A Real-world Toxicity Atlas Shows that Adverse Events of Combination Therapies Commonly Result in Additive Interactions.

PURPOSE: Combination therapies are a promising approach for improving cancer treatment, but it is challenging to predict their resulting adverse events in a real-world setting. EXPERIMENTAL DESIGN: We provide here a proof-of-concept study using 15 million patient records from the FDA Adverse Event Reporting System (FAERS). Complex adverse event frequencies of drugs or their combinations were visualized as heat maps onto a two-dimensional grid. Adverse event frequencies were shown as colors to assess the ratio between individual and combined drug effects. To capture these patterns, we trained a convolutional neural network (CNN) autoencoder using 7,300 single-drug heat maps. In addition, statistical synergy analyses were performed on the basis of BLISS independence or χ2 testing. RESULTS: The trained CNN model was able to decode patterns, showing that adverse events occur in global rather than isolated and unique patterns. Patterns were not likely to be attributed to disease symptoms given their relatively limited contribution to drug-associated adverse events. Pattern recognition was validated using trial data from ClinicalTrials.gov and drug combination data. We examined the adverse event interactions of 140 drug combinations known to be avoided in the clinic and found that near all of them showed additive rather than synergistic interactions, also when assessed statistically. CONCLUSIONS: Our study provides a framework for analyzing adverse events and suggests that adverse drug interactions commonly result in additive effects with a high level of overlap of adverse event patterns. These real-world insights may advance the implementation of new combination therapies in clinical practice.

Predicting the target landscape of kinase inhibitors using 3D convolutional neural networks.

Many therapies in clinical trials are based on single drug-single target relationships. To further extend this concept to multi-target approaches using multi-targeted drugs, we developed a machine learning pipeline to unravel the target landscape of kinase inhibitors. This pipeline, which we call 3D-KINEssence, uses a new type of protein fingerprints (3D FP) based on the structure of kinases generated through a 3D convolutional neural network (3D-CNN). These 3D-CNN kinase fingerprints were matched to molecular Morgan fingerprints to predict the targets of each respective kinase inhibitor based on available bioactivity data. The performance of the pipeline was evaluated on two test sets: a sparse drug-target set where each drug is matched in most cases to a single target and also on a densely-covered drug-target set where each drug is matched to most if not all targets. This latter set is more challenging to train, given its non-exclusive character. Our model's root-mean-square error (RMSE) based on the two datasets was 0.68 and 0.8, respectively. These results indicate that 3D FP can predict the target landscape of kinase inhibitors at around 0.8 log units of bioactivity. Our strategy can be utilized in proteochemometric or chemogenomic workflows by consolidating the target landscape of kinase inhibitors.

To Target or Not to Target Schistosoma mansoni Cyclic Nucleotide Phosphodiesterase 4A?

Schistosomiasis is a neglected tropical disease with high morbidity. Recently, the Schistosoma mansoni phosphodiesterase SmPDE4A was suggested as a putative new drug target. To support SmPDE4A targeted drug discovery, we cloned, isolated, and biochemically characterized the full-length and catalytic domains of SmPDE4A. The enzymatically active catalytic domain was crystallized in the apo-form (PDB code: 6FG5) and in the cAMP- and AMP-bound states (PDB code: 6EZU). The SmPDE4A catalytic domain resembles human PDE4 more than parasite PDEs because it lacks the parasite PDE-specific P-pocket. Purified SmPDE4A proteins (full-length and catalytic domain) were used to profile an in-house library of PDE inhibitors (PDE4NPD toolbox). This screening identified tetrahydrophthalazinones and benzamides as potential hits. The PDE inhibitor NPD-0001 was the most active tetrahydrophthalazinone, whereas the approved human PDE4 inhibitors roflumilast and piclamilast were the most potent benzamides. As a follow-up, 83 benzamide analogs were prepared, but the inhibitory potency of the initial hits was not improved. Finally, NPD-0001 and roflumilast were evaluated in an in vitro anti-S. mansoni assay. Unfortunately, both SmPDE4A inhibitors were not effective in worm killing and only weakly affected the egg-laying at high micromolar concentrations. Consequently, the results with these SmPDE4A inhibitors strongly suggest that SmPDE4A is not a suitable target for anti-schistosomiasis therapy.

KLIFS: an overhaul after the first 5 years of supporting kinase research.

Kinases are a prime target of drug development efforts with >60 drug approvals in the past two decades. Due to the research into this protein family, a wealth of data has been accumulated that keeps on growing. KLIFS-Kinase-Ligand Interaction Fingerprints and Structures-is a structural database focusing on how kinase inhibitors interact with their targets. The aim of KLIFS is to support (structure-based) kinase research through the systematic collection, annotation, and processing of kinase structures. Now, 5 years after releasing the initial KLIFS website, the database has undergone a complete overhaul with a new website, new logo, and new functionalities. In this article, we start by looking back at how KLIFS has been used by the research community, followed by a description of the renewed KLIFS, and conclude with showcasing the functionalities of KLIFS. Major changes include the integration of approved drugs and inhibitors in clinical trials, extension of the coverage to atypical kinases, and a RESTful API for programmatic access. KLIFS is available at the new domain https://klifs.net.

The Landscape of Atypical and Eukaryotic Protein Kinases.

Kinases are attractive anticancer targets due to their central role in the growth, survival, and therapy resistance of tumor cells. This review explores the two primary kinase classes, the eukaryotic protein kinases (ePKs) and the atypical protein kinases (aPKs), and provides a structure-centered comparison of their sequences, structures, hydrophobic spines, mutation and SNP hotspots, and inhibitor interaction patterns. Despite the limited sequence similarity between these two classes, atypical kinases commonly share the archetypical kinase fold but lack conserved eukaryotic kinase motifs and possess altered hydrophobic spines. Furthermore, atypical kinase inhibitors explore only a limited number of binding modes both inside and outside the orthosteric binding site. The distribution of genetic variations in both classes shows multiple ways they can interfere with kinase inhibitor binding. This multilayered review provides a research framework bridging the eukaryotic and atypical kinase classes.

PDEStrIAn: A Phosphodiesterase Structure and Ligand Interaction Annotated Database As a Tool for Structure-Based Drug Design.

A systematic analysis is presented of the 220 phosphodiesterase (PDE) catalytic domain crystal structures present in the Protein Data Bank (PDB) with a focus on PDE-ligand interactions. The consistent structural alignment of 57 PDE ligand binding site residues enables the systematic analysis of PDE-ligand interaction fingerprints (IFPs), the identification of subtype-specific PDE-ligand interaction features, and the classification of ligands according to their binding modes. We illustrate how systematic mining of this phosphodiesterase structure and ligand interaction annotated (PDEStrIAn) database provides new insights into how conserved and selective PDE interaction hot spots can accommodate the large diversity of chemical scaffolds in PDE ligands. A substructure analysis of the cocrystallized PDE ligands in combination with those in the ChEMBL database provides a toolbox for scaffold hopping and ligand design. These analyses lead to an improved understanding of the structural requirements of PDE binding that will be useful in future drug discovery studies.

KLIFS: a structural kinase-ligand interaction database.

Protein kinases play a crucial role in cell signaling and are important drug targets in several therapeutic areas. The KLIFS database contains detailed structural kinase-ligand interaction information derived from all (>2900) structures of catalytic domains of human and mouse protein kinases deposited in the Protein Data Bank in order to provide insights into the structural determinants of kinase-ligand binding and selectivity. The kinase structures have been processed in a consistent manner by systematically analyzing the structural features and molecular interaction fingerprints (IFPs) of a predefined set of 85 binding site residues with bound ligands. KLIFS has been completely rebuilt and extended (>65% more structures) since its first release as a data set, including: novel automated annotation methods for (i) the assessment of ligand-targeted subpockets and the analysis of (ii) DFG and (iii) αC-helix conformations; improved and automated protocols for (iv) the generation of sequence/structure alignments, (v) the curation of ligand atom and bond typing for accurate IFP analysis and (vi) weekly database updates. KLIFS is now accessible via a website (http://klifs.vu-compmedchem.nl) that provides a comprehensive visual presentation of different types of chemical, biological and structural chemogenomics data, and allows the user to easily access, compare, search and download the data.