Functional annotation of enzyme-encoding genes using deep learning with transformer layers

Supplementary datasets for the paper "Improved annotation of enzyme-encoding genes using deep learning with transformer layers".

The datasets include Supplementary Data 1 (Predicted EC numbers for protein sequences from Swiss-Prot database using DeepECtransformer), Supplementary Data 2 (Visualization of the latent representations of enzyme sequences in the Swiss-Prot database using TMAP), Supplementary Data 3 (Commonly highlighted motifs for each EC number using DeepEC v2 neural network), Supplementary Data 4 (Sequences for each of strain specific alleles), Supplementary Data 5 (EC number prediction results for the y-ome proteins), Supplementary Data 6 (EC numbers of 128,100,490 protein sequences in 70,600 genomes in NCBI), and Supplementary Data 7 (Solubility prediction results for 295 y-ome proteins).