Non-linear Deep Neural Network for Rapid and Accurate Prediction of Phenotypic Responses to Kinase Inhibitors

Inference of drug off-target effects on cellular signaling using interactome-based deep learning

Many diseases emerge from dysregulated cellular signaling, and drugs are often designed to target specific signaling proteins. Off-target effects are, however, common and may ultimately result in failed clinical trials. Here we develop a computer model of the cell's transcriptional response to drugs for improved understanding of their mechanisms of action. The model is based on ensembles of artificial neural networks and simultaneously infers drug-target interactions and their downstream effects on intracellular signaling. With this, it predicts transcription factors' activities, while recovering known drug-target interactions and inferring many new ones, which we validate with an independent dataset. As a case study, we analyze the effects of the drug Lestaurtinib on downstream signaling. Alongside its intended target, FLT3, the model predicts an inhibition of CDK2 that enhances the downregulation of the cell cycle-critical transcription factor FOXM1. Our approach can therefore enhance our understanding of drug signaling for therapeutic design.

Polypharmacology-based kinome screen identifies new regulators of KSHV reactivation

Kaposi's sarcoma-associated herpesvirus (KSHV) causes several human diseases including Kaposi's sarcoma (KS), a leading cause of cancer in Africa and in patients with AIDS. KS tumor cells harbor KSHV predominantly in a latent form, while typically <5% contain lytic replicating virus. Because both latent and lytic stages likely contribute to cancer initiation and progression, continued dissection of host regulators of this biological switch will provide insights into fundamental pathways controlling the KSHV life cycle and related disease pathogenesis. Several cellular protein kinases have been reported to promote or restrict KSHV reactivation, but our knowledge of these signaling mediators and pathways is incomplete. We employed a polypharmacology-based kinome screen to identify specific kinases that regulate KSHV reactivation. Those identified by the screen and validated by knockdown experiments included several kinases that enhance lytic reactivation: ERBB2 (HER2 or neu), ERBB3 (HER3), ERBB4 (HER4), MKNK2 (MNK2), ITK, TEC, and DSTYK (RIPK5). Conversely, ERBB1 (EGFR1 or HER1), MKNK1 (MNK1) and FRK (PTK5) were found to promote the maintenance of latency. Mechanistic characterization of ERBB2 pro-lytic functions revealed a signaling connection between ERBB2 and the activation of CREB1, a transcription factor that drives KSHV lytic gene expression. These studies provided a proof-of-principle application of a polypharmacology-based kinome screen for the study of KSHV reactivation and enabled the discovery of both kinase inhibitors and specific kinases that regulate the KSHV latent-to-lytic replication switch.

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

The discovery of selective and potent kinase inhibitors is crucial for the treatment of various diseases, but the process is challenging due to the high structural similarity among kinases. Efficient kinome-wide bioactivity profiling is essential for understanding kinase function and identifying selective inhibitors. In this study, we propose AiKPro, a deep learning model that combines structure-validated multiple sequence alignments and molecular 3D conformer ensemble descriptors to predict kinase-ligand binding affinities. Our deep learning model uses an attention-based mechanism to capture complex patterns in the interactions between the kinase and the ligand. To assess the performance of AiKPro, we evaluated the impact of descriptors, the predictability for untrained kinases and compounds, and kinase activity profiling based on odd ratios. Our model, AiKPro, shows good Pearson's correlation coefficients of 0.88 and 0.87 for the test set and for the untrained sets of compounds, respectively, which also shows the robustness of the model. AiKPro shows good kinase-activity profiles across the kinome, potentially facilitating the discovery of novel interactions and selective inhibitors. Our approach holds potential implications for the discovery of novel, selective kinase inhibitors and guiding rational drug design.

Polypharmacology-based kinome screen identifies new regulators of KSHV reactivation

Kaposi's sarcoma-associated herpesvirus (KSHV) causes several human diseases including Kaposi's sarcoma (KS), a leading cause of cancer in Africa and in patients with AIDS. KS tumor cells harbor KSHV predominantly in a latent form, while typically <5% contain lytic replicating virus. Because both latent and lytic stages likely contribute to cancer initiation and progression, continued dissection of host regulators of this biological switch will provide insights into fundamental pathways controlling the KSHV life cycle and related disease pathogenesis. Several cellular protein kinases have been reported to promote or restrict KSHV reactivation, but our knowledge of these signaling mediators and pathways is incomplete. We employed a polypharmacology-based kinome screen to identifiy specific kinases that regulate KSHV reactivation. Those identified by the screen and validated by knockdown experiments included several kinases that enhance lytic reactivation: ERBB2 (HER2 or neu ), ERBB3 (HER3), ERBB4 (HER4), MKNK2 (MNK2), ITK, TEC, and DSTYK (RIPK5). Conversely, ERBB1 (EGFR1 or HER1), MKNK1 (MNK1) and FRK (PTK5) were found to promote the maintenance of latency. Mechanistic characterization of ERBB2 pro-lytic functions revealed a signaling connection between ERBB2 and the activation of CREB1, a transcription factor that drives KSHV lytic gene expression. These studies provided a proof-of-principle application of a polypharmacology-based kinome screen for the study of KSHV reactivation and enabled the discovery of both kinase inhibitors and specific kinases that regulate the KSHV latent-to-lytic replication switch.

Author Summary

Kaposi's sarcoma-associated herpesvirus (KSHV) causes Kaposi's sarcoma, a cancer particularly prevalent in Africa. In cancer cells, the virus persists in a quiescent form called latency, in which only a few viral genes are made. Periodically, the virus switches into an active replicative cycle in which most of the viral genes are made and new virus is produced. What controls the switch from latency to active replication is not well understood, but cellular kinases, enzymes that control many cellular processes, have been implicated. Using a cell culture model of KSHV reactivation along with an innovative screening method that probes the effects of many cellular kinases simultaneously, we identified drugs that significantly limit KSHV reactivation, as well as specific kinases that either enhance or restrict KSHV replicative cycle. Among these were the ERBB kinases which are known to regulate growth of cancer cells. Understanding how these and other kinases contribute to the switch leading to production of more infectious virus helps us understand the mediators and mechanisms of KSHV diseases. Additionally, because kinase inhibitors are proving to be effective for treating other diseases including some cancers, identifying ones that restrict KSHV replicative cycle may lead to new approaches to treating KSHV-related diseases.

Deep Neural Network Modeling Identifies Biomarkers of Response to Immune-checkpoint Therapy

Immunotherapy has shown significant promise as a treatment for cancer, such as lung cancer and melanoma. However, only 10%–30% of the patients respond to treatment with immune checkpoint blockers (ICBs), underscoring the need for biomarkers to predict response to immunotherapy. Here, we developed DeepGeneX, a computational framework that uses advanced deep neural network modeling and feature elimination to reduce single-cell RNA-seq data on ∼26,000 genes to six of the most important genes (CCR7, SELL, GZMB, WARS, GZMH, and LGALS1), that accurately predict response to immunotherapy. We also discovered that the high LGALS1 and WARS-expressing macrophage population represent a biomarker for ICB therapy nonresponders, suggesting that these macrophages may be a target for improving ICB response. Taken together, DeepGeneX enables biomarker discovery and provides an understanding of the molecular basis for the model’s predictions.

•

Predicting biomarkers for immunotherapy response remains a challenge

•

DeepGeneX combines neural networks with single-cell RNAseq to predict responders

•

LGALS1 and WARS-expressing macrophages in nonresponders impact T cell activation

•

DeepGeneX enables biomarker discovery and elucidates underlying molecular mechanism

Drug Repositioning and Subgroup Discovery for Precision Medicine Implementation in Triple Negative Breast Cancer

Simple Summary

The heterogeneity of complicated diseases like cancer negatively affects patients’ responses to treatment. Finding homogeneous subgroups of patients within the cancer population and finding the appropriate treatment for each subgroup will improve patients’ survival. In this study, we focus on triple-negative breast cancer (TNBC), where approximately 80% of patients do not entirely respond to chemotherapy. Our aim is to find subgroups of TNBC patients and identify drugs that have the potential to tailor treatments for each group through drug repositioning. After applying our method to TNBC, we found that different targeted mechanisms were suggested for different groups of patients. Our findings could help the research community to gain a better understanding of different subgroups within the TNBC population and can help the drugs to be repurposed with explainable results regarding the targeted mechanism.

Abstract

Breast cancer (BC) is the leading cause of death among female patients with cancer. Patients with triple-negative breast cancer (TNBC) have the lowest survival rate. TNBC has substantial heterogeneity within the BC population. This study utilized our novel patient stratification and drug repositioning method to find subgroups of BC patients that share common genetic profiles and that may respond similarly to the recommended drugs. After further examination of the discovered patient subgroups, we identified five homogeneous druggable TNBC subgroups. A drug repositioning algorithm was then applied to find the drugs with a high potential for each subgroup. Most of the top drugs for these subgroups were chemotherapy used for various types of cancer, including BC. After analyzing the biological mechanisms targeted by these drugs, ferroptosis was the common cell death mechanism induced by the top drugs in the subgroups with neoplasm subdivision and race as clinical variables. In contrast, the antioxidative effect on cancer cells was the common targeted mechanism in the subgroup of patients with an age less than 50. Literature reviews were used to validate our findings, which could provide invaluable insights to streamline the drug repositioning process and could be further studied in a wet lab setting and in clinical trials.

Utilizing preclinical models to develop targeted therapies for rare central nervous system cancers

Patients with rare central nervous system (CNS) tumors typically have a poor prognosis and limited therapeutic options. Historically, these cancers have been difficult to study due to small number of patients. Recent technological advances have identified molecular drivers of some of these rare cancers which we can now use to generate representative preclinical models of these diseases. In this review, we outline the advantages and disadvantages of different models, emphasizing the utility of various in vitro and ex vivo models for target discovery and mechanistic inquiry and multiple in vivo models for therapeutic validation. We also highlight recent literature on preclinical model generation and screening approaches for ependymomas, histone mutated high-grade gliomas, and atypical teratoid rhabdoid tumors, all of which are rare CNS cancers that have recently established genetic or epigenetic drivers. These preclinical models are critical to advancing targeted therapeutics for these rare CNS cancers that currently rely on conventional treatments.

Machine learning identifies molecular regulators and therapeutics for targeting SARS-CoV2-induced cytokine release

Although 15-20% of COVID-19 patients experience hyper-inflammation induced by massive cytokine production, cellular triggers of this process and strategies to target them remain poorly understood. Here, we show that the N-terminal domain (NTD) of the SARS-CoV-2 spike protein substantially induces multiple inflammatory molecules in myeloid cells and human PBMCs. Using a combination of phenotypic screening with machine learning-based modeling, we identified and experimentally validated several protein kinases, including JAK1, EPHA7, IRAK1, MAPK12, and MAP3K8, as essential downstream mediators of NTD-induced cytokine production, implicating the role of multiple signaling pathways in cytokine release. Further, we found several FDA-approved drugs, including ponatinib, and cobimetinib as potent inhibitors of the NTD-mediated cytokine release. Treatment with ponatinib outperforms other drugs, including dexamethasone and baricitinib, inhibiting all cytokines in response to the NTD from SARS-CoV-2 and emerging variants. Finally, ponatinib treatment inhibits lipopolysaccharide-mediated cytokine release in myeloid cells in vitro and lung inflammation mouse model. Together, we propose that agents targeting multiple kinases required for SARS-CoV-2-mediated cytokine release, such as ponatinib, may represent an attractive therapeutic option for treating moderate to severe COVID-19.

Nanomedicine of tyrosine kinase inhibitors

Recent progress in nanomedicine and targeted therapy brings new breeze into the field of therapeutic applications of tyrosine kinase inhibitors (TKIs). These drugs are known for many side effects due to non-targeted mechanism of action that negatively impact quality of patients' lives or that are responsible for failure of the drugs in clinical trials. Some nanocarrier properties provide improvement of drug efficacy, reduce the incidence of adverse events, enhance drug bioavailability, helps to overcome the blood-brain barrier, increase drug stability or allow for specific delivery of TKIs to the diseased cells. Moreover, nanotechnology can bring new perspectives into combination therapy, which can be highly efficient in connection with TKIs. Lastly, nanotechnology in combination with TKIs can be utilized in the field of theranostics, i.e. for simultaneous therapeutic and diagnostic purposes. The review provides a comprehensive overview of advantages and future prospects of conjunction of nanotransporters with TKIs as a highly promising approach to anticancer therapy.