Data-Driven Exploration of Selectivity and Off-Target Activities of Designated Chemical Probes

Target-specific compound selectivity for multi-target drug discovery and repurposing

Most drug molecules modulate multiple target proteins, leading either to therapeutic effects or unwanted side effects. Such target promiscuity partly contributes to high attrition rates and leads to wasted costs and time in the current drug discovery process, and makes the assessment of compound selectivity an important factor in drug development and repurposing efforts. Traditionally, selectivity of a compound is characterized in terms of its target activity profile (wide or narrow), which can be quantified using various statistical and information theoretic metrics. Even though the existing selectivity metrics are widely used for characterizing the overall selectivity of a compound, they fall short in quantifying how selective the compound is against a particular target protein (e.g., disease target of interest). We therefore extended the concept of compound selectivity towards target-specific selectivity, defined as the potency of a compound to bind to the particular protein in comparison to the other potential targets. We decompose the target-specific selectivity into two components: 1) the compound’s potency against the target of interest (absolute potency), and 2) the compound’s potency against the other targets (relative potency). The maximally selective compound-target pairs are then identified as a solution of a bi-objective optimization problem that simultaneously optimizes these two potency metrics. In computational experiments carried out using large-scale kinase inhibitor dataset, which represents a wide range of polypharmacological activities, we show how the optimization-based selectivity scoring offers a systematic approach to finding both potent and selective compounds against given kinase targets. Compared to the existing selectivity metrics, we show how the target-specific selectivity provides additional insights into the target selectivity and promiscuity of multi-targeting kinase inhibitors. Even though the selectivity score is shown to be relatively robust against both missing bioactivity values and the dataset size, we further developed a permutation-based procedure to calculate empirical p-values to assess the statistical significance of the observed selectivity of a compound-target pair in the given bioactivity dataset. We present several case studies that show how the target-specific selectivity can distinguish between highly selective and broadly-active kinase inhibitors, hence facilitating the discovery or repurposing of multi-targeting drugs.

Polypharmacology of clinical sodium glucose co-transport protein 2 inhibitors and relationship to suspected adverse drug reactions

Sodium glucose co-transporter 2 inhibitors (SGLT2i) are a promising second-line treatment strategy for type 2 diabetes mellitus (T2DM) with a developing landscape of both beneficial cardio- and nephroprotective properties and emerging adverse drug reactions (ADRs) including diabetic ketoacidosis (DKA), genetic mycotic infections, and amputations among others. A national register study (MHRA Yellow Card, UK) was used to quantify the SGLT2i's suspected ADRs relative to their Rx rate (OpenPrescribing, UK). The polypharmacology profiles of SGLT2i were data-mined (ChEMBL) for the first time. The ADR reports (n = 3629) and prescribing numbers (Rx n = 5,813,325) for each SGLT2i in the United Kingdom (from launch date to the beginning December 2019) were determined. Empagliflozin possesses the most selective SGLT2/SGLT1 inhibition profile at ~2500-fold, ~10-fold more selective than cangliflozin (~260-fold). Canagliflozin was found to also inhibit CYP at clinically achievable concentrations. We find that for overall ADR rates, empagliflozin versus dapagliflozin and empagliflozin versus canagliflozin are statistically significant (χ2 , p < .05), while dapagliflozin versus canagliflozin is not. In terms of overall ADRs, there is a greater relative rate for canagliflozin > dapagliflozin > empagliflozin. For fatalities, there is a greater relative rate for dapagliflozin > canagliflozin > empagliflozin. An organ classification that resulted in a statistically significant difference between SGLT2i was suspected infection/infestation ADRs between empagliflozin and dapagliflozin. Our findings at this stage of SGLT2i usage in the United Kingdom suggest that empagliflozin, the most selective SGLT2i, had the lowest suspected ADR incident rate (relative to prescribing) and in all reported classes of ADRs identified including infections, amputations, and DKA.

Data-driven molecular design for discovery and synthesis of novel ligands: a case study on SARS-CoV-2

Bridging systems biology and drug design, we propose a deep learning framework for de novo discovery of molecules tailored to bind with given protein targets. Our methodology is exemplified by the task of designing antiviral candidates to target SARS-CoV-2 related proteins. Crucially, our framework does not require fine-tuning for specific proteins but is demonstrated to generalize in proposing ligands with high predicted binding affinities against unseen targets. Coupling our framework with the automatic retrosynthesis prediction of IBM RXN for Chemistry, we demonstrate the feasibility of swift chemical synthesis of molecules with potential antiviral properties that were designed against a specific protein target. In particular, we synthesize an antiviral candidate designed against the host protein angiotensin converting enzyme 2 (ACE2); a surface receptor on human respiratory epithelial cells that facilitates SARS-CoV-2 cell entry through its spike glycoprotein.

This is achieved as follows. First, we train a multimodal ligand–protein binding affinity model on predicting affinities of bioactive compounds to target proteins and couple this model with pharmacological toxicity predictors. Exploiting this multi-objective as a reward function of a conditional molecular generator that consists of two variational autoencoders (VAE), our framework steers the generation toward regions of the chemical space with high-reward molecules. Specifically, we explore a challenging setting of generating ligands against unseen protein targets by performing a leave-one-out-cross-validation on 41 SARS-CoV-2-related target proteins. Using deep reinforcement learning, it is demonstrated that in 35 out of 41 cases, the generation is biased towards sampling binding ligands, with an average increase of 83% comparing to an unbiased VAE. The generated molecules exhibit favorable properties in terms of target binding affinity, selectivity and drug-likeness. We use molecular retrosynthetic models to provide a synthetic accessibility assessment of the best generated hit molecules. Finally, with this end-to-end framework, we synthesize 3-Bromobenzylamine, a potential inhibitor of the host ACE2 protein, solely based on the recommendations of a molecular retrosynthesis model and a synthesis protocol prediction model. We hope that our framework can contribute towards swift discovery of de novo molecules with desired pharmacological properties.

Enhancing Chemogenomics with Predictive Pharmacology

One of the grand challenges in contemporary chemical biology is the generation of a probe for every member of the human proteome. Probe selection and optimization strategies typically rely on experimental bioactivity data to determine the potency and selectivity of candidate molecules. However, this approach is profoundly limited by the sparsity of the known data, the annotation bias often found in the literature, and the cost of physical screening. Recent advancements in predictive pharmacology, such as the application of multitask and transfer learning, as well as the use of biologically motivated, structure-agnostic features to characterize molecules, should serve to mitigate these issues. Computational modeling likely offers the only cost-effective approach to substantially increasing the bioactivity annotation density both on the local and global scale and thus, we argue, will need to make a substantial contribution if the ambitious goals of probing the human proteome are to be realized in the foreseeable future.

Relevance of physicochemical properties and functional pharmacology data to predict the clinical safety profile of direct oral anticoagulants

Direct oral anticoagulants (DOACs) have rapidly become the drug class of choice for anticoagulation therapy in secondary care. It is known that gastrointestinal hemorrhage are potential side effects of the DOAC drug class. In this study we have investigated the relevance of molecular structure and on/off-target pharmacology as a predictor of adverse drug reactions (ADRs) for the DOAC drug class. Use of the Reaxys MedChem module allowed for data mining of all possible reported off-target effects of the DOAC class members. For the first time, the MHRA Yellow card database in combination with prescribing rates in the United Kingdom (data for n = 30 566 936 DOAC Rx (up to 2017) and ADR data n = 22 275 (up to 2018)) were used for our data comparison of DOACs. From the underlying reported data, we were able to rank the DOACs in terms of the likely adverse events we would expect to observe. We identified potential risks of ADRs based on the DOACs pharmacology including the expected GI hemorrhage, but also the unexpected risk of stroke, pulmonary embolism and kidney injury. Statistically significant (P < .001) differences were found between all DOACs and their total number of ADRs. Although the risks are small, strong statistical correlation between observed pharmacology and national ADR data is observed in three out of the five areas of concern.