FRANK: a pan-cancer RNA-seq classifier for childhood tumors with data-efficient learning
- 1Vilnius University Hospital Santaros Klinikos
Abstract
Accurate characterization of tumor subtype is of paramount importance in guiding treatment decisions in pediatric cancers. Here, we present FRANK (Fully-connected RNA-based Augmentation Neural Klassifier), a machine learning approach for classifying pan-cancer pediatric tumors. We curated a set of 11,467 transcriptomes to build a high-quality training dataset representing 181 distinct childhood tumor and normal tissue types. We used extensive data augmentation techniques with a hierarchical penalty term to train a neural network capable of detecting tumor types with as few as three training examples. To evaluate the generalization of the trained model, we perform validation on nine datasets spanning 16,398 samples, achieving an overall accuracy of 98.3%. Furthermore, we demonstrated that FRANK outperformed other published pediatric pan-cancer RNA-seq classifiers on an external dataset. To evaluate the robustness, we showed that FRANK remained accurate when applied to long-read RNA-sequencing data, as well as to noisy and low-quality data.
Related
- Stage-Stratified Explainable Machine Learning Identifies a Reproducible Transcriptomic Classifier with Stage-Dependent Feature Importance in Colorectal Cancer: A Multi-Cohort Study with Saudi Population Contextualisation
- Transcriptomic Profiling and Demographic Analysis of Appalachian Patients with Pancreatic Ductal Adenocarcinoma using the Purity Independent Subtyping of Tumors (PurIST) Classifier
- A machine learning classifier reveals hidden rare biallelic heterozygous variants in the coding regions of Meniere disease genome
- Deep learning-based classifier for malignant plasma cell identification in myeloma
- Rigorous nested cross-validation and external generalization-gap analysis of a machine-learning classifier for U-251 glioblastoma cytotoxicity
BibTeX
@misc{sablauskas2026frank,
title = {{FRANK: a pan-cancer RNA-seq classifier for childhood tumors with data-efficient learning}},
author = {K. Sablauskas and T. Kiselova and L. Bardina and I. Nartisa and A. Zucenka and A. Viluma and L. Gailite and A. Jakaitiene and D. Rots},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.23.26355605},
url = {https://www.medrxiv.org/content/10.64898/2026.09.23.26355605v2},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - FRANK: a pan-cancer RNA-seq classifier for childhood tumors with data-efficient learning
AU - K. Sablauskas
AU - T. Kiselova
AU - L. Bardina
AU - I. Nartisa
AU - A. Zucenka
AU - A. Viluma
AU - L. Gailite
AU - A. Jakaitiene
AU - D. Rots
PY - 2026
DA - 2026/09/23
PB - medRxiv
DO - 10.64898/2026.09.23.26355605
UR - https://www.medrxiv.org/content/10.64898/2026.09.23.26355605v2
AB - Accurate characterization of tumor subtype is of paramount importance in guiding treatment decisions in pediatric cancers. Here, we present FRANK (Fully-connected RNA-based Augmentation Neural Klassifier), a machine learning approach for classifying pan-cancer pediatric tumors. We curated a set of 11,467 transcriptomes to build a high-quality training dataset representing 181 distinct childhood tumor and normal tissue types. We used extensive data augmentation techniques with a hierarchical penalty term to train a neural network capable of detecting tumor types with as few as three training examples. To evaluate the generalization of the trained model, we perform validation on nine datasets spanning 16,398 samples, achieving an overall accuracy of 98.3%. Furthermore, we demonstrated that FRANK outperformed other published pediatric pan-cancer RNA-seq classifiers on an external dataset. To evaluate the robustness, we showed that FRANK remained accurate when applied to long-read RNA-sequencing data, as well as to noisy and low-quality data.
ER -