pytoda.proteins.processing module

Amino Acid sequence processing utilities.

Summary

Reference

REAL_AAS = ['A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'Y']

Polarity, Charge, Hydophobicity, Aromaticity, Ionizability, StartStop Nonpolar = -1, Polar = 1 Negative = -1, Neutral = 0, Positive = 1 Hydrophobic = -1, Hydrophilic = 1 NonAromatic = -1, Aromatic = 1 NonIonizable = -1, Ionizable = 1 Stop = -1, Start = 1, Neither = 0

AA_PROPERTIES_NUM = {'-': (0, 0, 0, 0, 0, 0.5), '<PAD>': (0, 0, 0, 0, 0, 0), '<START>': (0, 0, 0, 0, 0, 1), '<STOP>': (0, 0, 0, 0, 0, -1), '<UNK>': (0, 0, 0, 0, 0, 0), 'A': (-1, 0, -1, -1, -1, 0), 'B': (1, -0.5, 1, -1, 0, 0), 'C': (1, 0, 1, -1, 1, 0), 'D': (1, -1, 1, -1, 1, 0), 'E': (1, -1, 1, -1, 1, 0), 'F': (-1, 0, -1, 1, -1, 0), 'G': (-1, 0, -1, -1, -1, 0), 'H': (1, 1, 1, -1, 1, 0), 'I': (-1, 0, -1, -1, -1, 0), 'K': (1, 1, 1, -1, 1, 0), 'L': (-1, 0, -1, -1, -1, 0), 'M': (-1, 0, -1, -1, -1, 0), 'N': (1, 0, 1, -1, -1, 0), 'O': (1, 0, 1, 1, 1, 0), 'P': (-1, 0, -1, -1, -1, 0), 'Q': (1, 0, 1, -1, -1, 0), 'R': (1, 1, 1, -1, 1, 0), 'S': (1, 0, 1, -1, -1, 0), 'T': (1, 0, 1, -1, -1, 0), 'U': (-1, 0, -1, -1, 1, 0), 'V': (-1, 0, -1, -1, -1, 0), 'W': (-1, 0, -1, 1, -1, 0), 'X': (0.2, 0, 0.1, -0.7, -0.2, 0), 'Y': (1, 0, -1, 1, 1, 0), 'Z': (1, -0.5, 1, -1, 0, 0)}

Molecular Weight, Residue Weight, pKa, pKb, pKx, pI, Hydrophobicity at pH2 Taken from: https://www.sigmaaldrich.com/life-science/metabolomics/learning-center/amino-acid-reference-chart.html

AA_FEAT = {'-': (0, 0, 0, 0, 0, 0, 0, 0.5), '<PAD>': (0, 0, 0, 0, 0, 0, 0, 0), '<START>': (0, 0, 0, 0, 0, 0, 0, 1), '<STOP>': (0, 0, 0, 0, 0, 0, 0, -1), '<UNK>': (0, 0, 0, 0, 0, 0, 0, 0), 'A': (89.1, 71.08, 2.34, 9.69, 0, 6, 47, 0), 'B': (132.615, 114.6, 1.95, 9.2, 1.825, 4.09, -29.5, 0), 'C': (121.16, 103.15, 1.96, 10.28, 8.18, 5.07, 52, 0), 'D': (133.11, 115.09, 1.88, 9.6, 3.65, 2.77, -18, 0), 'E': (147.13, 129.12, 2.19, 9.67, 4.25, 3.22, 8, 0), 'F': (165.19, 147.18, 1.83, 9.13, 0, 5.48, 92, 0), 'G': (75.07, 57.05, 2.34, 9.6, 0, 5.97, 0, 0), 'H': (155.16, 137.14, 1.82, 9.17, 6, 7.59, -42, 0), 'I': (131.18, 113.16, 2.36, 9.6, 0, 6.02, 100, 0), 'K': (146.19, 128.18, 2.18, 8.95, 10.53, 9.74, -37, 0), 'L': (131.18, 113.16, 2.36, 9.6, 0, 5.98, 100, 0), 'M': (149.21, 131.2, 2.28, 9.21, 0, 5.74, 74, 0), 'N': (132.12, 114.11, 2.02, 8.8, 0, 5.41, -41, 0), 'O': (131.13, 113.11, 1.82, 9.65, 0, 0, 0, 0), 'P': (115.13, 97.12, 1.99, 10.6, 0, 6.3, -46, 0), 'Q': (146.15, 128.13, 2.17, 9.13, 0, 5.65, -18, 0), 'R': (174.2, 156.19, 2.17, 9.04, 12.48, 10.76, -26, 0), 'S': (105.09, 87.08, 2.21, 9.15, 0, 5.68, -7, 0), 'T': (119.12, 101.11, 2.09, 9.1, 0, 5.6, 13, 0), 'U': (168.07, 150.05, 5.47, 10.28, 0, 3.9, 52, 0), 'V': (117.15, 99.13, 2.32, 9.62, 0, 5.96, 97, 0), 'W': (204.23, 186.22, 2.83, 9.39, 0, 5.89, 84, 0), 'X': (136.74, 118.73, 2.06, 9.0, 2.51, 5.74, 21.86, 0), 'Y': (181.19, 163.18, 2.2, 9.11, 10.07, 5.66, 49, 0), 'Z': (146.64, 128.625, 2.18, 9.4, 2.125, 4.435, -5, 0)}

//www.ncbi.nlm.nih.gov/Class/FieldGuide/BLOSUM62.txt

Type

Taken from

Type

https