Compound Activity Prediction with Dose-Dependent Transcriptomic Profiles and Deep Learning.

Predicting compound activity in assays is a long-standing challenge in drug discovery. Computational models based on compound-induced gene expression signatures from a single profiling assay have shown promise toward predicting compound activity in other, seemingly unrelated, assays. Applications of such models include predicting mechanisms-of-action (MoA) for phenotypic hits, identifying off-target activities, and identifying polypharmacologies. Here, we introduce transcriptomics-to-activity transformer (TAT) models that leverage gene expression profiles observed over compound treatment at multiple concentrations to predict the compound activity in other biochemical or cellular assays. We built TAT models based on gene expression data from a RASL-seq assay to predict the activity of 2692 compounds in 262 dose-response assays. We obtained useful models for 51% of the assays, as determined through a realistic held-out set. Prospectively, we experimentally validated the activity predictions of a TAT model in a malaria inhibition assay. With a 63% hit rate, TAT successfully identified several submicromolar malaria inhibitors. Our results thus demonstrate the potential of transcriptomic responses over compound concentration and the TAT modeling framework as a cost-efficient way to identify the bioactivities of promising compounds across many assays.

Discovery and Preclinical Pharmacology of INE963, a Potent and Fast-Acting Blood-Stage Antimalarial with a High Barrier to Resistance and Potential for Single-Dose Cures in Uncomplicated Malaria.

A series of 5-aryl-2-amino-imidazothiadiazole (ITD) derivatives were identified by a phenotype-based high-throughput screening using a blood stage Plasmodium falciparum (Pf) growth inhibition assay. A lead optimization program focused on improving antiplasmodium potency, selectivity against human kinases, and absorption, distribution, metabolism, excretion, and toxicity properties and extended pharmacological profiles culminated in the identification of INE963 (1), which demonstrates potent cellular activity against Pf 3D7 (EC50 = 0.006 µM) and achieves "artemisinin-like" kill kinetics in vitro with a parasite clearance time of <24 h. A single dose of 30 mg/kg is fully curative in the Pf-humanized severe combined immunodeficient mouse model. INE963 (1) also exhibits a high barrier to resistance in drug selection studies and a long half-life (T1/2) across species. These properties suggest the significant potential for INE963 (1) to provide a curative therapy for uncomplicated malaria with short dosing regimens. For these reasons, INE963 (1) was progressed through GLP toxicology studies and is now undergoing Ph1 clinical trials.

ARB-1740, a RNA Interference Therapeutic for Chronic Hepatitis B Infection.

Current approved nucleoside analogue treatments for chronic hepatitis B virus (HBV) infection are effective at controlling viral titer but are not curative and have minimal impact on the production of viral proteins such as surface antigen (HBsAg), the HBV envelope protein believed to play a role in maintaining the immune tolerant state required for viral persistence. Novel agents are needed to effect HBV cure, and reduction of HBV antigenemia may potentiate activation of effective and long-lasting host immune control. ARB-1740 is a clinical stage RNA interference agent composed of three siRNAs delivered using lipid nanoparticle technology. In a number of cell and animal models of HBV, ARB-1740 caused HBV RNA reduction, leading to inhibition of multiple elements of the viral life cycle including HBsAg, HBeAg, and HBcAg viral proteins as well as replication marker HBV DNA. ARB-1740 demonstrated pan-genotypic activity in vitro and in vivo, targeting three distinct highly conserved regions of the HBV genome, and effectively inhibited replication of nucleoside analogue-resistant HBV variants. Combination of ARB-1740 with a capsid inhibitor and pegylated interferon-alpha led to greater liver HBsAg reduction which correlated with more robust induction of innate immune responses in a human chimeric mouse model of HBV. The preclinical profile of ARB-1740 demonstrates the promise of RNA interference and HBV antigen reduction in treatment strategies driving toward a cure for HBV.