Single Cell Gene Expression Prediction via Prototype-based Proximal Neural Factorization

In the realm of single-cell analysis, accurately predicting gene expressions is crucial for understanding cellular functions and interactions. Traditional approaches often face significant challenges due to intrinsic noise, high dimensionality, and limited data availability in single-cell datasets. On the other hand, deep learning methods are prone to overfitting and perform poorly with limited data. This paper introduces a novel framework, Prototype-based Proximal Neural Factorization (PPNF), which harnesses the power of prototype learning and neural factorization to address these issues. Our method leverages a robust learning paradigm that identifies representative prototypes from single-cell data, facilitating a more resilient and interpretable data representations. We validate our approach using a diverse set of single-cell datasets, demonstrating that our method significantly outperforms existing techniques in terms of both robustness and accuracy. PPNF shows its effectiveness even with limited data, thereby reducing the financial and computational burden associated with high-throughput technologies. By enhancing the robustness and generalizability of single-cell gene expression predictions, our framework provides significant benefits for advancing the analysis and interpretation of single-cell gene expression data, particularly in data-limited scenarios, demonstrating its potential for more cost-effective applications.