I am new to these Bioinformatics and related machine learning like things. And I am beginning my project on protein classification using machine learning. What I do have is two fasta files of two classes of proteins. To do machine learning on it, I need to convert it into a .csv file having features. I have no idea where to start with. It would be a great support if anyone could help me load the AA indices from here: ftp.genome.jp/pub/db/community/aaindex/.
I am attaching the photo of my fasta file along with this here: ibb.co/CHNzvnH
And thanks in advance.