Skip to content
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: 1 addition & 0 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ dependencies = [
"matchms>=0.23",
"numpy>=1.24",
"PyYAML>=6.0",
"tqdm>=4.66",
]

[project.optional-dependencies]
Expand Down
22 changes: 7 additions & 15 deletions yogimass/processing.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
from __future__ import annotations

import logging
from tqdm import tqdm
from matchms.importing import load_from_mgf, load_from_msp
from matchms.filtering import (
default_filters,
Expand All @@ -25,9 +26,6 @@

logger = logging.getLogger(__name__)

# Interval for progress logging
LOG_INTERVAL = 1000


def metadata_processing(spectrum):
"""
Expand Down Expand Up @@ -78,19 +76,16 @@ def clean_mgf_library(mgf_path: str) -> list:
"""
logger.info(f"Cleaning {mgf_path} library spectra...")
library_list = list(load_from_mgf(mgf_path))

# Apply filters sequentially
processed_spectra = []
for i, s in enumerate(library_list):
if (i + 1) % LOG_INTERVAL == 0:
logger.info(f"Processed {i + 1} / {len(library_list)} spectra...")

for s in tqdm(library_list, desc="Cleaning spectra", unit="spectrum"):
meta_processed = metadata_processing(s)
if meta_processed:
peak_processed = peak_processing(meta_processed)
if peak_processed:
processed_spectra.append(peak_processed)

logger.info(f"Retained {len(processed_spectra)} spectra after cleaning.")
return processed_spectra

Expand All @@ -101,17 +96,14 @@ def clean_msp_library(msp_path: str) -> list:
"""
logger.info(f"Cleaning {msp_path} library spectra...")
library_list = list(load_from_msp(msp_path))

processed_spectra = []
for i, s in enumerate(library_list):
if (i + 1) % LOG_INTERVAL == 0:
logger.info(f"Processed {i + 1} / {len(library_list)} spectra...")

processed_spectra = []
for s in tqdm(library_list, desc="Cleaning spectra", unit="spectrum"):
meta_processed = metadata_processing(s)
if meta_processed:
peak_processed = peak_processing(meta_processed)
if peak_processed:
processed_spectra.append(peak_processed)

logger.info(f"Retained {len(processed_spectra)} spectra after cleaning.")
return processed_spectra