← all datasets

UniProt

Emerging
2papers using it
2025first seen

UniProt is a comprehensive protein sequence and functional information database that contains a vast collection of protein sequences, including 79,000 terpene synthase sequences used to evaluate the performance of the TpsGPT model in generating functional enzyme candidates.

Papers using UniProt (2)

UniProt dataset β€” papers, benchmarks & downloads Β· AI for Science