1.Information summary file: The information file generated in the first step should first be normalized into a specific format, tab-separated txt file format.
2.Species file: The species folder (separated by tabs) containing the compilation summary file, species information should be placed in columns 8 and 9 respectively.So that species information can be added to the final extraction results.
3. fastaFile: contains cds or protein sequence files downloaded from NCBI and placed in the folder named 'fastaFile'
4. The generated results folder should be named 'results'