diff --git a/data/data_processing.py b/data/data_processing.py index a8a1202f2d635a5cc41882c90bfff5c2dcb9f060..a40b2d98e5fbe3017354d1b3576cc142025990da 100644 --- a/data/data_processing.py +++ b/data/data_processing.py @@ -2,7 +2,34 @@ import matplotlib.pyplot as plt import numpy as np import pandas as pd # from loess.loess_1d import loess_1d -from constant import ALPHABET_UNMOD_REV + +ALPHABET_UNMOD = { + "": 0, + "A": 1, + "C": 2, + "D": 3, + "E": 4, + "F": 5, + "G": 6, + "H": 7, + "I": 8, + "K": 9, + "L": 10, + "M": 11, + "N": 12, + "P": 13, + "Q": 14, + "R": 15, + "S": 16, + "T": 17, + "V": 18, + "W": 19, + "Y": 20, + "OxM": 21, + "CaC": 22 +} + +ALPHABET_UNMOD_REV = {v: k for k, v in ALPHABET_UNMOD.items()} # def align(dataset, reference, column_dataset, column_ref, seq_data, seq_ref):