Commit f93e213b authored by Martin Larralde's avatar Martin Larralde
Browse files

Add methods to get the occurrences and frequencies of amino acids in a `Peptide`

parent 26d4c118
import array
import collections
import math
import random
import statistics
......@@ -115,6 +116,23 @@ class ZScales(typing.NamedTuple):
class Peptide(object):
# --- Class constants ----------------------------------------------------
# fmt: off
_CODE1 = [
"A", "R", "N", "D", "C", "Q", "E", "G", "H", "I", "L", "K", "M", "F",
"P", "O", "S", "U", "T", "W", "Y", "V", "B", "Z", "X", "J",
# fmt: off
_CODE3 = [
"Ala", "Arg", "Asn", "Asp", "Cys", "Gln", "Glu", "Gly", "His", "Ile",
"Leu", "Lys", "Met", "Phe", "Pro", "Pyl", "Ser", "Sec", "Thr", "Trp",
"Tyr", "Val", "Asx", "Glx", "Xaa", "Xle",
# --- Class methods ------------------------------------------------------
def sample(
......@@ -308,6 +326,46 @@ class Peptide(object):
# --- Sequence properties -----------------------------------------------
def counts(self) -> typing.Dict[str, int]:
"""Return a table of amino-acid counts in the peptide.
`dict`: A dictionary mapping each amino-acid code to the number
of times it occurs in the peptide sequence.
>>> p = Peptide("SDKEVDEVDAALS")
>>> {k:v for k,v in p.counts().items() if v != 0}
{'A': 2, 'D': 3, 'E': 2, 'L': 1, 'K': 1, 'S': 2, 'V': 2}
# NB: This is consistently faster than using a `collections.Counter`
# because `str.count` has a fast C implementation based on
# `memchr` while `collections.Counter` has to iterate, which has
# some overhead.
return {
aa: self.sequence.count(aa)
for aa in self._CODE1
def frequencies(self) -> typing.Dict[str, float]:
"""Return a table of amino-acid frequencies in the peptide.
`dict`: A dictionary mapping each amino-acid code to its
frequency in the peptide sequence.
>>> p = Peptide("AALS")
>>> {k:v for k,v in p.frequencies().items() if v != 0}
{'A': 0.5, 'L': 0.25, 'S': 0.25}
return {
for aa,count in self.counts().items()
# --- Physico-chemical properties ----------------------------------------
def aliphatic_index(self) -> float:
......@@ -1070,9 +1128,6 @@ class Peptide(object):
This function builds a profile computing the hydrophobic moment of
a section of the peptide based on the primary sequecne.
>>> peptide = Peptide("ARQQNLFINFCLILIFLLLI")
>>> uH = peptide.hydrophobic_moment_profile(window=12, angle=100)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment