Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 67 of the 69 references it cites were found in a registry or an index.

Predicting heterogeneity in clone-specific therapeutic vulnerabilities using single-cell transcriptomic signatures

Open access

Published version of a preprint

Abstract

While understanding molecular heterogeneity across patients underpins precision oncology, there is increasing appreciation for taking intra-tumor heterogeneity into account. Based on large-scale analysis of cancer omics datasets, we highlight the importance of intra-tumor transcriptomic heterogeneity (ITTH) for predicting clinical outcomes. Leveraging single-cell RNA-seq (scRNA-seq) with a recommender system (CaDRReS-Sc), we show that heterogeneous gene-expression signatures can predict drug response with high accuracy (80%). Using patient-proximal cell lines, we established the validity of CaDRReS-Sc’s monotherapy (Pearson r >0.6) and combinatorial predictions targeting clone-specific vulnerabilities (>10% improvement). Applying CaDRReS-Sc to rapidly expanding scRNA-seq compendiums can serve as in silico screen to accelerate drug-repurposing studies. Availability: https://github.com/CSB5/CaDRReS-Sc .

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s13073-021-01000-y

Cites

67 of 67 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Impact of intra-patient transcriptomic heterogeneity on clinical outcomes. a Scatterplots showing the correlation between transcriptomic heterogeneity estimates based on in silico deconvolution (ITTH score) versus single-cell analysis derived values (scITTH score). b Survival analysis with ITTH clusters (Low/Medium/High) identified significant differences across various cancer types (FDR-corrected log-rank p value<0.05). c Plots depicting the overlap between clusters based on transcriptomic profiles (TC) and ITTH scores. P values are based on Fisher’s exact test and indicate that the clusters are distinct for most cancer types. d Comparison between ITTH scores of patients from different RECIST classes for Doxorubicin, Carboplatin, and Leucovorin highlighting significant differences (*FDR-corrected Wilcoxon p value<0.05)
Fig. 1 Impact of intra-patient transcriptomic heterogeneity on clinical outcomes. a Scatterplots showing the correlation between transcriptomic heterogeneity estimates based on in silico deconvolution (ITTH score) versus single-cell analysis derived values (scITTH score). b Survival analysis with ITTH clusters (Low/Medium/High) identified significant differences across various cancer types (FDR-corrected log-rank p value<0.05). c Plots depicting the overlap between clusters based on transcriptomic profiles (TC) and ITTH scores. P values are based on Fisher’s exact test and indicate that the clusters are distinct for most cancer types. d Comparison between ITTH scores of patients from different RECIST classes for Doxorubicin, Carboplatin, and Leucovorin highlighting significant differences (*FDR-corrected Wilcoxon p value<0.05)CC BY · PubMed Central
Fig. 2 CaDRReS-Sc accurately predicts drug response in unseen cell types. a Overview of single-cell RNA-seq workflow to preprocess sequencing data and provide inputs to CaDRReS-Sc (indicated by blue dashed lines). The normalized read count values and cell clustering results are utilized by CaDRReS-Sc for predicting drug response, taking into account transcriptomic heterogeneity within each patient. b Overview of CaDRReS-Sc workflow, where a pre-trained pharmacogenomic space based on drug response and gene expression profiles from cell-line experiments is used to provide cell- or cluster-specific drug response predictions. These are then combined to estimate overall drug response and prioritize drug combinations for a patient. c Comparison of prediction accuracy on unseen cell types between CaDRReS-Sc’s objective function and a naïve function that does not take uncertainty in IC50 values into account. Each dot represents a drug (n=226), and dot colors represent the percentage of sensitive cell lines. As can be seen here, CaDRReS-Sc’s objective function is particularly useful when the percentage of sensitive cell lines is low. d Comparison of median absolute error (MAE) obtained based on predictions using CaDRReS-Sc as well as a naïve objective function. CaDRReS-Sc’s robust objective function results in lower MAE across a majority of drugs (points above the y=x line), especially for drugs with a lower percentage of sensitive cell lines (lighter shades). e Histograms showing the average prediction accuracy (error bars show 1 standard deviation) using different drug response prediction approaches. f Histograms showing MAE (error bars show 1 standard deviation) with different drug response prediction approaches. Overall, CaDRReS-Sc was seen to have high accuracy on the sensitive/non-sensitive classification task while reporting the lowest MAE for the IC50 regression task
Fig. 2 CaDRReS-Sc accurately predicts drug response in unseen cell types. a Overview of single-cell RNA-seq workflow to preprocess sequencing data and provide inputs to CaDRReS-Sc (indicated by blue dashed lines). The normalized read count values and cell clustering results are utilized by CaDRReS-Sc for predicting drug response, taking into account transcriptomic heterogeneity within each patient. b Overview of CaDRReS-Sc workflow, where a pre-trained pharmacogenomic space based on drug response and gene expression profiles from cell-line experiments is used to provide cell- or cluster-specific drug response predictions. These are then combined to estimate overall drug response and prioritize drug combinations for a patient. c Comparison of prediction accuracy on unseen cell types between CaDRReS-Sc’s objective function and a naïve function that does not take uncertainty in IC50 values into account. Each dot represents a drug (n=226), and dot colors represent the percentage of sensitive cell lines. As can be seen here, CaDRReS-Sc’s objective function is particularly useful when the percentage of sensitive cell lines is low. d Comparison of median absolute error (MAE) obtained based on predictions using CaDRReS-Sc as well as a naïve objective function. CaDRReS-Sc’s robust objective function results in lower MAE across a majority of drugs (points above the y=x line), especially for drugs with a lower percentage of sensitive cell lines (lighter shades). e Histograms showing the average prediction accuracy (error bars show 1 standard deviation) using different drug response prediction approaches. f Histograms showing MAE (error bars show 1 standard deviation) with different drug response prediction approaches. Overall, CaDRReS-Sc was seen to have high accuracy on the sensitive/non-sensitive classification task while reporting the lowest MAE for the IC50 regression taskCC BY · PubMed Central
Fig. 3 Calibrated drug response prediction in heterogenous patient-derived cell lines using scRNA-seq data. a PCA plot showing the diversity of single-cell transcriptomic profiles from different patient-derived cell lines. Comparison of observed and predicted cell death percentages for 5 patient-derived cell lines using 8 different drugs (at lower concentrations), based on CaDRReS-Sc analysis at the b cell-level, c cluster-level, and d patient-level. Error bars show 1 standard deviation based on 3 experimental replicates. Note that that cell and cluster-level predictions show a greater correlation with experimental observations than patient-level predictions, highlighting the utility of scRNA-seq data. e–f PCA plots showing varied cell-level response predictions to treatment with Epothilone B and Doxorubicin, highlighting substantial inter- and intra-patient drug response heterogeneity
Fig. 3 Calibrated drug response prediction in heterogenous patient-derived cell lines using scRNA-seq data. a PCA plot showing the diversity of single-cell transcriptomic profiles from different patient-derived cell lines. Comparison of observed and predicted cell death percentages for 5 patient-derived cell lines using 8 different drugs (at lower concentrations), based on CaDRReS-Sc analysis at the b cell-level, c cluster-level, and d patient-level. Error bars show 1 standard deviation based on 3 experimental replicates. Note that that cell and cluster-level predictions show a greater correlation with experimental observations than patient-level predictions, highlighting the utility of scRNA-seq data. e–f PCA plots showing varied cell-level response predictions to treatment with Epothilone B and Doxorubicin, highlighting substantial inter- and intra-patient drug response heterogeneityCC BY · PubMed Central
Fig. 4 Prioritizing drug combinations targeting transcriptionally-distinct subclones with CaDRReS-Sc. a Proportions of various transcriptionally distinct cell clusters (n=21) in head and neck cancer patient-derived cell lines. b Heatmap of predicted cell death percentages across cell clusters within each patient. c Comparison between predicted and observed drug response for five different drug combinations and patient-derived cells. Boxplots contrasting monotherapy (gray) and combinatorial therapy (orange) response based on d CaDRReS-Sc predictions and e experimental measurements. Error bars show 1 standard deviation (n=2–3), dashed lines indicate the best monotherapy, and asterisk symbols indicate drug combinations that show improvement. In general, relative response values for monotherapy and combinatorial therapy, as observed from experimental measurements, were also reflected in CaDRReS-Sc predictions. f Boxplots showing that drug combinations that were observed to improve over monotherapy (x-axis, no/low vs high determined based on median value in experiment) had significantly higher predicted improvements (combination over monotherapy) using CaDRReS-Sc as well (y-axis)
Fig. 4 Prioritizing drug combinations targeting transcriptionally-distinct subclones with CaDRReS-Sc. a Proportions of various transcriptionally distinct cell clusters (n=21) in head and neck cancer patient-derived cell lines. b Heatmap of predicted cell death percentages across cell clusters within each patient. c Comparison between predicted and observed drug response for five different drug combinations and patient-derived cells. Boxplots contrasting monotherapy (gray) and combinatorial therapy (orange) response based on d CaDRReS-Sc predictions and e experimental measurements. Error bars show 1 standard deviation (n=2–3), dashed lines indicate the best monotherapy, and asterisk symbols indicate drug combinations that show improvement. In general, relative response values for monotherapy and combinatorial therapy, as observed from experimental measurements, were also reflected in CaDRReS-Sc predictions. f Boxplots showing that drug combinations that were observed to improve over monotherapy (x-axis, no/low vs high determined based on median value in experiment) had significantly higher predicted improvements (combination over monotherapy) using CaDRReS-Sc as well (y-axis)CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 69 references

Cited by

See all 66

Metadata

Authors
Suphavilai, C., Chia, S., Sharma, A., Tu, L., Da Silva, R. P., Mongia, A., DasGupta, R., & Nagarajan, N.
Affiliations
Agency for Science, Technology and Research (SG)
Corresponding author
  • DasGupta, Ramanuj
  • Nagarajan, Niranjan
Venue
Genome Medicine
Published
2021-12
Volume
13
Issue
1
Pages
189-189
ISSN
1756-994X (ISSN-L)
OpenAlex
W4225886114
Cited by
58
References
69
Citations by year
2026: 8 · 2025: 13 · 2024: 21 · 2023: 8 · 2022: 6 · 2021: 2
FWCI
3.61
Type
journal article
Language
en
Open access
Licence
Locations
  • Genome Medicine (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • National University of Singapore (submittedVersion, cc-by)
  • cIRcle (University of British Columbia) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Genome Institute of Singapore
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Cancer Genomics and Diagnostics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
Keywords
intratumoral heterogeneity, drug response prediction, single-cell transcriptomics, recommender systems, precision oncology, drug repurposing
MeSH terms
Clone Cells, Humans, Neoplasms, Software, Sequence Analysis, RNA, Gene Expression Profiling, Precision Medicine, Single-Cell Analysis, Transcriptome

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Predicting heterogeneity in clone-specific therapeutic vulnerabilities using single-cell transcriptomic signatures. https://app.cochat.ai/papers/10.1186/s13073-021-01000-y
The paper
Suphavilai, C., Chia, S., Sharma, A., Tu, L., Da Silva, R. P., Mongia, A., DasGupta, R., & Nagarajan, N. (2021). Predicting heterogeneity in clone-specific therapeutic vulnerabilities using single-cell transcriptomic signatures. Genome Medicine. https://doi.org/10.1186/s13073-021-01000-y

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.