Transcriptomic Models for Immunotherapy Response Prediction Show Limited Cross-cohort Generalisability
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910132446691328 |
|---|---|
| author | Liang, Yuheng Chhuo, Lucy Argha, Ahmadreza Farbehi, Nona Chen, Lu Alizadehsani, Roohallah Hosseinzadeh, Mehdi Beheshti, Amin Porntaveetusm, Thantrira Ye, Youqiong Alinejad-Rokny, Hamid |
| author_facet | Liang, Yuheng Chhuo, Lucy Argha, Ahmadreza Farbehi, Nona Chen, Lu Alizadehsani, Roohallah Hosseinzadeh, Mehdi Beheshti, Amin Porntaveetusm, Thantrira Ye, Youqiong Alinejad-Rokny, Hamid |
| contents | Immune checkpoint inhibitors (ICIs) have transformed cancer therapy; yet substantial proportion of patients exhibit intrinsic or acquired resistance, making accurate pre-treatment response prediction a critical unmet need. Transcriptomics-based biomarkers derived from bulk and single-cell RNA sequencing (scRNA-seq) offer a promising avenue for capturing tumour-immune interactions, yet the cross-cohort generalisability of existing prediction models remains unclear.We systematically benchmark nine state-of-the-art transcriptomic ICI response predictors, five bulk RNA-seq-based models (COMPASS, IRNet, NetBio, IKCScore, and TNBC-ICI) and four scRNA-seq-based models (PRECISE, DeepGeneX, Tres and scCURE), using publicly available independent datasets unseen during model development. Overall, predictive performance was modest: bulk RNA-seq models performed at or near chance level across most cohorts, while scRNA-seq models showed only marginal improvements. Pathway-level analyses revealed sparse and inconsistent biomarker signals across models. Although scRNA-seq-based predictors converged on immune-related programs such as allograft rejection, bulk RNA-seq-based models exhibited little reproducible overlap. PRECISE and NetBio identified the most coherent immune-related themes, whereas IRNet predominantly captured metabolic pathways weakly aligned with ICI biology. Together, these findings demonstrate the limited cross-cohort robustness and biological consistency of current transcriptomic ICI prediction models, underscoring the need for improved domain adaptation, standardised preprocessing, and biologically grounded model design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05478 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Transcriptomic Models for Immunotherapy Response Prediction Show Limited Cross-cohort Generalisability Liang, Yuheng Chhuo, Lucy Argha, Ahmadreza Farbehi, Nona Chen, Lu Alizadehsani, Roohallah Hosseinzadeh, Mehdi Beheshti, Amin Porntaveetusm, Thantrira Ye, Youqiong Alinejad-Rokny, Hamid Genomics Machine Learning Immune checkpoint inhibitors (ICIs) have transformed cancer therapy; yet substantial proportion of patients exhibit intrinsic or acquired resistance, making accurate pre-treatment response prediction a critical unmet need. Transcriptomics-based biomarkers derived from bulk and single-cell RNA sequencing (scRNA-seq) offer a promising avenue for capturing tumour-immune interactions, yet the cross-cohort generalisability of existing prediction models remains unclear.We systematically benchmark nine state-of-the-art transcriptomic ICI response predictors, five bulk RNA-seq-based models (COMPASS, IRNet, NetBio, IKCScore, and TNBC-ICI) and four scRNA-seq-based models (PRECISE, DeepGeneX, Tres and scCURE), using publicly available independent datasets unseen during model development. Overall, predictive performance was modest: bulk RNA-seq models performed at or near chance level across most cohorts, while scRNA-seq models showed only marginal improvements. Pathway-level analyses revealed sparse and inconsistent biomarker signals across models. Although scRNA-seq-based predictors converged on immune-related programs such as allograft rejection, bulk RNA-seq-based models exhibited little reproducible overlap. PRECISE and NetBio identified the most coherent immune-related themes, whereas IRNet predominantly captured metabolic pathways weakly aligned with ICI biology. Together, these findings demonstrate the limited cross-cohort robustness and biological consistency of current transcriptomic ICI prediction models, underscoring the need for improved domain adaptation, standardised preprocessing, and biologically grounded model design. |
| title | Transcriptomic Models for Immunotherapy Response Prediction Show Limited Cross-cohort Generalisability |
| topic | Genomics Machine Learning |
| url | https://arxiv.org/abs/2604.05478 |