skip to main content


Title: Deep transfer learning of cancer drug responses by integrating bulk and single-cell RNA-seq data
Abstract

Drug screening data from massive bulk gene expression databases can be analyzed to determine the optimal clinical application of cancer drugs. The growing amount of single-cell RNA sequencing (scRNA-seq) data also provides insights into improving therapeutic effectiveness by helping to study the heterogeneity of drug responses for cancer cell subpopulations. Developing computational approaches to predict and interpret cancer drug response in single-cell data collected from clinical samples can be very useful. We propose scDEAL, a deep transfer learning framework for cancer drug response prediction at the single-cell level by integrating large-scale bulk cell-line data. The highlight in scDEAL involves harmonizing drug-related bulk RNA-seq data with scRNA-seq data and transferring the model trained on bulk RNA-seq data to predict drug responses in scRNA-seq. Another feature of scDEAL is the integrated gradient feature interpretation to infer the signature genes of drug resistance mechanisms. We benchmark scDEAL on six scRNA-seq datasets and demonstrate its model interpretability via three case studies focusing on drug response label prediction, gene signature identification, and pseudotime analysis. We believe that scDEAL could help study cell reprogramming, drug selection, and repurposing for improving therapeutic efficacy.

 
more » « less
Award ID(s):
1945971
NSF-PAR ID:
10377774
Author(s) / Creator(s):
; ; ; ; ; ; ;
Publisher / Repository:
Nature Publishing Group
Date Published:
Journal Name:
Nature Communications
Volume:
13
Issue:
1
ISSN:
2041-1723
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. One important characteristic of single-cell RNA sequencing (scRNA-seq) data is its high sparsity, where the gene-cell count data matrix contains high proportion of zeros. The sparsity has motivated widespread discussions on dropouts and missing data, as well as imputation algorithms of scRNA-seq analysis. Here, we aim to investigate whether there exist genes that are more prone to be under-detected in scRNA-seq, and if yes, what commonalities those genes may share. From public data sources, we gathered paired bulk RNA-seq and scRNA-seq data from 53 human samples, which were generated in diverse biological contexts. We derived pseudo-bulk gene expression by averaging the scRNA-seq data across cells. Comparisons of the paired bulk and pseudo-bulk gene expression profiles revealed that there indeed exists a collection of genes that are frequently under-detected in scRNA-seq compared to bulk RNA-seq. This result was robust to randomization when unpaired bulk and pseudo-bulk gene expression profiles were compared. We performed motif search to the last 350 bp of the identified genes, and observed an enrichment of poly(T) motif. The poly(T) motif toward the tails of those genes may be able to form hairpin structures with the poly(A) tails of their mRNA transcripts, making it difficult for their mRNA transcripts to be captured during scRNA-seq library preparation, which is a mechanistic conjecture of why certain genes may be more prone to be under-detected in scRNA-seq. 
    more » « less
  2. Abstract The transcriptional plasticity of cancer cells promotes intercellular heterogeneity in response to anticancer drugs and facilitates the generation of subpopulation surviving cells. Characterizing single-cell transcriptional heterogeneity after drug treatments can provide mechanistic insights into drug efficacy. Here, we used single-cell RNA-seq to examine transcriptomic profiles of cancer cells treated with paclitaxel, celecoxib and the combination of the two drugs. By normalizing the expression of endogenous genes to spike-in molecules, we found that cellular mRNA abundance shows dynamic regulation after drug treatment. Using a random forest model, we identified gene signatures classifying single cells into three states: transcriptional repression, amplification and control-like. Treatment with paclitaxel or celecoxib alone generally repressed gene transcription across single cells. Interestingly, the drug combination resulted in transcriptional amplification and hyperactivation of mitochondrial oxidative phosphorylation pathway linking to enhanced cell killing efficiency. Finally, we identified a regulatory module enriched with metabolism and inflammation-related genes activated in a subpopulation of paclitaxel-treated cells, the expression of which predicted paclitaxel efficacy across cancer cell lines and in vivo patient samples. Our study highlights the dynamic global transcriptional activity driving single-cell heterogeneity during drug response and emphasizes the importance of adding spike-in molecules to study gene expression regulation using single-cell RNA-seq. 
    more » « less
  3. Abstract

    While single cell RNA sequencing (scRNA-seq) is invaluable for studying cell populations, cell-surface proteins are often integral markers of cellular function and serve as primary targets for therapeutic intervention. Here we propose a transfer learning framework, single cell Transcriptome to Protein prediction with deep neural network (cTP-net), to impute surface protein abundances from scRNA-seq data by learning from existing single-cell multi-omic resources.

     
    more » « less
  4. Inferring gene regulatory networks (GRNs) from single-cell RNA-seq (scRNA-seq) data is an important computational question to find regulatory mechanisms involved in fundamental cellular processes. Although many computational methods have been designed to predict GRNs from scRNA-seq data, they usually have high false positive rates and none infer GRNs by directly using the paired datasets of case-versus-control experiments. Here we present a novel deep-learning-based method, named scTIGER, for GRN detection by using the co-differential relationships of gene expression profiles in paired scRNA-seq datasets. scTIGER employs cell-type-based pseudotiming, an attention-based convolutional neural network method and permutation-based significance testing for inferring GRNs among gene modules. As state-of-the-art applications, we first applied scTIGER to scRNA-seq datasets of prostate cancer cells, and successfully identified the dynamic regulatory networks of AR, ERG, PTEN and ATF3 for same-cell type between prostatic cancerous and normal conditions, and two-cell types within the prostatic cancerous environment. We then applied scTIGER to scRNA-seq data from neurons with and without fear memory and detected specific regulatory networks for BDNF, CREB1 and MAPK4. Additionally, scTIGER demonstrates robustness against high levels of dropout noise in scRNA-seq data.

     
    more » « less
  5. Abstract

    Spatial transcriptomics data play a crucial role in cancer research, providing a nuanced understanding of the spatial organization of gene expression within tumor tissues. Unraveling the spatial dynamics of gene expression can unveil key insights into tumor heterogeneity and aid in identifying potential therapeutic targets. However, in many large-scale cancer studies, spatial transcriptomics data are limited, with bulk RNA-seq and corresponding Whole Slide Image (WSI) data being more common (e.g. TCGA project). To address this gap, there is a critical need to develop methodologies that can estimate gene expression at near-cell (spot) level resolution from existing WSI and bulk RNA-seq data. This approach is essential for reanalyzing expansive cohort studies and uncovering novel biomarkers that have been overlooked in the initial assessments. In this study, we present STGAT (Spatial Transcriptomics Graph Attention Network), a novel approach leveraging Graph Attention Networks (GAT) to discern spatial dependencies among spots. Trained on spatial transcriptomics data, STGAT is designed to estimate gene expression profiles at spot-level resolution and predict whether each spot represents tumor or non-tumor tissue, especially in patient samples where only WSI and bulk RNA-seq data are available. Comprehensive tests on two breast cancer spatial transcriptomics datasets demonstrated that STGAT outperformed existing methods in accurately predicting gene expression. Further analyses using the TCGA breast cancer dataset revealed that gene expression estimated from tumor-only spots (predicted by STGAT) provides more accurate molecular signatures for breast cancer sub-type and tumor stage prediction, and also leading to improved patient survival and disease-free analysis. Availability: Code is available at https://github.com/compbiolabucf/STGAT.

     
    more » « less