Recent Major Transcriptomics and Epitranscriptomics Contributions toward Personalized and Precision Medicine

Molecular profiling and therapeutic tailoring to address disease heterogeneity in systemic lupus erythematosus

Systemic lupus erythematosus (SLE) is a chronic, heterogeneous, systemic autoimmune disease characterized by autoantibody production, complement activation, and immune complex deposition. SLE predominantly affects young, middle-aged, and child-bearing women with episodes of flare-up and remission, although it affects males at a much lower frequency (female: male; 7:1 to 15:1). Technological and molecular advancements have helped in patient stratification and improved patient prognosis, morbidity, and treatment regimens overall, impacting quality of life. Despite several attempts to comprehend the pathogenesis of SLE, knowledge about the precise molecular mechanisms underlying this disease is still lacking. The current treatment options for SLE are pragmatic and aim to develop composite biomarkers for daily practice, which necessitates the robust development of novel treatment strategies and drugs targeting specific responsive pathways. In this communication, we review and aim to explore emerging therapeutic modalities, including multiomics-based approaches, rational drug design, and CAR-T-cell-based immunotherapy, for the management of SLE.

Therapeutic biomarkers in acute myeloid leukemia: functional and genomic approaches

Acute myeloid leukemia (AML) is clinically and genetically a heterogeneous disease characterized by clonal expansion of abnormal hematopoietic progenitors. Genomic approaches to precision medicine have been implemented to direct targeted therapy for subgroups of AML patients, for instance, IDH inhibitors for IDH1/2 mutated patients, and FLT3 inhibitors with FLT3 mutated patients. While next generation sequencing for genetic mutations has improved treatment outcomes, only a fraction of AML patients benefit due to the low prevalence of actionable targets. In recent years, the adoption of newer functional technologies for quantitative phenotypic analysis and patient-derived avatar models has strengthened the potential for generalized functional precision medicine approach. However, functional approach requires robust standardization for multiple variables such as functional parameters, time of drug exposure and drug concentration for making in vitro predictions. In this review, we first summarize genomic and functional therapeutic biomarkers adopted for AML therapy, followed by challenges associated with these approaches, and finally, the future strategies to enhance the implementation of precision medicine.

Interpretable deep learning for improving cancer patient survival based on personal transcriptomes

Precision medicine chooses the optimal drug for a patient by considering individual differences. With the tremendous amount of data accumulated for cancers, we develop an interpretable neural network to predict cancer patient survival based on drug prescriptions and personal transcriptomes (CancerIDP). The deep learning model achieves 96% classification accuracy in distinguishing short-lived from long-lived patients. The Pearson correlation between predicted and actual months-to-death values is as high as 0.937. About 27.4% of patients may survive longer with an alternative medicine chosen by our deep learning model. The median survival time of all patients can increase by 3.9 months. Our interpretable neural network model reveals the most discriminating pathways in the decision-making process, which will further facilitate mechanistic studies of drug development for cancers.