Individualized Prediction of Drug Response and Rational Combination Therapy in NSCLC Using Artificial Intelligence-Enabled Studies of Acute Phosphoproteomic Changes

The Virtual Child

SUMMARY

We are building the world's first Virtual Child-a computer model of normal and cancerous human development at the level of each individual cell. The Virtual Child will "develop cancer" that we will subject to unlimited virtual clinical trials that pinpoint, predict, and prioritize potential new treatments, bringing forward the day when no child dies of cancer, giving each one the opportunity to lead a full and healthy life.

Deep Learning in Phosphoproteomics: Methods and Application in Cancer Drug Discovery

Protein phosphorylation is a key post-translational modification (PTM) that is a central regulatory mechanism of many cellular signaling pathways. Several protein kinases and phosphatases precisely control this biochemical process. Defects in the functions of these proteins have been implicated in many diseases, including cancer. Mass spectrometry (MS)-based analysis of biological samples provides in-depth coverage of phosphoproteome. A large amount of MS data available in public repositories has unveiled big data in the field of phosphoproteomics. To address the challenges associated with handling large data and expanding confidence in phosphorylation site prediction, the development of many computational algorithms and machine learning-based approaches have gained momentum in recent years. Together, the emergence of experimental methods with high resolution and sensitivity and data mining algorithms has provided robust analytical platforms for quantitative proteomics. In this review, we compile a comprehensive collection of bioinformatic resources used for the prediction of phosphorylation sites, and their potential therapeutic applications in the context of cancer.

Rational combinations of targeted cancer therapies: background, advances and challenges

Over the past two decades, elucidation of the genetic defects that underlie cancer has resulted in a plethora of novel targeted cancer drugs. Although these agents can initially be highly effective, resistance to single-agent therapies remains a major challenge. Combining drugs can help avoid resistance, but the number of possible drug combinations vastly exceeds what can be tested clinically, both financially and in terms of patient availability. Rational drug combinations based on a deep understanding of the underlying molecular mechanisms associated with therapy resistance are potentially powerful in the treatment of cancer. Here, we discuss the mechanisms of resistance to targeted therapies and how effective drug combinations can be identified to combat resistance. The challenges in clinically developing these combinations and future perspectives are considered.

Mutational analysis and protein profiling predict drug sensitivity in multiple myeloma cell lines

INTRODUCTION

Multiple myeloma (MM) is a heterogeneous disease where cancer-driver mutations and aberrant signaling may lead to disease progression and drug resistance. Drug responses vary greatly, and there is an unmet need for biomarkers that can guide precision cancer medicine in this disease.

METHODS

To identify potential predictors of drug sensitivity, we applied integrated data from drug sensitivity screening, mutational analysis and functional signaling pathway profiling in 9 cell line models of MM. We studied the sensitivity to 33 targeted drugs and their association with the mutational status of cancer-driver genes and activity level of signaling proteins.

RESULTS

We found that sensitivity to mitogen-activated protein kinase kinase 1 (MEK1) and phosphatidylinositol-3 kinase (PI3K) inhibitors correlated with mutations in NRAS/KRAS, and PI3K family genes, respectively. Phosphorylation status of MEK1 and protein kinase B (AKT) correlated with sensitivity to MEK and PI3K inhibition, respectively. In addition, we found that enhanced phosphorylation of proteins, including Tank-binding kinase 1 (TBK1), as well as high expression of B cell lymphoma 2 (Bcl-2), correlated with low sensitivity to MEK inhibitors.

DISCUSSION

Taken together, this study shows that mutational status and signaling protein profiling might be used in further studies to predict drug sensitivities and identify resistance markers in MM.