Dataset Groups Activity Stream AMMA dataset The dataset used in the paper for protein representation learning, consisting of 120k sequence, structure, and function triplets. BibTex: @dataset{Seul_Lee_and_Minseon_Kim_and_Dongki_Kim_and_Eunji_Ko_and_Sung_Ju_Hwang_2024, abstract = {The dataset used in the paper for protein representation learning, consisting of 120k sequence, structure, and function triplets.}, author = {Seul Lee and Minseon Kim and Dongki Kim and Eunji Ko and Sung Ju Hwang}, doi = {10.57702/upr3eahh}, institution = {No Organization}, keyword = {'multi-modal representation learning', 'protein function', 'protein sequence', 'protein structure'}, month = {dec}, publisher = {TIB}, title = {AMMA dataset}, url = {https://service.tib.eu/ldmservice/dataset/amma-dataset}, year = {2024} }
