The sequences of raw data that include model training dataset and validated testing dataset are all provided in here, 
and the sequences files are presented in FASTA format.


These train set are named as below:
Train-Promoter.fasta: The dataset listed the promoter sequence of train genes, 
the length is 1503 bps of each target gene because we retrived promoter from the start coden of ATG.
Train-Middle.fasta: The dataset listed the sequence of central region between target gene and T-DNA inserted site, the length is 301 bps of each target gene because we retrived
Middle from the up- and downstream 150 bps of center point. Sometimes, the length will be shorter than 301 if the center point is very close the genome terminal.


The test set are named as below:
Test-Promoter.fasta
Test-Middle.fasta

The testing dataset are aplied to validate individual model accuracy.