Skip to content

Fix support for sqlalchemy v2, keeping backwards compatibility with v1.4 #249

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

Open
RalfG wants to merge 3 commits into
base: releases
Choose a base branch
from
+286 −50
Open

Fix support for sqlalchemy v2, keeping backwards compatibility with v1.4 #249

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a9181fe
Fix support for sqlalchemy v2, keeping backwards compatibility with v1.4
RalfG Dec 9, 2025
3826d8b
Revert unneeded string conversion of path; use pathlike instead of pa…
RalfG Dec 10, 2025
b6fa6dc
Merge branch 'releases' into fix/support-sqlalchemy2
RalfG Dec 11, 2025
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
74 changes: 40 additions & 34 deletions ms2pip/_utils/dlib.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,16 +18,18 @@
TypeDecorator,
)
from sqlalchemy.dialects.sqlite import BLOB
from sqlalchemy.engine import Connection

DLIB_VERSION = "0.1.14"


class CompressedArray(TypeDecorator):
""" Sqlite-like does not support arrays.
Let's use a custom type decorator.
"""Sqlite-like does not support arrays.
Let's use a custom type decorator.

See http://docs.sqlalchemy.org/en/latest/core/types.html#sqlalchemy.types.TypeDecorator
See http://docs.sqlalchemy.org/en/latest/core/types.html#sqlalchemy.types.TypeDecorator
"""

impl = BLOB

def __init__(self, dtype, *args, **kwargs):
Expand All @@ -49,51 +51,55 @@ def copy(self):

metadata = MetaData()

big_float = numpy.dtype('>f4')
big_double = numpy.dtype('>f8')
big_float = numpy.dtype(">f4")
big_double = numpy.dtype(">f8")

Entry = Table(
'entries',
"entries",
metadata,
Column('PrecursorMz', Float, nullable=False, index=True),
Column('PrecursorCharge', Integer, nullable=False),
Column('PeptideModSeq', String, nullable=False),
Column('PeptideSeq', String, nullable=False, index=True),
Column('Copies', Integer, nullable=False),
Column('RTInSeconds', Float, nullable=False),
Column('Score', Float, nullable=False),
Column('MassEncodedLength', Integer, nullable=False),
Column('MassArray', CompressedArray(big_double), nullable=False),
Column('IntensityEncodedLength', Integer, nullable=False),
Column('IntensityArray', CompressedArray(big_float), nullable=False),
Column('CorrelationEncodedLength', Integer, nullable=True),
Column('CorrelationArray', CompressedArray(big_float), nullable=True),
Column('RTInSecondsStart', Float, nullable=True),
Column('RTInSecondsStop', Float, nullable=True),
Column('MedianChromatogramEncodedLength', Integer, nullable=True),
Column('MedianChromatogramArray', CompressedArray(big_float), nullable=True),
Column('SourceFile', String, nullable=False),
Column("PrecursorMz", Float, nullable=False, index=True),
Column("PrecursorCharge", Integer, nullable=False),
Column("PeptideModSeq", String, nullable=False),
Column("PeptideSeq", String, nullable=False, index=True),
Column("Copies", Integer, nullable=False),
Column("RTInSeconds", Float, nullable=False),
Column("Score", Float, nullable=False),
Column("MassEncodedLength", Integer, nullable=False),
Column("MassArray", CompressedArray(big_double), nullable=False),
Column("IntensityEncodedLength", Integer, nullable=False),
Column("IntensityArray", CompressedArray(big_float), nullable=False),
Column("CorrelationEncodedLength", Integer, nullable=True),
Column("CorrelationArray", CompressedArray(big_float), nullable=True),
Column("RTInSecondsStart", Float, nullable=True),
Column("RTInSecondsStop", Float, nullable=True),
Column("MedianChromatogramEncodedLength", Integer, nullable=True),
Column("MedianChromatogramArray", CompressedArray(big_float), nullable=True),
Column("SourceFile", String, nullable=False),
)

Index('ix_entries_PeptideModSeq_PrecursorCharge_SourceFile', Entry.c.PeptideModSeq, Entry.c.PrecursorCharge, Entry.c.SourceFile)
Index(
"ix_entries_PeptideModSeq_PrecursorCharge_SourceFile",
Entry.c.PeptideModSeq,
Entry.c.PrecursorCharge,
Entry.c.SourceFile,
)

PeptideToProtein = Table(
'peptidetoprotein',
"peptidetoprotein",
metadata,
Column('PeptideSeq', String, nullable=False, index=True),
Column('isDecoy', Boolean, nullable=True),
Column('ProteinAccession', String, nullable=False, index=True),
Column("PeptideSeq", String, nullable=False, index=True),
Column("isDecoy", Boolean, nullable=True),
Column("ProteinAccession", String, nullable=False, index=True),
)

Metadata = Table(
'metadata',
"metadata",
metadata,
Column('Key', String, nullable=False, index=True),
Column('Value', String, nullable=False),
Column("Key", String, nullable=False, index=True),
Column("Value", String, nullable=False),
)


def open_sqlite(filename: Union[str, Path]) -> sqlalchemy.engine.Connection:
def open_sqlite(filename: Union[str, Path]) -> Connection:
engine = sqlalchemy.create_engine(f"sqlite:///{filename}")
metadata.bind = engine
return engine.connect()
26 changes: 14 additions & 12 deletions ms2pip/spectrum_output.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,13 +47,15 @@
from collections import defaultdict
from io import StringIO
from pathlib import Path
from os import PathLike
from time import localtime, strftime
from typing import Any, Dict, Generator, List, Optional, Union

import numpy as np
from psm_utils import PSM, Peptidoform
from pyteomics import proforma
from sqlalchemy import engine, select
from sqlalchemy import select
from sqlalchemy.engine import Connection

from ms2pip._utils import dlib
from ms2pip.result import ProcessingResult
Expand All @@ -62,7 +64,7 @@


def write_spectra(
filename: Union[str, Path],
filename: Union[str, PathLike],
processing_results: List[ProcessingResult],
file_format: str = "tsv",
write_mode: str = "w",
Expand Down Expand Up @@ -92,7 +94,7 @@ class _Writer(ABC):

suffix = ""

def __init__(self, filename: Union[str, Path], write_mode: str = "w"):
def __init__(self, filename: Union[str, PathLike], write_mode: str = "w"):
self.filename = Path(filename).with_suffix(self.suffix)
self.write_mode = write_mode

Expand Down Expand Up @@ -466,7 +468,7 @@ class Bibliospec(_Writer):
"ion-mobility",
]

def __init__(self, filename: Union[str, Path], write_mode: str = "w"):
def __init__(self, filename: Union[str, PathLike], write_mode: str = "w"):
super().__init__(filename, write_mode)
self.ssl_file = self.filename.with_suffix(self.ssl_suffix)
self.ms2_file = self.filename.with_suffix(self.ms2_suffix)
Expand Down Expand Up @@ -618,7 +620,7 @@ def _format_modified_sequence(peptidoform: Peptidoform) -> str:
)

@staticmethod
def _get_last_ssl_scan_number(ssl_file: Union[str, Path, StringIO]):
def _get_last_ssl_scan_number(ssl_file: Union[str, PathLike, StringIO]):
"""Read scan number of last line in a Bibliospec SSL file."""
if isinstance(ssl_file, StringIO):
ssl_file.seek(0)
Expand Down Expand Up @@ -653,7 +655,7 @@ def open(self):
def write(self, processing_results: List[ProcessingResult]):
"""Write MS2PIP predictions to a DLIB SQLite file."""
connection = self._file_object
dlib.metadata.create_all()
dlib.metadata.create_all(connection.engine)
self._write_metadata(connection)
self._write_entries(processing_results, connection, self.filename)
self._write_peptide_to_protein(processing_results, connection)
Expand Down Expand Up @@ -682,11 +684,11 @@ def _format_modified_sequence(peptidoform: Peptidoform) -> str:
)

@staticmethod
def _write_metadata(connection: engine.Connection):
def _write_metadata(connection: Connection):
"""Write metadata to DLIB SQLite file."""
with connection.begin():
version = connection.execute(
select([dlib.Metadata.c.Value]).where(dlib.Metadata.c.Key == "version")
select(dlib.Metadata.c.Value).where(dlib.Metadata.c.Key == "version")
).scalar()
if version is None:
connection.execute(
Expand All @@ -699,8 +701,8 @@ def _write_metadata(connection: engine.Connection):
@staticmethod
def _write_entries(
processing_results: List[ProcessingResult],
connection: engine.Connection,
output_filename: str,
connection: Connection,
output_filename: Union[str, PathLike],
):
"""Write spectra to DLIB SQLite file."""
with connection.begin():
Expand Down Expand Up @@ -730,7 +732,7 @@ def _write_entries(
)

@staticmethod
def _write_peptide_to_protein(results: List[ProcessingResult], connection: engine.Connection):
def _write_peptide_to_protein(results: List[ProcessingResult], connection: Connection):
"""Write peptide-to-protein mappings to DLIB SQLite file."""
peptide_to_proteins = {
(result.psm.peptidoform.sequence, protein)
Expand All @@ -743,7 +745,7 @@ def _write_peptide_to_protein(results: List[ProcessingResult], connection: engin
sql_peptide_to_proteins = set()
proteins = {protein for _, protein in peptide_to_proteins}
for peptide_to_protein in connection.execute(
dlib.PeptideToProtein.select().where(
select(dlib.PeptideToProtein).where(
dlib.PeptideToProtein.c.ProteinAccession.in_(proteins)
)
):
Expand Down
3 changes: 1 addition & 2 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,8 +37,7 @@ dependencies = [
"pandas>=1,<3",
"pyarrow",
"pyteomics>=3.5,<5",
"tomlkit>=0.5,<1",
"sqlalchemy>=1.3,<2",
"sqlalchemy>=1.4,<3",
"click>=7,<9",
"xgboost>=1.3,<3",
"lxml>=4",
Expand Down
Loading