research. Amongst others, machine learning techniques have been employed to model relationships between the chemical structure of a compound and its metabolic fate. Examples for these techniques, which were originally developed in fields far from drug discovery, are artificial neural networks or support vector machines. This paper summarizes the application of various machine learning techniques to predict the interaction between organic molecules and metabolic enzymes. More complex endpoints such as metabolic stability or in vivo clearance will also be addressed. It is shown that the prediction of metabolic endpoints with machine learning techniques has made considerable progress over the past few years. Depending on the procedure used, either classification or quantitative prediction is possible for even large and diverse compound sets. Together with the expanding experimental data basis, these in silico methods have become valuable tools in the drug discovery and development process.

A support vector machine approach to classify human cytochrome P450 3A4 inhibitors

SummaryThe cytochrome P450 (CYP) enzyme superfamily plays a major role in the metabolism of commercially available drugs. Inhibition of these enzymes by a drug may result in a plasma level increase of another drug, thus leading to unwanted drug–drug interactions when two or more drugs are coadministered. Therefore, fast and reliable in silico methods predicting CYP inhibition from calculated molecular properties are an important tool which can be applied to assess both already synthesized as well as virtual compounds. We have studied the performance of support vector machines (SVMs) to classify compounds according to their potency to inhibit CYP3A4. The data set for model generation consists of more than 1300 structural diverse drug-like research molecules which were divided into training and test sets. The predictive power of SVMs crucially depends on a careful selection of parameters specifying the kernel function and the penalty for misclassifications. In this study we have investigated a procedure to identify a valid set of SVM parameters which is based on a sampling of the parameter space on a regular grid. From this set of parameters, either single SVMs or SVM committees were trained to distinguish between strong and weak inhibitors or to achieve a more realistic three-class assignment, with one class representing medium inhibitors. This workflow was studied for several kernel functions and descriptor sets. All SVM models performed significantly better than PLS-DA models which were generated from the corresponding descriptor sets. As a very promising result, simple two-dimensional (2D) descriptors yield a three-class model which correctly classifies more than 70% of the test set. Our work illustrates that SVMs used in combination with simple 2D descriptors provide a very effective and reliable tool which allows a fast assessment of CYP3A4 inhibition potency in an early in silico filtering process.

A composite model for HERG blockade

hERG blockade is one of the major toxicological problems in lead structure optimization. Reliable ligand‐based in silico models for predicting hERG blockade therefore have considerable potential for saving time and money, as patch‐clamp measurements are very expensive and no crystal structures of the hERG‐encoded channel are available. Herein we present a predictive QSAR model for hERG blockade that differentiates between specific and nonspecific binding. Specific binders are identified by preliminary pharmacophore scanning. In addition to descriptor‐based models for the compounds selected as hitting one of two different pharmacophores, we also use a model for nonspecific binding that reproduces blocking properties of molecules that do not fit either of the two pharmacophores. PLS and SVR models based on interpretable quantum mechanically derived descriptors on a literature dataset of 113 molecules reach overall R2 values between 0.60 and 0.70 for independent validation sets and R2 values between 0.39 and 0.76 after partitioning according to the pharmacophore search for the test sets. Our findings suggest that hERG blockade may occur through different types of binding, so that several different models may be necessary to assess hERG toxicity.

Form follows function: Shape analysis of protein cavities for receptor-based drug design

Identification of potential ligand‐binding pockets is an initial step in receptor‐based drug design. While many geometric or energy‐based binding‐site prediction methods characterize the size and shape of protein cavities, few of them offer an estimate of the pockets ability to bind small drug‐like molecules. Here, we present a shape‐based technique to examine binding‐site druggability from the crystal structure of a given protein target. The method includes the PocketPicker algorithm to determine putative binding‐site volumes for ligand‐interaction. Pocket shape descriptors were calculated for both known ligand binding sites and empty pockets and were then subjected to self‐organizing map clustering. Descriptors were calculated for structures derived from a database of representative drug‐protein complexes with experimentally determined binding affinities to characterize the “druggable pocketome”. The new method provides a means for selecting drug targets and potential ligand‐binding pockets based on structural considerations and addresses orphan binding sites.

Computational approaches to predict drug metabolism.

Background: Metabolism is one of the key parameters to be investigated and optimized in drug discovery projects. Metabolically unstable compounds or potential inhibitors of important enzymes should be detected as early as possible. As more compounds are synthesized than can be investigated experimentally, powerful computational methods are needed. Objective: We give an overview of state-of-the-art in-silico methods to predict experimental metabolic endpoints with a focus on the applicability in pharmaceutical industry. A macroscopic as well as a microscopic view of the metabolic fate and the interaction with metabolizing enzymes are given. Methods: Ligand-, protein- and rule-based approaches are presented. Conclusion: Although considerable progress has been made, the results of the calculations still need careful inspection. The domain of applicability of the models as well as methodological limitations have to be taken into account.

What can we learn from molecular dynamics simulations for GPCR drug design

Recent years have seen a tremendous progress in the elucidation of experimental structural information for G-protein coupled receptors (GPCRs). Although for the vast majority of pharmaceutically relevant GPCRs structural information is still accessible only by homology models the steadily increasing amount of structural information fosters the application of structure-based drug design tools for this important class of drug targets. In this article we focus on the application of molecular dynamics (MD) simulations in GPCR drug discovery programs. Typical application scenarios of MD simulations and their scope and limitations will be described on the basis of two selected case studies, namely the binding of small molecule antagonists to the human CC chemokine receptor 3 (CCR3) and a detailed investigation of the interplay between receptor dynamics and solvation for the binding of small molecules to the human muscarinic acetylcholine receptor 3 (hM3R).

Mining Electronic Laboratory Notebooks: Analysis, Retrosynthesis, and Reaction Based Enumeration

An approach to automatically analyze and use the knowledge contained in electronic laboratory notebooks (ELNs) has been developed. Reactions were reduced to their reactive center and converted to a string representation (SMIRKS) which formed the basis for reaction classification and in silico (retro-)synthesis. Of the SMIRKS that occurred at least five times, 98% successfully regenerated the original product. The extracted reaction rules (SMIRKS) and corresponding reactants span a virtual chemical space which showed a strong dependence on the size of the reactive center. Whereas relatively few robust reaction types were sufficient to describe a large part of all reactions, considerably more reaction rules were necessary to cover all reactions in the ELN. Furthermore, reaction sequences were extracted to identify frequent combinations and diversifying reaction steps. Based on the extracted knowledge a (retro-)synthesis tool was built allowing for de novo design of compounds which have a high chance of being synthetically accessible. In an example application of the de novo design tool, various feasible retrosynthetic routes to the query molecule were obtained. Reaction based enumeration along the top ranked route yielded a library of 29 920 compounds with diverse properties, 99.9% of which are novel in the sense that they are unknown to the public domain.

Bias-correction of regression models: a case study on hERG inhibition.

In the present work we develop a predictive QSAR model for the blockade of the hERG channel. Additionally, this specific end point is used as a test scenario to develop and evaluate several techniques for fusing predictions from multiple regression models. hERG inhibition models which are presented here are based on a combined data set of roughly 550 proprietary and 110 public domain compounds. Models are built using various statistical learning techniques and different sets of molecular descriptors. Single Support Vector Regression, Gaussian Process, or Random Forest models achieve root mean-squared errors of roughly 0.6 log units as determined from leave-group-out cross-validation. An analysis of the evaluation strategy on the performance estimates shows that standard leave-group-out cross-validation yields overly optimistic results. As an alternative, a clustered cross-validation scheme is introduced to obtain a more realistic estimate of the model performance. The evaluation of several techniques to combine multiple prediction models shows that the root mean squared error as determined from clustered cross-validation can be reduced from 0.73 +/- 0.01 to 0.57 +/- 0.01 using a local bias correction strategy.

Architectural Repertoire of Ligand-Binding Pockets on Protein Surfaces

Knowledge of the three‐dimensional structure of ligand binding sites in proteins provides valuable information for computer‐assisted drug design. We present a method for the automated extraction and classification of ligand binding site topologies, in which protein surface cavities are represented as branched frameworks. The procedure employs a growing neural gas approach for pocket topology assignment and pocket framework generation. We assessed the structural diversity of 623 known ligand binding site topologies based on framework cluster analysis. At a resolution of 5 Å only 23 structurally distinct topology groups were formed; this suggests an overall limited structural diversity of ligand‐accommodating protein cavities. Higher resolution allowed for identification of protein‐family specific pocket features. Pocket frameworks highlight potentially preferred modes of ligand–receptor interactions and will help facilitate the identification of druggable subpockets suitable for ligand affinity and selectivity optimization.

From Molecular Shape to Potent Bioactive Agents I: Bioisosteric Replacement of Molecular Fragments

Ligand binding to a macromolecular receptor is based on complementarity of both molecular shape and receptor–ligand interaction points. With surprisingly few exceptions, ligandbased virtual screening approaches consider only one of these two principles explicitly. To fill this gap, we have developed a method for comparison of both molecular shape and potential pharmacophore points (PPPs), termed SQUIRREL (Sophisticated QUantification of InteRaction RELationships). This ligand-based technique was applied in the design of a small, focused screening library with the aim to find novel agonists of peroxisome proliferator-activated receptors (PPARs). PPARs are pharmaceutically relevant members of the nuclear receptor superfamily. Although agonists of PPARa and PPARg have been approved for treatment of dyslipidemia and type-2 diabetes, novel leads with distinct selectivity profiles are required to improved safety and enhanced therapeutic efficacy. Among several new bioactive chemotypes, we identified a potent PPARaselective activator (EC50 = 44 5 nm) from a large compound collection with minimal experimental effort. This compound represents a scaffold-hop from known PPAR agonists and provides proof-of-concept for the potential utility of ligand-based virtual screening in early phases of drug discovery. A necessary prerequisite for SQUIRREL is one or more active reference molecules, that is, known PPARa agonists in this study (compounds 1–3, Scheme 1). The ligand binding site of all PPARs is large and deeply buried, and a great part of the ligand surface interacts with protein residues. In particular, a potent PPAR agonist should interact with residues stabilizing the AF2 “activation” helix (S280, Y314, H440, Y464 in PPARa ; S289, H323, Y473, H449 in PPARg). Therefore, we decided to follow a two-step virtual screening protocol for shape-based matching and subsequent pharmacophore-based scoring of candidate compounds. The first step was to obtain a multitude of possible shapebased alignments of the reference molecules and the screening compounds. For this task, we used our Shapelets approach. The basic idea of Shapelets is to locate similar local shapes on molecular surfaces, and compare two molecules based on the pair-wise similarity of local shape descriptions (Figure 1 a). The method starts from a smooth triangulated molecular surface, which is obtained by isosurface extraction. Isosurfaces are then decomposed into “knobs” and “planes” by fitting hyperbolic paraboloids. By representing two molecules as two sets of such hyperbolic paraboloids, pair-wise, shapebased alignments can be obtained by clique detection in association graphs. The second step was to assess the quality of the shapebased alignments in terms of a “fuzzy” pharmacophore function, which originates from the LIQUID concept. This scoring function matches Gaussian representations of PPPs and computes their overlap for two aligned molecules. The sum of all PPPs can be interpreted as a pharmacophoric density field (Figure 1 b). The overlap of two fields is computed as a similarity score indicating the match of a molecule to a given reference molecule. As an initial test of SQUIRREL, we performed retrospective virtual screening. The task was to retrieve known PPAR agonists from a large collection of druglike compounds. Virtual screening methods that use a combination of shape and pharmacophore information performed better on subtype-selective PPAR agonists than methods that exclusively used only shapeor pharmacophore-based matching (see Supporting Information). SQUIRREL was shown to be well-suited to the task of PPAR ligand retrieval, with high success rates for the top-ranking compounds. Scheme 1. Reference PPAR agonists for virtual screening. Compound 1 (GW590735): EC50 = 4 nm (PPARa),>10 mm (PPARg) ; [5] Compound 2 (Merck): IC50 = 140 nm (PPARa) IC50 = 1.7 mm (PPARg) [14] ; Compound 3 (Aventis): EC50 = 0.3 nm (PPARa), [15] activity on PPARg not reported.