TABLE III.

Description of Formats and Contents of the iDASH24 Dataset Files

File Name	Format	Description
Example Sequences (example_AA_sequences.txt)	Space delimited file. Class	Protein sequences for evaluation and challenge
Dashformer.keras	Keras model file	Protein classification model
Dashformer_model_parameters	Text-formatted Parameters	Directory contains the parameters of classification model
DASHformer_Challenge.py	Python code for the model	The Python code for exploring and evaluating model
dashformer_tokenizer.json	Json file	Tokenizer file for processing input sequences
PFAM_training_sequences.txt	Space delimited text file	1.2m protein sequence database
DASHformer.requirements	Python requirements list	The list of requirements to run the classification model