ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training.
Le ZhuoZewen ChiMinghao XuHeyan HuangJianan ZhaoHeqi ZhengConghui HeXian-Ling MaoWentao ZhangPublished in: ACL (1) (2024)
Keyphrases
- protein structure
- amino acids
- protein sequences
- protein structure prediction
- tandem mass spectra
- subcellular localization
- protein protein interactions
- protein interaction data
- training set
- programming language
- sequence alignment
- mass spectrometry
- drug design
- linguistic knowledge
- molecular structures
- mass spectra
- amino acid sequences
- protein function
- neural network
- co occurrence
- natural language