pLM-BLAST: distant homology detection based on direct comparison of sequence representations from protein language models.
Kamil KaminskiJan LudwiczakKamil PawlickiVikram AlvaStanislaw Dunin-HorkawiczPublished in: Bioinform. (2023)
Keyphrases
- language model
- sequence alignment
- language modeling
- sequence analysis
- n gram
- document retrieval
- protein sequences
- word clouds
- information retrieval
- retrieval model
- statistical language models
- probabilistic model
- pairwise
- query expansion
- amino acids
- test collection
- speech recognition
- language modelling
- context sensitive
- vector space model
- smoothing methods
- relevance model
- language models for information retrieval
- document ranking
- amino acid sequences
- language model for information retrieval
- protein structure prediction
- sequence data
- retrieval effectiveness
- query terms
- information retrieval systems
- protein function
- translation model
- binding sites
- query specific
- secondary structure
- cross language information retrieval
- ad hoc information retrieval