1022-scpFormer: Foundation Model for Single-Cell Proteomics

Paper Talk · May 24, 2026 · 20m

scpFormer is a transformer-based foundation model created to unify and interpret fragmented single-cell proteomics data across various technologies and experimental designs. To overcome the lack of universal reference panels, the model employs a continuous semantic tokenization strategy that maps proteins to a shared space using their amino acid sequences. This innovative architecture allows the system to handle an open vocabulary of proteins, enabling the integration of disparate datasets and the prediction of unmeasured markers through in silico imputation. By pre-training on over 390…