scDrugLink: Single-Cell Drug Repurposing for CNS Diseases via Computationally Linking Drug Targets and Perturbation Signatures.

in IEEE journal of biomedical and health informatics by Li Huang, Xu Lu, Dongsheng Chen

TLDR

  • scDrugLink is a computational method that improves drug repurposing for CNS diseases by integrating single-cell transcriptomic data with drug targets and perturbation signatures.
  • The method outperforms state-of-the-art methods in a systematic evaluation and has potential to improve personalized treatment strategies for CNS diseases.

Abstract

Central nervous system (CNS) diseases such as glioblastoma (GBM), multiple sclerosis (MS), and Alzheimer's disease (AD) remain challenging due to their complexity and limited treatments. Conventional drug repurposing strategies often rely on bulk RNA sequencing data, which can overlook cellular heterogeneity and mask rare but critical cell populations. Here, we introduce scDrugLink, a computational method that integrates single-cell transcriptomic data with drug targets and perturbation signatures to improve repurposing. For each cell type, scDrugLink constructs a Drug2Cell matrix based on drug targets to estimate promotion/inhibition scores and derives sensitivity/resistance scores by reverse matching signatures and disease-associated genes. These scores are then "linked," yielding robust therapeutic rankings. In our study, we present a systematic evaluation of single-cell drug repurposing methods for CNS diseases. Applied to atlas data for GBM, MS, and AD, scDrugLink surpassed three state-of-the-art methods (ASGARD, DrugReSC, and scDrugPrio), achieving area under the receiver operating characteristic curve (AUC) ranges of 0.6286-0.7242 and area under the precision-recall curve (AUPRC) ranges of 0.3412-0.5484. It also ranked top when comparing AUC and AUPRC at the level of individual cell types. Moreover, applying the "linking" principle to baseline methods boosted their performance, on average improving AUC and AUPRC by 0.0160 and 0.0244, respectively. Despite the advancements, the complexity and heterogeneity of CNS diseases, along with incomplete drug data, indicate that further improvement is necessary. We discuss these challenges and suggest directions for enhancing single-cell drug repurposing in the future.

Overview

  • The study introduces scDrugLink, a computational method that integrates single-cell transcriptomic data with drug targets and perturbation signatures to improve drug repurposing for central nervous system (CNS) diseases.
  • The method constructs a Drug2Cell matrix for each cell type, estimating promotion/inhibition scores and deriving sensitivity/resistance scores to yield robust therapeutic rankings.
  • The study evaluates scDrugLink's performance on atlas data for glioblastoma (GBM), multiple sclerosis (MS), and Alzheimer's disease (AD), outperforming state-of-the-art methods.

Comparative Analysis & Findings

  • scDrugLink achieved area under the receiver operating characteristic curve (AUC) ranges of 0.6286-0.7242 and area under the precision-recall curve (AUPRC) ranges of 0.3412-0.5484 in the evaluation.
  • When comparing AUC and AUPRC at the level of individual cell types, scDrugLink ranked top.
  • Applying the 'linking' principle to baseline methods boosted their performance, improving AUC and AUPRC by 0.0160 and 0.0244, respectively.

Implications and Future Directions

  • Despite advancements, the complexity and heterogeneity of CNS diseases, along with incomplete drug data, indicate that further improvement is necessary.
  • The study highlights the importance of considering single-cell data and incorporating the 'linking' principle to enhacing single-cell drug repurposing
  • Future directions include enhancing scDrugLink by incorporating more comprehensive drug data, improving the accuracy of promoter/inhibitor scores, and developing personalized treatment strategies.
Read Full Article