A Premalignant Cell-Based Model for Functionalization and Classification of PTEN Variants

Area of Science:

• Oncology
• Genetics
• Biotechnology

Background:

• Accurate classification of genetic variants in disease-associated genes like PTEN is crucial for patient management.
• Many PTEN variants lack clear benign or pathogenic classifications, hindering clinical decision-making.
• PTEN hamartoma tumor syndrome is linked to PTEN mutations, but recent variants require functional assessment.

Purpose of the Study:

• To develop and validate a novel cell-based assay for functional characterization of PTEN variants.
• To utilize machine learning to classify the pathogenicity of PTEN missense variants based on functional data.
• To improve the annotation of clinical significance for PTEN variants, particularly those of uncertain significance.

Main Methods:

• A cell-based assay using PTEN-null mammary epithelial cells to assess spheroid formation rescue by PTEN variants.
• Functional assessment of 47 PTEN missense variants, with a focus on those lacking clear ClinVar classifications.
• Application of a machine learning model trained on functional scores and genotypic data for variant classification.

Main Results:

• The assay successfully functionalized 47 missense PTEN variants, classifying many previously uncharacterized ones.
• The machine learning model achieved high accuracy in predicting variant pathogenicity based on functional data.
• Reduced protein stability was identified as a potential mechanism for pathogenicity in certain PTEN variants.
• The developed assay demonstrated superior performance, scalability, and speed compared to computational prediction methods.

Conclusions:

• The combined 3D tumor spheroid modeling and machine learning approach effectively classifies PTEN missense variants.
• This assay provides a robust and scalable alternative for annotating the clinical significance of cancer-associated PTEN variants.
• The findings will aid in distinguishing benign from pathogenic PTEN variants, facilitating appropriate patient care and surveillance.