msreport 0.0.27__tar.gz → 0.0.28__tar.gz

{msreport-0.0.27 → msreport-0.0.28}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: msreport
-Version: 0.0.27
+Version: 0.0.28
 Summary: Post processing and analysis of quantitative proteomics data
 Author-email: "David M. Hollenstein" <hollenstein.david@gmail.com>
 License: Apache-2.0
@@ -19,12 +19,15 @@ Requires-Dist: pandas>=1.4.4
 Requires-Dist: profasta>=0.0.4
 Requires-Dist: pyteomics>=4.6.0
 Requires-Dist: pyyaml>=6.0.0
-Requires-Dist: rpy2>=3.5.3
+Requires-Dist: rpy2!=3.5.13,>=3.5.3
 Requires-Dist: scikit-learn>=1.0.0
 Requires-Dist: scipy>=1.9.1
 Requires-Dist: seaborn>=0.12.0
 Requires-Dist: statsmodels>=0.13.2
 Requires-Dist: typing_extensions>=4
+Provides-Extra: dev
+Requires-Dist: mypy>=1.15.0; extra == "dev"
+Requires-Dist: pytest>=8.3.5; extra == "dev"
 Dynamic: license-file
 
 [![Project Status: WIP – Initial development is in progress, but there has not yet been a stable, usable release suitable for the public.](https://www.repostatus.org/badges/latest/wip.svg)](https://www.repostatus.org/#wip)
@@ -118,7 +121,7 @@ command as described above.
 ### Additional requirements
 
 MsReport provides an interface to the R package LIMMA for differential expression
-analysis, which requires a local installation of R (R version 3.4 or higher) and the
+analysis, which requires a local installation of R (R version 4.0 or higher) and the
 system environment variable "R_HOME" to be set to the R home directory. Note that it
 might be necessary to restart the computer after adding the "R_HOME" variable. The R
 home directory can also be found from within R by using the command below, and might

{msreport-0.0.27 → msreport-0.0.28}/README.md

@@ -89,7 +89,7 @@ command as described above.
 ### Additional requirements
 
 MsReport provides an interface to the R package LIMMA for differential expression
-analysis, which requires a local installation of R (R version 3.4 or higher) and the
+analysis, which requires a local installation of R (R version 4.0 or higher) and the
 system environment variable "R_HOME" to be set to the R home directory. Note that it
 might be necessary to restart the computer after adding the "R_HOME" variable. The R
 home directory can also be found from within R by using the command below, and might

{msreport-0.0.27 → msreport-0.0.28}/msreport/__init__.py

@@ -1,13 +1,11 @@
-from msreport.qtable import Qtable
-from msreport.reader import MaxQuantReader, FragPipeReader, SpectronautReader
-
-from msreport.fasta import import_protein_database
-
 import msreport.analyze
 import msreport.export
 import msreport.impute
 import msreport.normalize
 import msreport.plot
 import msreport.reader
+from msreport.fasta import import_protein_database
+from msreport.qtable import Qtable
+from msreport.reader import FragPipeReader, MaxQuantReader, SpectronautReader
 
-__version__ = "0.0.27"
+__version__ = "0.0.28"

{msreport-0.0.27 → msreport-0.0.28}/msreport/aggregate/condense.py

@@ -71,7 +71,7 @@ def maximum_per_column(array: np.ndarray) -> np.ndarray:
     return np.array([maximum(i) for i in array.transpose()])
 
 
-def minimum(array: np.ndarray) -> int:
+def minimum(array: np.ndarray) -> float:
     """Returns the lowest finite value from one or multiple columns."""
     array = array.flatten()
     if np.isfinite(array).any():

{msreport-0.0.27 → msreport-0.0.28}/msreport/aggregate/pivot.py

@@ -1,6 +1,7 @@
 from typing import Iterable, Union
 
 import pandas as pd
+
 import msreport.aggregate.condense as CONDENSE
 import msreport.helper
 

{msreport-0.0.27 → msreport-0.0.28}/msreport/aggregate/summarize.py

@@ -218,7 +218,7 @@ def aggregate_unique_groups(
     columns_to_aggregate: Union[str, Iterable],
     condenser: Callable,
     is_sorted: bool,
-) -> (np.ndarray, np.ndarray):
+) -> tuple[np.ndarray, np.ndarray]:
     """Aggregates column(s) by applying a condenser function to unique groups.
 
     The function returns two arrays containing the aggregated values and the
@@ -256,7 +256,7 @@ def aggregate_unique_groups(
 
 def _prepare_grouping_indices(
     table: pd.DataFrame, group_by: str, is_sorted: bool
-) -> (np.ndarray, np.ndarray, pd.DataFrame):
+) -> tuple[np.ndarray, np.ndarray, pd.DataFrame]:
     """Prepares start indices and names of unique groups from a sorted dataframe.
 
     Args:

{msreport-0.0.27 → msreport-0.0.28}/msreport/analyze.py

@@ -1,8 +1,9 @@
-""" The analyze module contains methods for analysing quantification results. """
+"""The analyze module contains methods for analysing quantification results."""
 
 from __future__ import annotations
-from typing import Iterable, Optional, Protocol
+
 import warnings
+from typing import Iterable, Optional, Protocol, Sequence
 
 import numpy as np
 import pandas as pd
@@ -10,6 +11,7 @@ import pandas as pd
 import msreport.normalize
 import msreport.rinterface
 from msreport.helper import find_sample_columns
+from msreport.qtable import Qtable
 
 
 class Transformer(Protocol):
@@ -234,7 +236,7 @@ def normalize_expression(
 
 def create_site_to_protein_normalizer(
     qtable: Qtable, category_column: str = "Representative protein"
-) -> msreport.normalizer.CategoricalNormalizer:
+) -> msreport.normalize.CategoricalNormalizer:
     """Creates a fitted `CategoricalNormalizer` for site-to-protein normalization.
 
     The `CategoricalNormalizer` is fitted to protein expression profiles of the provided
@@ -254,8 +256,8 @@ def create_site_to_protein_normalizer(
         samples_as_columns=True,
         features=[category_column],
     )
-    completely_quantified = (
-        ~reference_expression[qtable.get_samples()].isna().any(axis=1)
+    completely_quantified = ~reference_expression[qtable.get_samples()].isna().any(
+        axis=1
     )
     reference_expression = reference_expression[completely_quantified]
 
@@ -275,7 +277,7 @@ def create_ibaq_transformer(
     qtable: Qtable,
     category_column: str = "Representative protein",
     ibaq_column: str = "iBAQ peptides",
-) -> msreport.normalizer.CategoricalNormalizer:
+) -> msreport.normalize.CategoricalNormalizer:
     """Creates a fitted `CategoricalNormalizer` for iBAQ transformation.
 
     The `CategoricalNormalizer` is fitted to iBAQ peptide counts of the provided
@@ -301,7 +303,7 @@ def create_ibaq_transformer(
     ibaq_factor_values[ibaq_factor_values < 1] = 1
     ibaq_factor_values = np.log2(ibaq_factor_values)
 
-    reference_table = pd.DataFrame({c: ibaq_factor_values for c in sample_columns})
+    reference_table = pd.DataFrame(dict.fromkeys(sample_columns, ibaq_factor_values))
     reference_table[category_column] = category_values
 
     normalizer = msreport.normalize.CategoricalNormalizer(category_column)
@@ -422,7 +424,15 @@ def calculate_multi_group_comparison(
             correspond to entries from qtable.design["Experiment"].
         exclude_invalid: If true, the column "Valid" is used to determine which rows are
             used for calculating the group comparisons; default True.
+
+    Raises:
+        ValueError: If 'experiment_pairs' contains invalid entries. Each experiment pair
+            must have exactly two entries and the two entries must not be the same. All
+            experiments must be present in qtable.design. No duplicate experiment pairs
+            are allowed.
     """
+    _validate_experiment_pairs(qtable, experiment_pairs)
+
     table = qtable.make_expression_table(samples_as_columns=True, features=["Valid"])
     comparison_tag = " vs "
 
@@ -475,7 +485,7 @@ def two_group_comparison(
 
 def calculate_multi_group_limma(
     qtable: Qtable,
-    experiment_pairs: Iterable[Iterable[str]],
+    experiment_pairs: Sequence[Iterable[str]],
     exclude_invalid: bool = True,
     batch: bool = False,
     limma_trend: bool = True,
@@ -491,8 +501,7 @@ def calculate_multi_group_limma(
 
     Requires that expression columns are set, and expression values are log2 transformed
     All rows with missing values are ignored, impute missing values to allow
-    differential expression analysis of all rows. The qtable.data column
-    "Representative protein" is used as the index.
+    differential expression analysis of all rows.
 
     Args:
         qtable: Qtable instance that contains expression values for differential
@@ -510,13 +519,17 @@ def calculate_multi_group_limma(
             limma.eBayes for details; default True.
 
     Raises:
+        ValueError: If 'experiment_pairs' contains invalid entries. Each experiment pair
+            must have exactly two entries and the two entries must not be the same. All
+            experiments must be present in qtable.design. No duplicate experiment pairs
+            are allowed.
         KeyError: If the "Batch" column is not present in the qtable.design when
             'batch' is set to True.
         ValueError: If all values from qtable.design["Batch"] are identical when 'batch'
             is set to True.
-        ValueError: If the same experiment pair has been specified multiple times in
-            'experiment_pairs'.
     """
+    _validate_experiment_pairs(qtable, experiment_pairs)
+
     # TODO: not tested #
     if batch and "Batch" not in qtable.get_design():
         raise KeyError(
@@ -528,17 +541,10 @@ def calculate_multi_group_limma(
             "When using calculate_multi_group_limma(batch=True), not all values from"
             ' qtable.design["Batch"] are allowed to be identical.'
         )
-    if len(list(experiment_pairs)) != len(set(experiment_pairs)):
-        raise ValueError(
-            "The same experiment pair has been specified multiple times."
-            " Each entry in the `experiment_pairs` argument must be unique."
-        )
 
     design = qtable.get_design()
-    table = qtable.make_expression_table(
-        samples_as_columns=True, features=["Representative protein"]
-    )
-    table = table.set_index("Representative protein")
+    table = qtable.make_expression_table(samples_as_columns=True)
+    table.index = table.index.astype(str)  # It appears that a string is required for R
     comparison_tag = " vs "
 
     if exclude_invalid:
@@ -554,7 +560,7 @@ def calculate_multi_group_limma(
         experiment_to_r[experiment] = f".EXPERIMENT__{i:04d}"
     r_to_experiment = {v: k for k, v in experiment_to_r.items()}
 
-    r_experiment_pairs = []
+    r_experiment_pairs: list[str] = []
     for exp1, exp2 in experiment_pairs:
         r_experiment_pairs.append(f"{experiment_to_r[exp1]}-{experiment_to_r[exp2]}")
 
@@ -583,7 +589,7 @@ def calculate_multi_group_limma(
 
 def calculate_two_group_limma(
     qtable: Qtable,
-    experiment_pair: list[str],
+    experiment_pair: Sequence[str],
     exclude_invalid: bool = True,
     limma_trend: bool = True,
 ) -> None:
@@ -596,8 +602,7 @@ def calculate_two_group_limma(
 
     Requires that expression columns are set, and expression values are log2
     transformed. All rows with missing values are ignored, impute missing values to
-    allow differential expression analysis of all rows. The qtable.data
-    column "Representative protein" is used as the index.
+    allow differential expression analysis of all rows.
 
     Args:
         qtable: Qtable instance that contains expression values for differential
@@ -608,27 +613,30 @@ def calculate_two_group_limma(
             used for the differential expression analysis; default True.
         limma_trend: If true, an intensity-dependent trend is fitted to the prior
             variances; default True.
+    Raises:
+        ValueError: If 'experiment_pair' contains invalid entries. The experiment pair
+            must have exactly two entries and the two entries must not be the same. Both
+            experiments must be present in qtable.design.
     """
-    # TODO: not tested #
-    expression_table = qtable.make_expression_table(
-        samples_as_columns=True, features=["Representative protein"]
-    )
+    _validate_experiment_pair(qtable, experiment_pair)
+
+    # TODO: LIMMA function not tested #
+    table = qtable.make_expression_table(samples_as_columns=True)
     comparison_tag = " vs "
 
     if exclude_invalid:
         valid = qtable["Valid"]
     else:
-        valid = np.full(expression_table.shape[0], True)
+        valid = np.full(table.shape[0], True)
 
     samples_to_experiment = {}
     for experiment in experiment_pair:
-        mapping = {s: experiment for s in qtable.get_samples(experiment)}
+        mapping = dict.fromkeys(qtable.get_samples(experiment), experiment)
         samples_to_experiment.update(mapping)
 
-    table_columns = ["Representative protein"]
-    table_columns.extend(samples_to_experiment.keys())
-    table = expression_table[table_columns]
-    table = table.set_index("Representative protein")
+    # Keep only samples that are present in the 'experiment_pair'
+    table = table[samples_to_experiment.keys()]
+    table.index = table.index.astype(str)  # It appears that a string is required for R
     not_nan = table.isna().sum(axis=1) == 0
 
     mask = np.all([valid, not_nan], axis=0)
@@ -649,3 +657,63 @@ def calculate_two_group_limma(
     mapping = {col: f"{col} {comparison_group}" for col in limma_table.columns}
     limma_table.rename(columns=mapping, inplace=True)
     qtable.add_expression_features(limma_table)
+
+
+def _validate_experiment_pairs(
+    qtable: Qtable, exp_pairs: Iterable[Iterable[str]]
+) -> None:
+    """Validates that experiment pairs are valid and raises an error if not.
+
+    - All 'exp_pairs' entries must have a length of exactly 2.
+    - All experiments must be present in the qtable.design.
+    - No duplicate experiments are allowed in a pair.
+    - No duplicate experiment pairs are allowed.
+
+    Args:
+        qtable: Qtable instance containing experiment data.
+        exp_pairs: Iterable of experiment pairs to validate.
+
+    Raises:
+        ValueError: If any of the validation checks fail.
+    """
+    all_experiments = {exp for pair in exp_pairs for exp in pair}
+    missing_experiments = all_experiments - set(qtable.get_experiments())
+    if missing_experiments:
+        raise ValueError(
+            f"Experiments '{missing_experiments}' not found in qtable.design."
+        )
+    for experiment_pair in exp_pairs:
+        _validate_experiment_pair(qtable, experiment_pair)
+
+    if len(list(exp_pairs)) != len({tuple(pair) for pair in exp_pairs}):
+        raise ValueError(
+            f"Some experiment pairs in {exp_pairs} have been specified multiple "
+            "times. Each pair must occur only once."
+        )
+
+
+def _validate_experiment_pair(qtable: Qtable, exp_pair: Iterable[str]) -> None:
+    """Validates the experiment pair is valid and raises an error if not.
+
+    - The experiment pair must contain exactly two entries
+    - The two entries of the experiment pair must be different.
+    - Both  experiments must be present in the qtable.design.
+
+    Args:
+        qtable: Qtable instance containing experiment data.
+        experiment_pairs: Iterable of experiment pairs to validate.
+
+    Raises:
+        ValueError: If any of the validation checks fail.
+    """
+    if len(list(exp_pair)) != 2:
+        raise ValueError(
+            f"Experiment pair '{exp_pair}' contains more than two entries."
+        )
+    if len(list(exp_pair)) != len(set(exp_pair)):
+        raise ValueError(f"Experiment pair '{exp_pair}' contains the same entry twice.")
+    if set(exp_pair) - set(qtable.get_experiments()):
+        raise ValueError(
+            f"Experiments '{set(exp_pair) - set(qtable.get_experiments())}' "
+            "not found in qtable.design."
+        )

{msreport-0.0.27 → msreport-0.0.28}/msreport/errors.py

@@ -1,5 +1,4 @@
-class MsreportError(Exception):
-    ...
+class MsreportError(Exception): ...
 
 
 class NotFittedError(ValueError, AttributeError):

{msreport-0.0.27 → msreport-0.0.28}/msreport/export.py

@@ -13,10 +13,10 @@ Index([
 ], dtype='object')
 """
 
-from collections import defaultdict as ddict
 import os
-from typing import Iterable, Optional, Protocol
 import warnings
+from collections import defaultdict as ddict
+from typing import Iterable, Optional, Protocol, Sequence
 
 import numpy as np
 import pandas as pd
@@ -88,7 +88,7 @@ def contaminants_to_clipboard(qtable: Qtable) -> None:
 
     for column_tag in column_tags:
         columns.extend(helper.find_sample_columns(data, column_tag, samples))
-    columns = np.array(columns)[[c in data.columns for c in columns]]
+    columns = [c for c in columns if c in data.columns]
 
     contaminants = qtable["Potential contaminant"]
     data = data.loc[contaminants, columns]
@@ -135,10 +135,10 @@ def to_perseus_matrix(
     numeric_columns = set(numeric_columns).difference(expression_columns)
     numeric_columns = set(numeric_columns).difference(categorical_columns)
 
-    column_categories = ddict(lambda: default_category)
-    column_categories.update({c: "N" for c in numeric_columns})
-    column_categories.update({c: "C" for c in categorical_columns})
-    column_categories.update({c: "E" for c in expression_columns})
+    column_categories: ddict[str, str] = ddict(lambda: default_category)
+    column_categories.update(dict.fromkeys(numeric_columns, "N"))
+    column_categories.update(dict.fromkeys(categorical_columns, "C"))
+    column_categories.update(dict.fromkeys(expression_columns, "E"))
 
     column_annotation = [column_categories[column] for column in table.columns]
     column_annotation[0] = f"{annotation_row_prefix}{column_annotation[0]}"
@@ -219,6 +219,7 @@ def write_html_coverage_map(
             "change in a future release."
         ),
         FutureWarning,
+        stacklevel=2,
     )
     # Get protein information from the protein database
     protein_entry = protein_db[protein_id]
@@ -314,8 +315,8 @@ def _amica_table_from(qtable: Qtable) -> pd.DataFrame:
         sample_columns = helper.find_sample_columns(
             amica_table, tag, qtable.get_samples()
         )
-        non_sample_columns = set(columns).difference(set(sample_columns))
-        amica_table.drop(non_sample_columns, inplace=True, axis=1)
+        non_sample_columns = list(set(columns).difference(set(sample_columns)))
+        amica_table.drop(columns=non_sample_columns, inplace=True, axis=1)
 
     # Log transform columns if necessary
     for tag in intensity_column_tags:
@@ -437,7 +438,7 @@ def _generate_html_sequence_map(
     highlights = highlights if highlights is not None else {}
     sequence_length = len(sequence)
 
-    def write_row_index(pos: int, strings: list) -> str:
+    def write_row_index(pos: int, strings: list):
         ndigits = len(str(sequence_length))
         row_index = str(pos + 1).rjust(ndigits)
         html_entry = '<FONT COLOR="#000000">' + row_index + "   " + "</FONT>"
@@ -457,7 +458,7 @@ def _generate_html_sequence_map(
 
     in_covered_region: bool = False
     strings = []
-    strings.append(f'<FONT COLOR="#606060">')  # Set default text color to grey
+    strings.append('<FONT COLOR="#606060">')  # Set default text color to grey
     write_row_index(0, strings)
     for pos, character in enumerate(sequence):
         if pos in coverage_start_idx:
@@ -483,13 +484,15 @@ def _generate_html_sequence_map(
         if pos in coverage_stop_idx:
             in_covered_region = False
             close_coverage_region(strings)
-    strings.append(f"</FONT>")
+    strings.append("</FONT>")
 
     html_sequence_block = "".join(strings)
     return html_sequence_block
 
 
-def _find_covered_region_boundaries(coverage_mask: Iterable[bool]) -> list[tuple[int]]:
+def _find_covered_region_boundaries(
+    coverage_mask: Sequence[bool],
+) -> list[tuple[int, int]]:
     """Returns a list of boundaries from continuously covered regions in a protein.
 
     Args:

{msreport-0.0.27 → msreport-0.0.28}/msreport/fasta.py

@@ -1,7 +1,6 @@
 import pathlib
 from typing import Iterable, Union
 
-
 from profasta.db import ProteinDatabase
 
 
@@ -24,5 +23,7 @@ def import_protein_database(
     database = ProteinDatabase()
     paths = [fasta_path] if isinstance(fasta_path, (str, pathlib.Path)) else fasta_path
     for path in paths:
+        if isinstance(path, pathlib.Path):
+            path = path.as_posix()
         database.add_fasta(path, header_parser=header_parser, overwrite=True)
     return database

{msreport-0.0.27 → msreport-0.0.28}/msreport/helper/__init__.py

@@ -1,21 +1,21 @@
 from .calc import (
-    mode,
+    calculate_monoisotopic_mass,
+    calculate_sequence_coverage,
     calculate_tryptic_ibaq_peptides,
     make_coverage_mask,
-    calculate_sequence_coverage,
-    calculate_monoisotopic_mass,
+    mode,
 )
 from .table import (
     apply_intensity_cutoff,
-    guess_design,
-    intensities_in_logspace,
     find_columns,
     find_sample_columns,
+    guess_design,
+    intensities_in_logspace,
+    join_tables,
     keep_rows_by_partial_match,
     remove_rows_by_partial_match,
-    join_tables,
-    rename_sample_columns,
     rename_mq_reporter_channels,
+    rename_sample_columns,
 )
 from .temp import (
     extract_modifications,

{msreport-0.0.27 → msreport-0.0.28}/msreport/helper/calc.py

@@ -1,15 +1,13 @@
-import itertools
-from typing import Iterable
+from typing import Iterable, Sequence
 
 import numpy as np
-import scipy.stats
-import scipy.optimize
-
 import pyteomics.mass
 import pyteomics.parser
+import scipy.optimize
+import scipy.stats
 
 
-def mode(values: Iterable) -> float:
+def mode(values: Sequence) -> float:
     """Calculate the mode by using kernel-density estimation.
 
     Args:
@@ -19,25 +17,26 @@ def mode(values: Iterable) -> float:
     Returns:
         The estimated mode. If no finite values are present, returns nan.
     """
-    values = np.asarray(values)
-    finite_values = values[np.isfinite(values)]
+    finite_values = np.asarray(values)[np.isfinite(values)]
     if len(finite_values) == 0:
         return np.nan
     elif len(np.unique(finite_values)) == 1:
         return np.unique(finite_values)[0]
 
     kde = scipy.stats.gaussian_kde(finite_values)
-    minimum_function = lambda x: -kde(x)[0]
+
+    def _minimum_function(x):
+        return -kde(x)[0]
 
     min_slice, max_sclice = np.percentile(finite_values, (2, 98))
     slice_step = 0.2
     brute_optimize_result = scipy.optimize.brute(
-        minimum_function, [slice(min_slice, max_sclice + slice_step, slice_step)]
+        _minimum_function, [slice(min_slice, max_sclice + slice_step, slice_step)]
     )
     rough_minimum = brute_optimize_result[0]
 
     local_optimize_result = scipy.optimize.minimize(
-        minimum_function, x0=rough_minimum, method="BFGS"
+        _minimum_function, x0=rough_minimum, method="BFGS"
     )
     fine_minimum = local_optimize_result.x[0]
     return fine_minimum
@@ -91,8 +90,8 @@ def calculate_monoisotopic_mass(protein_sequence: str) -> float:
 
 
 def make_coverage_mask(
-    protein_length: int, peptide_positions: list[(int, int)]
-) -> np.array:
+    protein_length: int, peptide_positions: Iterable[Iterable[int]]
+) -> np.ndarray:
     """Returns a Boolean array with True for positions present in 'peptide_positions'.
 
     Args:
@@ -109,8 +108,8 @@ def make_coverage_mask(
 
 
 def calculate_sequence_coverage(
-    protein_length: int, peptide_positions: list[(int, int)], ndigits: int = 1
-) -> np.array:
+    protein_length: int, peptide_positions: Iterable[Iterable[int]], ndigits: int = 1
+) -> float:
     """Calculates the protein sequence coverage given a list of peptide positions.
 
     Args:

{msreport-0.0.27 → msreport-0.0.28}/msreport/helper/maxlfq.py

@@ -1,6 +1,6 @@
 import itertools
-from typing import Callable
 import warnings
+from typing import Callable
 
 import numpy as np
 
@@ -125,7 +125,7 @@ def calculate_pairwise_mode_log_ratio_matrix(
 
 def prepare_coefficient_matrix(
     ratio_matrix: np.ndarray,
-) -> (np.ndarray, np.ndarray, np.ndarray):
+) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
     """Prepares coefficients, ratios, and initial row indices from a log ratio matrix.
 
     Args:

{msreport-0.0.27 → msreport-0.0.28}/msreport/helper/table.py

@@ -1,5 +1,5 @@
 import re
-from typing import Iterable, Union
+from typing import Iterable, Sequence, Union
 
 import numpy as np
 import pandas as pd
@@ -63,7 +63,7 @@ def intensities_in_logspace(data: Union[pd.DataFrame, np.ndarray, Iterable]) ->
     """
     data = np.array(data, dtype=float)
     mask = np.isfinite(data)
-    return np.all(data[mask].flatten() <= 64)
+    return bool(np.all(data[mask].flatten() <= 64))
 
 
 def rename_sample_columns(table: pd.DataFrame, mapping: dict[str, str]) -> pd.DataFrame:
@@ -102,7 +102,7 @@ def rename_sample_columns(table: pd.DataFrame, mapping: dict[str, str]) -> pd.Da
 
 
 def rename_mq_reporter_channels(
-    table: pd.DataFrame, channel_names: Iterable[str]
+    table: pd.DataFrame, channel_names: Sequence[str]
 ) -> None:
     """Renames reporter channel numbers with sample names.
 
@@ -157,8 +157,7 @@ def find_columns(
     Returns:
         A list of column names.
     """
-    matches = [substring in col for col in table.columns]
-    matched_columns = np.array(table.columns)[matches].tolist()
+    matched_columns = [col for col in table.columns if substring in col]
     if must_be_substring:
         matched_columns = [col for col in matched_columns if col != substring]
     return matched_columns
@@ -255,7 +254,7 @@ def remove_rows_by_partial_match(
 
 
 def join_tables(
-    tables: Iterable[pd.DataFrame], reset_index: bool = False
+    tables: Sequence[pd.DataFrame], reset_index: bool = False
 ) -> pd.DataFrame:
     """Returns a joined dataframe.
 

{msreport-0.0.27 → msreport-0.0.28}/msreport/impute.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
-from typing import Optional, Any
+
+from typing import Any, Optional
 
 import numpy as np
 import pandas as pd
@@ -51,7 +52,7 @@ class FixedValueImputer:
             Returns the fitted FixedValueImputer instance.
         """
         if self.strategy == "constant":
-            fill_values = {column: self.fill_value for column in table.columns}
+            fill_values = dict.fromkeys(table.columns, self.fill_value)
         elif self.strategy == "below":
             if self.column_wise:
                 fill_values = {}
@@ -59,7 +60,7 @@ class FixedValueImputer:
                     fill_values[column] = _calculate_integer_below_min(table[column])
             else:
                 int_below_min = _calculate_integer_below_min(table)
-                fill_values = {column: int_below_min for column in table.columns}
+                fill_values = dict.fromkeys(table.columns, int_below_min)
         self._sample_fill_values = fill_values
         return self