quantms-utils 0.0.2__tar.gz → 0.0.4__tar.gz

{quantms_utils-0.0.2/quantms_utils.egg-info → quantms_utils-0.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: quantms-utils
-Version: 0.0.2
+Version: 0.0.4
 Summary: Python package with scripts and helpers for the QuantMS workflow
 Home-page: https://www.github.com/bigbio/pyquantms
 Author: Yasset Perez-Riverol, Dai Chengxin
@@ -20,13 +20,21 @@ Requires-Python: >=3.8,<4
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: click
-Requires-Dist: sdrf-pipelines
+Requires-Dist: sdrf-pipelines>=0.0.29
 Requires-Dist: pyopenms
-Requires-Dist: ms2rescore==3.0.2
-Requires-Dist: psm-utils==0.8.0
+Requires-Dist: ms2rescore==3.0.3
+Requires-Dist: deeplc==2.2.27
+Requires-Dist: ms2pip==4.0.0.dev8
+Requires-Dist: psm-utils==0.8.2
+Requires-Dist: deeplcretrainer==0.2.11
 Requires-Dist: pydantic
 Requires-Dist: pandas
+Requires-Dist: protobuf<4,>=3.9.2
 Requires-Dist: numpy
+Requires-Dist: pyarrow
+Requires-Dist: pygam
+Requires-Dist: scipy
+Requires-Dist: scikit-learn
 
 # quantms-utils
 [![Python application](https://github.com/bigbio/quantms-utils/actions/workflows/python-app.yml/badge.svg)](https://github.com/bigbio/quantms-utils/actions/workflows/python-app.yml)

{quantms_utils-0.0.2 → quantms_utils-0.0.4/quantms_utils.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: quantms-utils
-Version: 0.0.2
+Version: 0.0.4
 Summary: Python package with scripts and helpers for the QuantMS workflow
 Home-page: https://www.github.com/bigbio/pyquantms
 Author: Yasset Perez-Riverol, Dai Chengxin
@@ -20,13 +20,21 @@ Requires-Python: >=3.8,<4
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: click
-Requires-Dist: sdrf-pipelines
+Requires-Dist: sdrf-pipelines>=0.0.29
 Requires-Dist: pyopenms
-Requires-Dist: ms2rescore==3.0.2
-Requires-Dist: psm-utils==0.8.0
+Requires-Dist: ms2rescore==3.0.3
+Requires-Dist: deeplc==2.2.27
+Requires-Dist: ms2pip==4.0.0.dev8
+Requires-Dist: psm-utils==0.8.2
+Requires-Dist: deeplcretrainer==0.2.11
 Requires-Dist: pydantic
 Requires-Dist: pandas
+Requires-Dist: protobuf<4,>=3.9.2
 Requires-Dist: numpy
+Requires-Dist: pyarrow
+Requires-Dist: pygam
+Requires-Dist: scipy
+Requires-Dist: scikit-learn
 
 # quantms-utils
 [![Python application](https://github.com/bigbio/quantms-utils/actions/workflows/python-app.yml/badge.svg)](https://github.com/bigbio/quantms-utils/actions/workflows/python-app.yml)

quantms_utils-0.0.4/quantms_utils.egg-info/requires.txt

@@ -0,0 +1,16 @@
+click
+sdrf-pipelines>=0.0.29
+pyopenms
+ms2rescore==3.0.3
+deeplc==2.2.27
+ms2pip==4.0.0.dev8
+psm-utils==0.8.2
+deeplcretrainer==0.2.11
+pydantic
+pandas
+protobuf<4,>=3.9.2
+numpy
+pyarrow
+pygam
+scipy
+scikit-learn

quantms_utils-0.0.4/quantmsutils/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.4"

{quantms_utils-0.0.2 → quantms_utils-0.0.4}/quantmsutils/diann/diann2mztab.py

@@ -11,7 +11,7 @@ import os
 import re
 import warnings
 from pathlib import Path
-from typing import Any, List, Tuple, Dict, Set, Union
+from typing import Any, Dict, List, Set, Tuple, Union
 
 import click
 import numpy as np
@@ -44,14 +44,14 @@ logger = logging.getLogger(__name__)
 @click.option("--qvalue_threshold", "-q", type=float)
 @click.pass_context
 def diann2mztab(
-        ctx,
-        folder,
-        exp_design,
-        dia_params,
-        diann_version,
-        charge,
-        missed_cleavages,
-        qvalue_threshold,
+    ctx,
+    folder,
+    exp_design,
+    dia_params,
+    diann_version,
+    charge,
+    missed_cleavages,
+    qvalue_threshold,
 ):
     """
     Convert DIA-NN output to MSstats, Triqler or mzTab.
@@ -228,7 +228,7 @@ def get_exp_design_dfs(exp_design_file):
             lambda x: _true_stem(x["Spectra_Filepath"]), axis=1
         )
 
-        s_table = [i.replace("\n", "").split("\t") for i in data[empty_row + 1:]][1:]
+        s_table = [i.replace("\n", "").split("\t") for i in data[empty_row + 1 :]][1:]
         s_header = data[empty_row + 1].replace("\n", "").split("\t")
         s_data_frame = pd.DataFrame(s_table, columns=s_header)
 
@@ -265,31 +265,31 @@ def compute_mass_modified_peptide(peptide_seq: str) -> float:
         if aa in aa_mass and not_mod:
             aa = aa_mass[aa]
         elif (
-                aa
-                not in [
-                    "G",
-                    "A",
-                    "V",
-                    "L",
-                    "I",
-                    "F",
-                    "M",
-                    "P",
-                    "W",
-                    "S",
-                    "C",
-                    "T",
-                    "Y",
-                    "N",
-                    "Q",
-                    "D",
-                    "E",
-                    "K",
-                    "R",
-                    "H",
-                ]
-                and not_mod
-                and aa != ")"
+            aa
+            not in [
+                "G",
+                "A",
+                "V",
+                "L",
+                "I",
+                "F",
+                "M",
+                "P",
+                "W",
+                "S",
+                "C",
+                "T",
+                "Y",
+                "N",
+                "Q",
+                "D",
+                "E",
+                "K",
+                "R",
+                "H",
+            ]
+            and not_mod
+            and aa != ")"
         ):
             logger.info(f"Unknown amino acid with mass not known:{aa}")
         peptide_parts.append(aa)
@@ -362,18 +362,18 @@ class DiannDirectory:
         return diann_version_id
 
     def validate_diann_version(self) -> None:
-        supported_diann_versions = ["1.8.1"]
+        supported_diann_versions = ["1.8.1", "1.9.beta.1"]
         if self.diann_version not in supported_diann_versions:
             raise ValueError(f"Unsupported DIANN version {self.diann_version}")
 
     def convert_to_mztab(
-            self,
-            report,
-            f_table,
-            charge: int,
-            missed_cleavages: int,
-            dia_params: List[Any],
-            out: Union[os.PathLike, str],
+        self,
+        report,
+        f_table,
+        charge: int,
+        missed_cleavages: int,
+        dia_params: List[Any],
+        out: Union[os.PathLike, str],
     ) -> None:
         logger.info("Converting to mzTab")
         self.validate_diann_version()
@@ -481,8 +481,8 @@ class DiannDirectory:
         }
         mass_vector = report["Modified.Sequence"].map(uniq_masses)
         report["Calculate.Precursor.Mz"] = (
-                                                   mass_vector + (PROTON_MASS_U * report["Precursor.Charge"])
-                                           ) / report["Precursor.Charge"]
+            mass_vector + (PROTON_MASS_U * report["Precursor.Charge"])
+        ) / report["Precursor.Charge"]
 
         logger.debug("Indexing Precursors")
         # Making the map is 1500x faster
@@ -589,16 +589,16 @@ def mztab_mtd(index_ref, dia_params, fasta, charge, missed_cleavages):
     out_mztab_mtd.loc[1, "software[1]-setting[1]"] = fasta
     out_mztab_mtd.loc[1, "software[1]-setting[2]"] = "db_version:null"
     out_mztab_mtd.loc[1, "software[1]-setting[3]"] = (
-            "fragment_mass_tolerance:" + fragment_mass_tolerance
+        "fragment_mass_tolerance:" + fragment_mass_tolerance
     )
     out_mztab_mtd.loc[1, "software[1]-setting[4]"] = (
-            "fragment_mass_tolerance_unit:" + fragment_mass_tolerance_unit
+        "fragment_mass_tolerance_unit:" + fragment_mass_tolerance_unit
     )
     out_mztab_mtd.loc[1, "software[1]-setting[5]"] = (
-            "precursor_mass_tolerance:" + precursor_mass_tolerance
+        "precursor_mass_tolerance:" + precursor_mass_tolerance
     )
     out_mztab_mtd.loc[1, "software[1]-setting[6]"] = (
-            "precursor_mass_tolerance_unit:" + precursor_mass_tolerance_unit
+        "precursor_mass_tolerance_unit:" + precursor_mass_tolerance_unit
     )
     out_mztab_mtd.loc[1, "software[1]-setting[7]"] = "enzyme:" + enzyme
     out_mztab_mtd.loc[1, "software[1]-setting[8]"] = "enzyme_term_specificity:full"
@@ -607,10 +607,10 @@ def mztab_mtd(index_ref, dia_params, fasta, charge, missed_cleavages):
         missed_cleavages
     )
     out_mztab_mtd.loc[1, "software[1]-setting[11]"] = (
-            "fixed_modifications:" + fixed_modifications
+        "fixed_modifications:" + fixed_modifications
     )
     out_mztab_mtd.loc[1, "software[1]-setting[12]"] = (
-            "variable_modifications:" + variable_modifications
+        "variable_modifications:" + variable_modifications
     )
 
     (fixed_mods, variable_mods, fix_flag, var_flag) = mtd_mod_info(
@@ -633,7 +633,7 @@ def mztab_mtd(index_ref, dia_params, fasta, charge, missed_cleavages):
             ]
             out_mztab_mtd.loc[1, "variable_mod[" + str(i) + "]-site"] = variable_mods[
                 i - 1
-                ][1]
+            ][1]
             out_mztab_mtd.loc[1, "variable_mod[" + str(i) + "]-position"] = "Anywhere"
     else:
         out_mztab_mtd.loc[1, "variable_mod[1]"] = variable_mods[0]
@@ -649,8 +649,8 @@ def mztab_mtd(index_ref, dia_params, fasta, charge, missed_cleavages):
             "[MS, MS:1000584, mzML file, ]"
         )
         out_mztab_mtd.loc[1, "ms_run[" + str(i) + "]-location"] = (
-                "file://"
-                + index_ref[index_ref["ms_run"] == i]["Spectra_Filepath"].values[0]
+            "file://"
+            + index_ref[index_ref["ms_run"] == i]["Spectra_Filepath"].values[0]
         )
         out_mztab_mtd.loc[1, "ms_run[" + str(i) + "]-id_format"] = (
             "[MS, MS:1000777, spectrum identifier nativeID format, ]"
@@ -659,7 +659,7 @@ def mztab_mtd(index_ref, dia_params, fasta, charge, missed_cleavages):
             "[MS, MS:1002038, unlabeled sample, ]"
         )
         out_mztab_mtd.loc[1, "assay[" + str(i) + "]-ms_run_ref"] = (
-                "ms_run[" + str(i) + "]"
+            "ms_run[" + str(i) + "]"
         )
 
     with warnings.catch_warnings():
@@ -723,16 +723,16 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
     col = {}
     for i in file:
         col[i] = (
-                "protein_abundance_assay["
-                + str(index_ref[index_ref["Run"] == _true_stem(i)]["ms_run"].values[0])
-                + "]"
+            "protein_abundance_assay["
+            + str(index_ref[index_ref["Run"] == _true_stem(i)]["ms_run"].values[0])
+            + "]"
         )
 
     pg.rename(columns=col, inplace=True)
 
     logger.debug("Classifying results type ...")
     pg["opt_global_result_type"] = "single_protein"
-    pg.loc[pg["Protein.Ids"].str.contains(";"), "opt_global_result_type"] = (
+    pg.loc[pg["Protein.Group"].str.contains(";"), "opt_global_result_type"] = (
         "indistinguishable_protein_group"
     )
 
@@ -741,7 +741,6 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
     out_mztab_prh = out_mztab_prh.drop(["Protein.Names"], axis=1)
     out_mztab_prh.rename(
         columns={
-            "Protein.Group": "accession",
             "First.Protein.Description": "description",
         },
         inplace=True,
@@ -762,14 +761,14 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
 
     logger.debug("Extracting accession values (keeping first)...")
     out_mztab_prh.loc[:, "accession"] = out_mztab_prh.apply(
-        lambda x: x["accession"].split(";")[0], axis=1
+        lambda x: x["Protein.Group"].split(";")[0], axis=1
     )
 
     protein_details_df = out_mztab_prh[
         out_mztab_prh["opt_global_result_type"] == "indistinguishable_protein_group"
-        ]
+    ]
     prh_series = (
-        protein_details_df["Protein.Ids"]
+        protein_details_df["Protein.Group"]
         .str.split(";", expand=True)
         .stack()
         .reset_index(level=1, drop=True)
@@ -806,7 +805,7 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
     # or out_mztab_PRH.loc[out_mztab_PRH["Protein.Ids"] == out_mztab_PRH["accession"], "ambiguity_members"] = "null"
     out_mztab_prh.loc[:, "ambiguity_members"] = out_mztab_prh.apply(
         lambda x: (
-            x["Protein.Ids"]
+            x["Protein.Group"]
             if x["opt_global_result_type"] == "indistinguishable_protein_group"
             else "null"
         ),
@@ -817,7 +816,7 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
     score_looker = ModScoreLooker(report)
     out_mztab_prh[["modifiedSequence", "best_search_engine_score[1]"]] = (
         out_mztab_prh.apply(
-            lambda x: score_looker.get_score(x["Protein.Ids"]),
+            lambda x: score_looker.get_score(x["Protein.Group"]),
             axis=1,
             result_type="expand",
         )
@@ -833,11 +832,11 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
     # This used to be a bottleneck in performance
     # This implementation drops the run time from 57s to 25ms
     protein_agg_report = (
-        report[["PG.MaxLFQ", "Protein.Ids", "study_variable"]]
-        .groupby(["study_variable", "Protein.Ids"])
+        report[["PG.MaxLFQ", "Protein.Group", "study_variable"]]
+        .groupby(["study_variable", "Protein.Group"])
         .agg({"PG.MaxLFQ": ["mean", "std", "sem"]})
         .reset_index()
-        .pivot(columns=["study_variable"], index="Protein.Ids")
+        .pivot(columns=["study_variable"], index="Protein.Group")
         .reset_index()
     )
     protein_agg_report.columns = [
@@ -845,7 +844,7 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
         for col in protein_agg_report.columns.values
     ]
     subname_mapper = {
-        "Protein.Ids::::": "Protein.Ids",
+        "Protein.Group::::": "Protein.Group",
         "PG.MaxLFQ::mean": "protein_abundance_study_variable",
         "PG.MaxLFQ::std": "protein_abundance_stdev_study_variable",
         "PG.MaxLFQ::sem": "protein_abundance_std_error_study_variable",
@@ -858,7 +857,7 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
     # to the Protein.Ids (A0A024RBG1;Q9NZJ9;Q9NZJ9-2), leading to A LOT of missing values.
     out_mztab_prh = out_mztab_prh.merge(
         protein_agg_report,
-        on="Protein.Ids",
+        on="Protein.Group",
         how="left",
         validate="many_to_one",
         copy=True,
@@ -871,7 +870,7 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
     out_mztab_prh.loc[:, "PRH"] = "PRT"
     index = out_mztab_prh.loc[:, "PRH"]
     out_mztab_prh.drop(
-        ["PRH", "Genes", "modifiedSequence", "Protein.Ids"], axis=1, inplace=True
+        ["PRH", "Genes", "modifiedSequence", "Protein.Group"], axis=1, inplace=True
     )
     out_mztab_prh.insert(0, "PRH", index)
     out_mztab_prh.fillna("null", inplace=True)
@@ -884,11 +883,11 @@ def mztab_prh(report, pg, index_ref, database, fasta_df):
 
 
 def mztab_peh(
-        report: pd.DataFrame,
-        pr: pd.DataFrame,
-        precursor_list: List[str],
-        index_ref: pd.DataFrame,
-        database: os.PathLike,
+    report: pd.DataFrame,
+    pr: pd.DataFrame,
+    precursor_list: List[str],
+    index_ref: pd.DataFrame,
+    database: os.PathLike,
 ) -> pd.DataFrame:
     """
     Construct PEH sub-table.
@@ -916,14 +915,14 @@ def mztab_peh(
     out_mztab_peh = pd.DataFrame()
     out_mztab_peh = pr.iloc[:, 0:10]
     out_mztab_peh.drop(
-        ["Protein.Group", "Protein.Names", "First.Protein.Description", "Proteotypic"],
+        ["Protein.Ids", "Protein.Names", "First.Protein.Description", "Proteotypic"],
         axis=1,
         inplace=True,
     )
     out_mztab_peh.rename(
         columns={
             "Stripped.Sequence": "sequence",
-            "Protein.Ids": "accession",
+            "Protein.Group": "accession",
             "Modified.Sequence": "opt_global_cv_MS:1000889_peptidoform_sequence",
             "Precursor.Charge": "charge",
         },
@@ -1106,8 +1105,8 @@ def mztab_psh(report, folder, database):
         # Standardize spectrum identifier format for bruker data
         if not isinstance(target.loc[0, "opt_global_spectrum_reference"], str):
             target.loc[:, "opt_global_spectrum_reference"] = "scan=" + target.loc[
-                                                                       :, "opt_global_spectrum_reference"
-                                                                       ].astype(str)
+                :, "opt_global_spectrum_reference"
+            ].astype(str)
 
         # TODO seconds returned from precursor.getRT()
         target.loc[:, "RT.Start"] = target.apply(lambda x: x["RT.Start"] / 60, axis=1)
@@ -1123,7 +1122,7 @@ def mztab_psh(report, folder, database):
     out_mztab_psh = out_mztab_psh[
         [
             "Stripped.Sequence",
-            "Protein.Ids",
+            "Protein.Group",
             "Q.Value",
             "RT.Start",
             "Precursor.Charge",
@@ -1184,7 +1183,7 @@ def mztab_psh(report, folder, database):
 
     out_mztab_psh.loc[:, "spectra_ref"] = out_mztab_psh.apply(
         lambda x: "ms_run[{}]:".format(x["ms_run"])
-                  + x["opt_global_spectrum_reference"],
+        + x["opt_global_spectrum_reference"],
         axis=1,
         result_type="expand",
     )
@@ -1239,7 +1238,7 @@ def classify_result_type(target):
     :return: A string implys protein type
     :rtype: str
     """
-    if ";" in target["Protein.Ids"]:
+    if ";" in target["Protein.Group"]:
         return "indistinguishable_protein_group"
     return "single_protein"
 
@@ -1293,7 +1292,7 @@ def match_in_report(report, target, max_, flag, level):
         return tuple(q_value)
 
     if flag == 1 and level == "protein":
-        result = report[report["Protein.Ids"] == target]
+        result = report[report["Protein.Group"] == target]
         prh_params = []
         for i in range(1, max_ + 1):
             match = result[result["study_variable"] == i]
@@ -1320,9 +1319,9 @@ class ModScoreLooker:
 
     def make_lookup_dict(self, report) -> Dict[str, Tuple[str, float]]:
         grouped_df = (
-            report[["Modified.Sequence", "Protein.Ids", "Global.PG.Q.Value"]]
+            report[["Modified.Sequence", "Protein.Group", "Global.PG.Q.Value"]]
             .sort_values("Global.PG.Q.Value", ascending=True)
-            .groupby(["Protein.Ids"])
+            .groupby(["Protein.Group"])
             .head(1)
         )
         #        Modified.Sequence               Protein.Ids  Global.PG.Q.Value
@@ -1332,7 +1331,7 @@ class ModScoreLooker:
         # 103588      NPVGYPLAWQFLR           Q9NZ08;Q9NZ08-2           0.000252
 
         out = {
-            row["Protein.Ids"]: (row["Modified.Sequence"], row["Global.PG.Q.Value"])
+            row["Protein.Group"]: (row["Modified.Sequence"], row["Global.PG.Q.Value"])
             for _, row in grouped_df.iterrows()
         }
         return out
@@ -1556,8 +1555,8 @@ def calculate_coverage(ref_sequence: str, sequences: Set[str]):
     for start, length in sorted(zip(starts, lengths)):
         if merged_starts and merged_starts[-1] + merged_lengths[-1] >= start:
             merged_lengths[-1] = (
-                    max(merged_starts[-1] + merged_lengths[-1], start + length)
-                    - merged_starts[-1]
+                max(merged_starts[-1] + merged_lengths[-1], start + length)
+                - merged_starts[-1]
             )
         else:
             merged_starts.append(start)
@@ -1569,7 +1568,7 @@ def calculate_coverage(ref_sequence: str, sequences: Set[str]):
 
 
 def calculate_protein_coverages(
-        report: pd.DataFrame, out_mztab_prh: pd.DataFrame, fasta_df: pd.DataFrame
+    report: pd.DataFrame, out_mztab_prh: pd.DataFrame, fasta_df: pd.DataFrame
 ) -> List[str]:
     """Calculates protein coverages for the PRH table.
 
@@ -1578,8 +1577,8 @@ def calculate_protein_coverages(
     protein in the PRH table (defined by accession, not protein.ids).
     """
     nested_df = (
-        report[["Protein.Ids", "Stripped.Sequence"]]
-        .groupby("Protein.Ids")
+        report[["Protein.Group", "Stripped.Sequence"]]
+        .groupby("Protein.Group")
         .agg({"Stripped.Sequence": set})
         .reset_index()
     )
@@ -1587,8 +1586,8 @@ def calculate_protein_coverages(
     # 0     A0A024RBG1;Q9NZJ9;Q9NZJ9-2                                   {SEQEDEVLLVSSSR}
     # 1        A0A096LP49;A0A096LP49-2                                  {SPWAMTERKHSSLER}
     # 2                A0AVT1;A0AVT1-2  {EDFTLLDFINAVK, KPDHVPISSEDER, QDVIITALDNVEAR,...
-    ids_to_seqs = dict(zip(nested_df["Protein.Ids"], nested_df["Stripped.Sequence"]))
-    acc_to_ids = dict(zip(out_mztab_prh["accession"], out_mztab_prh["Protein.Ids"]))
+    ids_to_seqs = dict(zip(nested_df["Protein.Group"], nested_df["Stripped.Sequence"]))
+    acc_to_ids = dict(zip(out_mztab_prh["accession"], out_mztab_prh["Protein.Group"]))
     fasta_id_to_seqs = dict(zip(fasta_df["id"], fasta_df["seq"]))
     acc_to_fasta_ids: dict = {}
 

{quantms_utils-0.0.2 → quantms_utils-0.0.4}/quantmsutils/mzml/mzml_statistics.py

@@ -1,9 +1,10 @@
-from pathlib import Path
-import sqlite3
 import re
+import sqlite3
+from pathlib import Path
 
 import click
 import pandas as pd
+import pyarrow
 from pyopenms import MSExperiment, MzMLFile
 
 
@@ -41,6 +42,14 @@ def mzml_statistics(ctx, ms_path: str, id_only: bool = False) -> None:
     ]
 
     def parse_mzml(file_name: str, file_columns: list, id_only: bool = False):
+        """
+        Parse mzML file and return a pandas DataFrame with the information. If id_only is True, it will also save a csv.
+        @param file_name: The file name of the mzML file
+        @param file_columns: The columns of the DataFrame
+        @param id_only: If True, it will save a csv with the spectrum id, mz and intensity
+        @return: A pandas DataFrame with the information of the mzML file
+        """
+
         info = []
         psm_part_info = []
         exp = MSExperiment()
@@ -123,11 +132,10 @@ def mzml_statistics(ctx, ms_path: str, id_only: bool = False) -> None:
         if id_only and len(psm_part_info) > 0:
             pd.DataFrame(
                 psm_part_info, columns=["scan", "ms_level", "mz", "intensity"]
-            ).to_csv(
-                f"{Path(ms_path).stem}_spectrum_df.csv",
-                mode="w",
+            ).to_parquet(
+                f"{Path(ms_path).stem}_spectrum_df.parquet",
                 index=False,
-                header=True,
+                compression="gzip",
             )
 
         return pd.DataFrame(info, columns=file_columns)
@@ -168,7 +176,7 @@ def mzml_statistics(ctx, ms_path: str, id_only: bool = False) -> None:
         except sqlite3.OperationalError as e:
             if "no such table: Precursors" in str(e):
                 print(
-                    f"No precursers recorded in {file_name}, This is normal for DIA data."
+                    f"No precursors recorded in {file_name}, This is normal for DIA data."
                 )
                 precursor_df = pd.DataFrame()
             else:
@@ -219,13 +227,12 @@ def mzml_statistics(ctx, ms_path: str, id_only: bool = False) -> None:
     elif Path(ms_path).suffix in [".mzML", ".mzml"]:
         ms_df = parse_mzml(ms_path, file_columns, id_only)
     else:
-        msg = f"Unrecognized or inexistent mass spec file '{ms_path}'"
+        msg = f"Unrecognized or the mass spec file '{ms_path}' do not exist"
         raise RuntimeError(msg)
 
-    ms_df.to_csv(
-        f"{Path(ms_path).stem}_ms_info.tsv",
-        mode="w",
-        sep="\t",
+    ms_df.to_parquet(
+        f"{Path(ms_path).stem}_ms_info.parquet",
+        engine="pyarrow",
         index=False,
-        header=True,
+        compression="gzip",
     )