Bacillus Unannotated Protvec Model

Protvec model  trained using 425,000 sequences from the Genome Taxonomy Database (GTDB). Sequences were dereplicated at 70% using CDHIT and filtered to remove sequences containing 'X', sequences shorter than 30 amino acids and sequences longer than 1024 amino acids. 

Training used a vector size of 100 and a context size of 25 to produce a dictionary object containing a 100-dimensional vector for each 3-mer present in the training data. 

Model is stored as a .pkl file which can be imported using the Python pickle module.