Towards holistic Compound Quality Scores: Extending ligand efficiency indices with compound pharmacokinetic characteristics.

The suitability of small molecules as oral drugs is often assessed by simple physicochemical rules, the application of ligand efficiency scores or by composite scores based on physicochemical compound properties. These rules and scores are empirical and typically lack mechanistic background, such as information on pharmacokinetics (PK). We introduce new types of Compound Quality Scores (CQS, specifically called dose scores and cmax scores), which explicitly include predicted or, when available, experimental PK parameters and combine these with on-target potency. These CQS scores are surrogates for an estimated dose and corresponding cmax and allow prioritizing of compounds within test cascades as well as before synthesis. We demonstrate the complementarity and, in most cases, superior performance relative to existing efficiency metrics by project examples.

Benchmarking Molecular Feature Attribution Methods with Activity Cliffs.

Feature attribution techniques are popular choices within the explainable artificial intelligence toolbox, as they can help elucidate which parts of the provided inputs used by an underlying supervised-learning method are considered relevant for a specific prediction. In the context of molecular design, these approaches typically involve the coloring of molecular graphs, whose presentation to medicinal chemists can be useful for making a decision of which compounds to synthesize or prioritize. The consistency of the highlighted moieties alongside expert background knowledge is expected to contribute to the understanding of machine-learning models in drug design. Quantitative evaluation of such coloring approaches, however, has so far been limited to substructure identification tasks. We here present an approach that is based on maximum common substructure algorithms applied to experimentally-determined activity cliffs. Using the proposed benchmark, we found that molecule coloring approaches in conjunction with classical machine-learning models tend to outperform more modern, graph-neural-network alternatives. The provided benchmark data are fully open sourced, which we hope will facilitate the testing of newly developed molecular feature attribution techniques.

Artificial intelligence in drug discovery: recent advances and future perspectives.

Introduction: Artificial intelligence (AI) has inspired computer-aided drug discovery. The widespread adoption of machine learning, in particular deep learning, in multiple scientific disciplines, and the advances in computing hardware and software, among other factors, continue to fuel this development. Much of the initial skepticism regarding applications of AI in pharmaceutical discovery has started to vanish, consequently benefitting medicinal chemistry.Areas covered: The current status of AI in chemoinformatics is reviewed. The topics discussed herein include quantitative structure-activity/property relationship and structure-based modeling, de novo molecular design, and chemical synthesis prediction. Advantages and limitations of current deep learning applications are highlighted, together with a perspective on next-generation AI for drug discovery.Expert opinion: Deep learning-based approaches have only begun to address some fundamental problems in drug discovery. Certain methodological advances, such as message-passing models, spatial-symmetry-preserving networks, hybrid de novo design, and other innovative machine learning paradigms, will likely become commonplace and help address some of the most challenging questions. Open data sharing and model development will play a central role in the advancement of drug discovery with AI.

Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance Assessment.

Graph neural networks are able to solve certain drug discovery tasks such as molecular property prediction and de novo molecule generation. However, these models are considered "black-box" and "hard-to-debug". This study aimed to improve modeling transparency for rational molecular design by applying the integrated gradients explainable artificial intelligence (XAI) approach for graph neural network models. Models were trained for predicting plasma protein binding, hERG channel inhibition, passive permeability, and cytochrome P450 inhibition. The proposed methodology highlighted molecular features and structural elements that are in agreement with known pharmacophore motifs, correctly identified property cliffs, and provided insights into unspecific ligand-target interactions. The developed XAI approach is fully open-sourced and can be used by practitioners to train new models on other clinically relevant endpoints.

Guided Iterative Substructure Search (GI-SSS) - A New Trick for an Old Dog.

Substructure search (SSS) is a fundamental technique supported by various chemical information systems. Many users apply it in an iterative manner: they modify their queries to shape the composition of the retrieved hit sets according to their needs. We propose and evaluate two heuristic extensions of SSS aimed at simplifying these iterative query modifications by collecting additional information during query processing and visualizing this information in an intuitive way. This gives the user a convenient feedback on how certain changes to the query would affect the retrieved hit set and reduces the number of trial-and-error cycles needed to generate an optimal search result. The proposed heuristics are simple, yet surprisingly effective and can be easily added to existing SSS implementations.

Matched Peptides: Tuning Matched Molecular Pair Analysis for Biopharmaceutical Applications.

Biopharmaceuticals hold great promise for the future of drug discovery. Nevertheless, rational drug design strategies are mainly focused on the discovery of small synthetic molecules. Herein we present matched peptides, an innovative analysis technique for biological data related to peptide and protein sequences. It represents an extension of matched molecular pair analysis toward macromolecular sequence data and allows quantitative predictions of the effect of single amino acid substitutions on the basis of statistical data on known transformations. We demonstrate the application of matched peptides to a data set of major histocompatibility complex class II peptide ligands and discuss the trends captured with respect to classical quantitative structure-activity relationship approaches as well as structural aspects of the investigated protein-peptide interface. We expect our novel readily interpretable tool at the interface of cheminformatics and bioinformatics to support the rational design of biopharmaceuticals and give directions for further development of the presented methodology.

SAR matrices: automated extraction of information-rich SAR tables from large compound data sets.

We introduce the SAR matrix data structure that is designed to elucidate SAR patterns produced by groups of structurally related active compounds, which are extracted from large data sets. SAR matrices are systematically generated and sorted on the basis of SAR information content. Matrix generation is computationally efficient and enables processing of large compound sets. The matrix format is reminiscent of SAR tables, and SAR patterns revealed by different categories of matrices are easily interpretable. The structural organization underlying matrix formation is more flexible than standard R-group decomposition schemes. Hence, the resulting matrices capture SAR information in a comprehensive manner.

Exploration of structure-activity relationship determinants in analogue series.

A computational methodology is introduced to systematically organize compound analogue series according to substitution sites and identify combinations of sites that determine structure-activity relationships (SARs) and make large contributions to SAR discontinuity. These sites are prime targets for further chemical modification. The approach involves the analysis of substitution patterns in "combinatorial analogue graphs" (CAG) and the application of an SAR analysis function to evaluate contributions of variable R-groups. It is applicable to analogue series spanning different potency ranges, for example, analogues taken from lead optimization programs or screening data sets (where potency differences might be subtle). In addition to determining key substitution patterns that cause significant SAR discontinuity, CAG analysis also identifies "SAR holes", i.e., nonexplored combinations of substitution sites, and SAR regions that are under-sampled in analogue series.

Merging chemical and biological space: Structural mapping of enzyme binding pocket space.

Structure-based drug design tries to mutually map pharmacological space populated by putative target proteins onto chemical space comprising possible small molecule drug candidates. Both spaces are connected where proteins and ligands recognize each other: in the binding pockets. Therefore, it is highly relevant to study the properties of the space composed by all possible binding cavities. In the present contribution, a global mapping of protein cavity space is presented by extracting consensus cavities from individual members of protein families and clustering them in terms of their shape and exposed physicochemical properties. Discovered similarities indicate common binding epitopes in binding pockets independent of any possibly given similarity in sequence and fold space. Unexpected links between remote targets indicate possible cross-reactivity of ligands and suggest putative side effects. The global clustering of cavity space is compared to a similar clustering of sequence and fold space and compared to chemical ligand space spanned by the chemical properties of small molecules found in binding pockets of crystalline complexes. The overall similarity architecture of sequence, fold, and cavity space differs significantly. Similarities in cavity space can be mapped best to similarities in ligand binding space indicating possible cross-reactivities. Most cross-reactivities affect co-factor and other endogenous ligand binding sites.

Structure-activity relationship anatomy by network-like similarity graphs and local structure-activity relationship indices.

The study of structure-activity relationships (SARs) of small molecules is of fundamental importance in medicinal chemistry and drug design. Here, we introduce an approach that combines the analysis of similarity-based molecular networks and SAR index distributions to identify multiple SAR components present within sets of active compounds. Different compound classes produce molecular networks of distinct topology. Subsets of compounds related by different local SARs are often organized in small communities in networks annotated with potency information. Many local SAR communities are not isolated but connected by chemical bridges, i.e., similar molecules occurring in different local SAR contexts. The analysis makes it possible to relate local and global SAR features to each other and identify key compounds that are major determinants of SAR characteristics. In many instances, such compounds represent start and end points of chemical optimization pathways and aid in the selection of other candidates from their communities.

Functional classification of protein kinase binding sites using Cavbase.

Increasingly, drug-discovery processes focus on complete gene families. Tools for analyzing similarities and differences across protein families are important for the understanding of key functional features of proteins. Herein we present a method for classifying protein families on the basis of the properties of their active sites. We have developed Cavbase, a method for describing and comparing protein binding pockets, and show its application to the functional classification of the binding pockets of the protein family of protein kinases. A diverse set of kinase cavities is mutually compared and analyzed in terms of recurring functional recognition patterns in the active sites. We are able to propose a relevant classification based on the binding motifs in the active sites. The obtained classification provides a novel perspective on functional properties across protein space. The classification of the MAP and the c-Abl kinases is analyzed in detail, showing a clear separation of the respective kinase subfamilies. Remarkable cross-relations among protein kinases are detected, in contrast to sequence-based classifications, which are not able to detect these relations. Furthermore, our classification is able to highlight features important in the optimization of protein kinase inhibitors. Using small-molecule inhibition data we could rationalize cross-reactivities between unrelated kinases which become apparent in the structural comparison of their binding sites. This procedure helps in the identification of other possible kinase targets that behave similarly in "binding pocket space" to the kinase under consideration.

Multiple graph alignment for the structural analysis of protein active sites.

Graphs are frequently used to describe the geometry and also the physicochemical composition of protein active sites. Here, the concept of graph alignment as a novel method for the structural analysis of protein binding pockets is presented. Using inexact graph-matching techniques, one is able to identify both conserved areas and regions of difference among different binding pockets. Thus, using multiple graph alignments, it is possible to characterize functional protein families and to examine differences among related protein families independent of sequence or fold homology. Optimized algorithms are described for the efficient calculation of multiple graph alignments for the analysis of physicochemical descriptors representing protein binding pockets. Additionally, it is shown how the calculated graph alignments can be analyzed to identify structural features that are characteristic for a given protein family and also features that are discriminative among related families. The methods are applied to a substantial high-quality subset of the PDB database and their ability to successfully characterize and classify 10 highly populated functional protein families is shown. Additionally, two related protein families from the group of serine proteases are examined and important structural differences are detected automatically and efficiently.

Strategies to search and design stabilizers of protein-protein interactions: a feasibility study.

Since protein-protein interactions play a pivotal role in the communication on the molecular level in virtually every biological system and process, the search and design for modulators of such interactions is of utmost importance. In recent years many inhibitors for specific protein-protein interactions have been developed, however, in only a few cases, small and druglike molecules are able to interfere in the complex formation of proteins. On the other hand, there are several small molecules known to modulate protein-protein interactions by means of stabilizing an already assembled complex. To achieve this goal, a ligand is binding to a pocket, which is located rim-exposed at the interface of the interacting proteins, for example as the phytotoxin Fusicoccin, which stabilizes the interaction of plant H+-ATPase and 14-3-3 protein by nearly a factor of 100. To suggest alternative leads, we performed a virtual screening campaign to discover new molecules putatively stabilizing this complex. Furthermore, we screen a dataset of 198 transient recognition protein-protein complexes for cavities, which are located rim-exposed at their interfaces. We provide evidence for high similarity between such rim-exposed cavities and usual ligands accommodating active sites of enzymes. This analysis suggests that rim-exposed cavities at protein-protein interfaces are druggable binding sites. Therefore, the principle of stabilizing protein-protein interactions seems to be a promising alternative to the approach of the competitive inhibition of such interactions by small molecules.

From the similarity analysis of protein cavities to the functional classification of protein families using cavbase.

In this contribution, the classification of protein binding sites using the physicochemical properties exposed to their pockets is presented. We recently introduced Cavbase, a method for describing and comparing protein binding pockets on the basis of the geometrical and physicochemical properties of their active sites. Here, we present algorithmic and methodological enhancements in the Cavbase property description and in the cavity comparison step. We give examples of the Cavbase similarity analysis detecting pronounced similarities in the binding sites of proteins unrelated in sequence. A similarity search using SARS M(pro) protease subpockets as queries retrieved ligands and ligand fragments accommodated in a physicochemical environment similar to that of the query. This allowed the characterization of the protease recognition pockets and the identification of molecular building blocks that can be incorporated into novel antiviral compounds. A cluster analysis procedure for the functional classification of binding pockets was implemented and calibrated using a diverse set of enzyme binding sites. Two relevant protein families, the alpha-carbonic anhydrases and the protein kinases, are used to demonstrate the scope of our cluster approach. We propose a relevant classification of both protein families, on the basis of the binding motifs in their active sites. The classification provides a new perspective on functional properties across a protein family and is able to highlight features important for potency and selectivity. Furthermore, this information can be used to identify possible cross-reactivities among proteins due to similarities in their binding sites.

Clustering of gene expression data using a local shape-based similarity measure.

MOTIVATION: Microarray technology enables the study of gene expression in large scale. The application of methods for data analysis then allows for grouping genes that show a similar expression profile and that are thus likely to be co-regulated. A relationship among genes at the biological level often presents itself by locally similar and potentially time-shifted patterns in their expression profiles. RESULTS: Here, we propose a new method (CLARITY; Clustering with Local shApe-based similaRITY) for the analysis of microarray time course experiments that uses a local shape-based similarity measure based on Spearman rank correlation. This measure does not require a normalization of the expression data and is comparably robust towards noise. It is also able to detect similar and even time-shifted sub-profiles. To this end, we implemented an approach motivated by the BLAST algorithm for sequence alignment. We used CLARITY to cluster the times series of gene expression data during the mitotic cell cycle of the yeast Saccharomyces cerevisiae. The obtained clusters were related to the MIPS functional classification to assess their biological significance. We found that several clusters were significantly enriched with genes that share similar or related functions.

Efficient similarity search in protein structure databases by k-clique hashing.

MOTIVATION: Graph-based clique-detection techniques are widely used for the recognition of common substructures in proteins. They permit the detection of resemblances that are independent of sequence or fold homologies and are also able to handle conformational flexibility. Their high computational complexity is often a limiting factor and prevents a detailed and fine-grained modeling of the protein structure. RESULTS: We present an efficient two-step method that significantly speeds up the detection of common substructures, especially when used to screen larger databases. It combines the advantages from both clique-detection and geometric hashing. The method is applied to an established approach for the comparison of protein binding-pockets, and some empirical results are presented. AVAILABILITY: Upon request from the authors.