Skip to content
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.

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

remove_unused_fragments bug fix #271

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 0 additions & 1 deletion alphabase/peptide/fragment.py
Original file line number Diff line number Diff line change
Expand Up @@ -928,7 +928,6 @@ def remove_unused_fragments(
returns the reindexed precursor DataFrame and the sliced fragment DataFrames
"""

precursor_df = precursor_df.sort_values([frag_start_col], ascending=True)
frag_idx = precursor_df[[frag_start_col, frag_stop_col]].values

new_frag_idx, fragment_pointer = compress_fragment_indices(frag_idx)
Expand Down
145 changes: 145 additions & 0 deletions tests/test_remove_unused_fragments.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,145 @@
import numpy as np
import pandas as pd
import pytest

from alphabase.peptide.fragment import remove_unused_fragments


@pytest.fixture
def hdf_data():
"""
Fixture to automatically generate precursor_df and fragment_intensity_df.
"""
# Data for precursor_df
sequences = [
"PSKGPLQSVQVFGR",
"FLISLLEEYFK",
"MTEDALRLNLLK",
"FMSAYEQR",
"PGPKGEAGPTGPQGEPGVR",
"YEITEQR",
"DAEAAEATAEGALKAEK",
"FGDSRGGGGNFGPGPGSNFR",
"LDEKENLSAK",
"ATVASSTQKFQDLGVK",
"GFALVGVGSEASSKK",
"LQLEIDQKK",
"MAGLELLSDQGYR",
"RGGPGGPPGPLMEQMGGR",
]

frag_start_idx = [151, 81, 110, 24, 296, 17, 229, 334, 69, 183, 180, 26, 123, 284]
frag_stop_idx = [164, 91, 121, 31, 314, 23, 245, 353, 78, 198, 194, 34, 135, 301]
charge = [2] * len(sequences)
nAA = [len(seq) for seq in sequences]

precursor_df = pd.DataFrame(
{
"sequence": sequences,
"frag_start_idx": frag_start_idx,
"frag_stop_idx": frag_stop_idx,
"charge": charge,
"nAA": nAA,
}
)

# Data for fragment_intensity_df
fragment_intensity_data = np.random.uniform(
0.0, 600.0, size=(max(precursor_df["frag_stop_idx"]), 4)
)
fragment_intensity_df = pd.DataFrame(
fragment_intensity_data, columns=["b_z1", "b_z2", "y_z1", "y_z2"]
)

return precursor_df, fragment_intensity_df


def test_case_no_nAA_column(hdf_data):
"""
Test case 1: Precursor dataframe without the 'nAA' column.
"""
precursor_df, fragment_intensity_df = hdf_data
case1_precursor_df = precursor_df.copy().drop(columns=["nAA"])
case1_precursor_df, _ = remove_unused_fragments(
precursor_df=case1_precursor_df,
fragment_df_list=(fragment_intensity_df,),
)

assert case1_precursor_df[
"frag_start_idx"
].is_monotonic_increasing, "frag_start_idx must be monotonic increasing"
assert (
case1_precursor_df["frag_start_idx"].iloc[1:].values
== case1_precursor_df["frag_stop_idx"].iloc[:-1].values
).all(), "frag_start_idx[i] must equal frag_stop_idx[i-1]"


def test_case_unordered_nAA_column(hdf_data):
"""
Test case 2: Precursor dataframe with unordered 'nAA' column.
"""
precursor_df, fragment_intensity_df = hdf_data
case2_precursor_df = (
precursor_df.copy().sample(frac=1, random_state=42).reset_index(drop=True)
)
case2_precursor_df_nAA = (
case2_precursor_df["nAA"].copy()
if "nAA" in case2_precursor_df.columns
else None
)

case2_precursor_df, _ = remove_unused_fragments(
precursor_df=case2_precursor_df,
fragment_df_list=(fragment_intensity_df,),
)

assert case2_precursor_df[
"frag_start_idx"
].is_monotonic_increasing, "frag_start_idx must be monotonic increasing"
assert (
case2_precursor_df["frag_start_idx"].iloc[1:].values
== case2_precursor_df["frag_stop_idx"].iloc[:-1].values
).all(), "frag_start_idx[i] must equal frag_stop_idx[i-1]"

if case2_precursor_df_nAA is not None:
assert (
case2_precursor_df["nAA"] == case2_precursor_df_nAA
).all(), "nAA values must remain unchanged"


def test_case_ordered_nAA_column(hdf_data):
"""
Test case 3: Precursor dataframe with ordered 'nAA' column.
"""
precursor_df, fragment_intensity_df = hdf_data
case3_precursor_df = (
precursor_df.sort_values("nAA").reset_index(drop=True)
if "nAA" in precursor_df.columns
else precursor_df.copy()
)
case3_precursor_df_nAA = (
case3_precursor_df["nAA"].copy()
if "nAA" in case3_precursor_df.columns
else None
)

case3_precursor_df, _ = remove_unused_fragments(
precursor_df=case3_precursor_df,
fragment_df_list=(fragment_intensity_df,),
)

assert case3_precursor_df[
"frag_start_idx"
].is_monotonic_increasing, "frag_start_idx must be monotonic increasing"
assert (
case3_precursor_df["frag_start_idx"].iloc[1:].values
== case3_precursor_df["frag_stop_idx"].iloc[:-1].values
).all(), "frag_start_idx[i] must equal frag_stop_idx[i-1]"

if case3_precursor_df_nAA is not None:
assert (
case3_precursor_df["nAA"] == case3_precursor_df_nAA
).all(), "nAA values must remain unchanged"
assert case3_precursor_df[
"nAA"
].is_monotonic_increasing, "nAA column must be monotonic increasing"
Loading