Single-cell profiling resolves gain- and loss-of-function mechanisms in CASR to advance mechanism-aware variant classification
- 1Labcorp
Abstract
Multiplexed assays of variant effect (MAVEs) and computational methods have advanced variant classification but have struggled to distinguish the molecular mechanism of variants with sufficient accuracy, limiting utility for multi-mechanism genes. Here, we coupled single-cell RNA-seq profiling with supervised machine learning to predict the mechanism of variants in CASR, a gene in which gain of function (GOF) variants cause hypocalcemia and loss of function (LOF) variants cause hypercalcemia. We engineered endogenous CASR-depleted HEK293 cells to express a single exogenous variant copy, measured their transcriptional profiles at single-cell resolution, trained a multi-class machine learning model on 96 expert-annotated variants (25 benign, 35 LOF, 36 GOF), and predicted mechanism for 157 variants of uncertain significance, of which 16 were predicted GOF and 54 LOF. The model showed high performance (macro F1 0.98, overall accuracy 0.98), and its predictions were corroborated by clinical phenotype and serum calcium measurements across more than 300,000 patients in a commercial genetic testing database. These results highlight the effectiveness of using molecular mechanism annotations with scRNA-seq to train models that distinguish molecular mechanisms of pathogenicity. The approach has immediate relevance for clinical variant classification and establishes a foundation for mechanism-guided clinical management in disorders with mechanism-dependent interventions, with potential application to other multi-mechanism genes.
Related
- Scalable methylome-transcriptome profiling resolves clonal organization in human hematopoiesis
- A DNA-barcoded Luria-Delbrück assay resolves mechanisms of adaptation
- Response mechanism of Sepia esculenta larvae under global warming, ocean acidification and salinity fluctuation: Integrated biochemical and transcriptome profiling
- Longitudinal single-cell transcriptional profiling identifies dynamic neurodegenerative mechanisms in Christianson Syndrome rat
- Molecular and functional profiling distinguishes PACS1 syndrome variant from PACS1 loss-of-function in iNeurons
BibTeX
@misc{padigepati2026singlecell,
title = {{Single-cell profiling resolves gain- and loss-of-function mechanisms in CASR to advance mechanism-aware variant classification}},
author = {S. R. Padigepati and D. Stafford and Y. Kobayashi and C. A. Tan and J. Kim and Y. Jiang and K. Ouyang and J. Reuter and A. M. B. Lacoste},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.26.754690},
url = {https://www.biorxiv.org/content/10.64898/2026.09.26.754690v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Single-cell profiling resolves gain- and loss-of-function mechanisms in CASR to advance mechanism-aware variant classification
AU - S. R. Padigepati
AU - D. Stafford
AU - Y. Kobayashi
AU - C. A. Tan
AU - J. Kim
AU - Y. Jiang
AU - K. Ouyang
AU - J. Reuter
AU - A. M. B. Lacoste
PY - 2026
DA - 2026/09/26
PB - bioRxiv
DO - 10.64898/2026.09.26.754690
UR - https://www.biorxiv.org/content/10.64898/2026.09.26.754690v1
AB - Multiplexed assays of variant effect (MAVEs) and computational methods have advanced variant classification but have struggled to distinguish the molecular mechanism of variants with sufficient accuracy, limiting utility for multi-mechanism genes. Here, we coupled single-cell RNA-seq profiling with supervised machine learning to predict the mechanism of variants in CASR, a gene in which gain of function (GOF) variants cause hypocalcemia and loss of function (LOF) variants cause hypercalcemia. We engineered endogenous CASR-depleted HEK293 cells to express a single exogenous variant copy, measured their transcriptional profiles at single-cell resolution, trained a multi-class machine learning model on 96 expert-annotated variants (25 benign, 35 LOF, 36 GOF), and predicted mechanism for 157 variants of uncertain significance, of which 16 were predicted GOF and 54 LOF. The model showed high performance (macro F1 0.98, overall accuracy 0.98), and its predictions were corroborated by clinical phenotype and serum calcium measurements across more than 300,000 patients in a commercial genetic testing database. These results highlight the effectiveness of using molecular mechanism annotations with scRNA-seq to train models that distinguish molecular mechanisms of pathogenicity. The approach has immediate relevance for clinical variant classification and establishes a foundation for mechanism-guided clinical management in disorders with mechanism-dependent interventions, with potential application to other multi-mechanism genes.
ER -