Skip to content

update uv absorbance weights #127

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Jung-Choi-01 merged 1 commit into from
Oct 20, 2026
Merged

update uv absorbance weights #127

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion backend/tests/test_protein.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -195,7 +195,7 @@ def test_prosite_short_to_regex(self):
def test_calculate_absorbance(self):
file = "backend/tests/data/singleProtein.fasta"
first_seq = next(iter(Protein.parse_protein(file).values()))[1]
expected = 740
expected = 25000
actual = Protein.calculate_absorbance(first_seq)

self.assertEqual(actual, expected)
Expand Down
42 changes: 22 additions & 20 deletions backend/utility/protein.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,26 +8,26 @@
class Protein():

AMINO_ACIDS = {
'A': {'mass': 71.07, 'pKa': 0, 'absorbance': 1},
'R': {'mass': 156.18, 'pKa': 12.48, 'absorbance': 1},
'N': {'mass': 114.08, 'pKa': 0, 'absorbance': 1},
'D': {'mass': 115.08, 'pKa': 3.65, 'absorbance': 1},
'C': {'mass': 103.14, 'pKa': 8.18, 'absorbance': 1},
'E': {'mass': 129.11, 'pKa': 4.25, 'absorbance': 1},
'Q': {'mass': 128.13, 'pKa': 0, 'absorbance': 1},
'G': {'mass': 57.05, 'pKa': 0, 'absorbance': 1},
'H': {'mass': 137.14, 'pKa': 6.00, 'absorbance': 1},
'I': {'mass': 113.16, 'pKa': 0, 'absorbance': 1},
'L': {'mass': 113.16, 'pKa': 0, 'absorbance': 1},
'K': {'mass': 128.17, 'pKa': 10.53, 'absorbance': 1},
'M': {'mass': 131.19, 'pKa': 0, 'absorbance': 1},
'F': {'mass': 147.17, 'pKa': 0, 'absorbance': 3},
'P': {'mass': 97.11, 'pKa': 0, 'absorbance': 1},
'S': {'mass': 87.07, 'pKa': 0, 'absorbance': 1},
'T': {'mass': 101.10, 'pKa': 0, 'absorbance': 1},
'W': {'mass': 186.21, 'pKa': 0, 'absorbance': 10},
'Y': {'mass': 163.17, 'pKa': 10.07, 'absorbance': 4},
'V': {'mass': 99.13, 'pKa': 0, 'absorbance': 1}
'A': {'mass': 71.07, 'pKa': 0, 'absorbance': 0},
'R': {'mass': 156.18, 'pKa': 12.48, 'absorbance': 0},
'N': {'mass': 114.08, 'pKa': 0, 'absorbance': 0},
'D': {'mass': 115.08, 'pKa': 3.65, 'absorbance': 0},
'C': {'mass': 103.14, 'pKa': 8.18, 'absorbance': 125},
'E': {'mass': 129.11, 'pKa': 4.25, 'absorbance': 0},
'Q': {'mass': 128.13, 'pKa': 0, 'absorbance': 0},
'G': {'mass': 57.05, 'pKa': 0, 'absorbance': 0},
'H': {'mass': 137.14, 'pKa': 6.00, 'absorbance': 0},
'I': {'mass': 113.16, 'pKa': 0, 'absorbance': 0},
'L': {'mass': 113.16, 'pKa': 0, 'absorbance': 0},
'K': {'mass': 128.17, 'pKa': 10.53, 'absorbance': 0},
'M': {'mass': 131.19, 'pKa': 0, 'absorbance': 0},
'F': {'mass': 147.17, 'pKa': 0, 'absorbance': 0},
'P': {'mass': 97.11, 'pKa': 0, 'absorbance': 0},
'S': {'mass': 87.07, 'pKa': 0, 'absorbance': 0},
'T': {'mass': 101.10, 'pKa': 0, 'absorbance': 0},
'W': {'mass': 186.21, 'pKa': 0, 'absorbance': 5500},
'Y': {'mass': 163.17, 'pKa': 10.07, 'absorbance': 1490},
'V': {'mass': 99.13, 'pKa': 0, 'absorbance': 0}
}

# Utilizes Biopython SeqIO library to parse through a fasta file given by the user and collect
Expand Down Expand Up @@ -75,6 +75,8 @@ def get_amino_acid_count(file):
def calculate_absorbance(sequence: str) -> int:
'''
Simulate the "UV Absorbance" of a protein as the sum of its amino acids' absorbances
Methodology/estimates taken from https://web.expasy.org/protparam/protparam-doc.html,
except we don't divide by molecular weight since we'd like to scale absorbance with molecular weight
'''
return sum(Protein.AMINO_ACIDS[amino_acid]['absorbance'] for amino_acid in sequence)

Expand Down
Loading