scpFormer

How it works

Where it comes from

Other

Highlighted claims

• The architecture has 21 million parameters, 12 transformer encoder blocks, hidden dimension 512, and 8 attention heads. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
• Each protein token combines an ESM-derived semantic identity embedding with a continuous expression-value embedding. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
• scpFormer replaces index-based protein tokens with continuous sequence-anchored protein identity embeddings and continuous expression-value embeddings. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
• scpFormer uses a learnable classification token and a transformer encoder to produce contextualized protein embeddings plus a global cell embedding. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
• The model uses ESM-derived protein embeddings to position proteins by structural and functional similarity, enabling unseen proteins to be incorporated without retraining a discrete vocabulary. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
• scpFormer is introduced as a foundation model for single-cell proteomics where no comparable foundation model had been established. — scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics