Usage:
DeepDetect.exe --input=input_path --output=output_path --regular=">(.*?)\s" --protease=Trypsin --missed_cleavages=2 --min_len=7 --max_len=47

Note:
1.The script is written under Python 3.6
2.The trypsin digestion scripts shared here do not follow the proline rule, which means that even if they are followed by proline (P), it will still cleave after lysine (K) or arginine (R).
3.The program outputs like this:
Protein id	Peptide sequence	Peptide detectability
sp|Q00604|NDP_HUMAN	MRKHVLAASFSMLSLLVIMGDTDSK	0.001457512395316663
The last column is the list of predicted peptide detectabilities.

How to use:
1.Open a command terminal and cd to this folder;
2.Input command: DeepDetect.exe --input=input_path --output=output_path --regular=">(.*?)\s" --protease=Trypsin --missed_cleavages=2 --min_len=7 --max_len=47

Seven arguments are:
--input: the path of protein sequence file in FASTA format (.fasta)
--output: the path of output file in TXT format (.txt)
--regular: the regular expression used to extract the protein id, default: ">(.*?)\s"
--protease: the digestion protease, default: Trypsin
--missed_cleavages:the maximum number of missed cleavages allowed in each theoretical peptide fragment, default: 2
--min_len: the minimum length of the theoretical peptide fragment, default: 7
--max_len: the maximum length of the theoretical peptide fragment, default: 47