PDB Plus LLM Contact Map embedding for ML classification research work
We propose a novel method for designing numerical embeddings in Euclidean space for proteins by leveraging 3D structure information, specifically employing the concept of contact maps. These embeddings are synergistically combined with features extracted from LLMs and traditional feature engineering techniques to enhance the performance of embeddings in supervised protein analysis. Experimental results on benchmark datasets, including PDB Bind and STCRDAB, demonstrate the superior performance of the proposed method for protein function prediction.
File Spike2Vec_PDB_Bind_3792_seq_k_3 is large so we are providing a raw data file with code to generate the embeddings.