Merge pull request #1 from tineclae/refactor-code

Refactor code

Author: TineClaeys

.gitignore

@@ -0,0 +1,6 @@
+*.pkl
+./Projects/Arnaud/*
+*.csv
+Projects/SCP_slavov/2024_Khan_testis/npop5_DIANN_report.tsv
+Projects/Cell_lines/metadata.xlsx
+Projects/Cell_lines/data.xlsx

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

MANIFEST.in

@@ -0,0 +1,15 @@
+include README.md
+include requirements.txt
+include LICENSE
+include mlmarker
+include tests
+
+exclude features.txt
+exclude setup.py
+exclude test_notebook.ipynb
+exclude Tissue_predictors2_fulldata.ipynb
+exclude MLMarker_Arnaud_quant.py
+
+prune data
+prune old_modules
+prune Projects

MLMarker_Arnaud_quant.py

@@ -0,0 +1,139 @@
+import logging
+import glob
+import pandas as pd
+import numpy as np
+import os
+import re
+import warnings
+# Filter out the specific warning message
+warnings.filterwarnings("ignore", message="A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.")
+from MLMarker_app import MLMarker
+import pymongo
+import sys
+
+
+logging.FileHandler('MLMarker.log') #Create a log file
+logging.basicConfig(level=logging.DEBUG, handlers=[logging.FileHandler('MLMarker.log')])
+
+
+def extract_pxd(file_path):
+    match = re.search(r'PXD.*?/(?<!zip/)', file_path) # Pattern that starts with PXD and ends with / but not with zip/
+    if match:
+        return match.group(0)[:-1]
+    else:
+        return None
+
+
+def extract_filename(file_path):
+    match = re.search(r'/(?!PXD).*?/', file_path) # Pattern that starts with / and everything else other than PXD and ends with /
+    if match:
+        return match.group(0)[1:-1]
+    else:
+        return None
+
+
+    
+def ionbot_first_to_prot_list(df):
+        """Only search in the rows : q-value <= 0.01, database = T, proteins != CONTAMINANT and '|'  
+        Return a list of uniprot id"""
+        df = df[['proteins', 'database', 'q-value']]
+        df = df[(df['database']=='T') & (df['q-value']<=0.01)]
+        df = df[~df['proteins'].apply(lambda x: '|' in x or 'CONTAMINANT' in x)]
+        uniprot_df = df['proteins'].apply(lambda uniprot: re.search(r'\)\)\(\((.*?)\)\)', uniprot).group(1) 
+                                          if re.search(r'\)\)\(\((.*?)\)\)', uniprot) else None) # Found the uniprot id with a ))((.*)) pattern
+        uniprot_df = uniprot_df.dropna() #Maybe not necessary 
+        list_uniprot = (list(set(uniprot_df)))
+        return list_uniprot
+
+
+def csv_path(path_file):   
+    """Return a dictionnary with the path of the csv files"""
+    for result_dir in glob.iglob(path_file, recursive=True): #Recursive search of the zip files in the folder
+        pxd = os.path.basename(os.path.split(result_dir)[0])
+        for run_dir in os.listdir(result_dir):
+            if run_dir.endswith('.mgf.gzip'): #Check if the file is a mgf.gz file
+                result_file = os.path.join(result_dir, run_dir, "ionbot.first.csv")
+                if os.path.exists(result_file):
+                    yield pxd, run_dir, result_file
+
+
+def MLMarker_Arnaud_quant(prot_list):
+    data = np.ones((1, len(prot_list)))
+    predict_df = pd.DataFrame(data, columns=prot_list)
+    test = MLMarker(predict_df.iloc[0:1,:], binary = True)
+    prediction = MLMarker.adjusted_shap_values_df(test, penalty_factor=0.5, n_preds=100)
+    prediction = prediction.sum(axis=1).sort_values(ascending=False)
+    df_predi = pd.DataFrame(prediction).transpose()
+    return df_predi
+
+
+def MLMarker_to_Dataframe(dico, lengths):
+    """Return a dataframe with the data of the mgf.gz files after the MLMarker analysis"""
+
+    df_big = pd.DataFrame()
+    processed = set()
+    for pxd, mgf_file, result_file in dico:
+        if (pxd, mgf_file) in processed:
+            logging.error(f'Duplicate in {pxd}/{mgf_file}')
+            continue
+        processed.add((pxd, mgf_file))
+
+        try:
+            with open(result_file) as f: 
+                df_first = pd.read_csv(f)
+                prot_list = ionbot_first_to_prot_quant(df_first, lengths)
+
+            df_temp = MLMarker_Arnaud_quant(prot_list)
+            df_temp['PXD_folder'] = pxd
+            df_temp['filename'] = mgf_file
+
+            df_big = pd.concat([df_big, df_temp])
+
+        except Exception as e: #Not sure if this is the best way to handle errors
+            logging.exception(f'Error in {pxd}/{mgf_file}')
+
+    return df_big
+
+
+def get_human_projects(mongo_uri):
+    db = pymongo.MongoClient(mongo_uri).pipeline
+    human_projects = {obj["accession"] for obj in db.metadata.find({"species": {"$in": ["Homo sapiens (Human)", "Homo sapiens (human)"]}})}
+    modified_projects = {obj["accession"] for obj in db.file_registry.find({"modifications.ionbot_name": {"$exists": True}})}
+    return human_projects.intersection(modified_projects)
+
+    
+def ionbot_first_to_prot_quant(df, lengths):
+        """Only search in the rows : q-value <= 0.01, database = T, proteins != CONTAMINANT and '|'  
+        Return a list of uniprot id"""
+        
+        df = df[['proteins', 'database', 'q-value']]
+        df = df[(df['database']=='T') & (df['q-value']<=0.01)]
+        df = df[~df['proteins'].apply(lambda x: '|' in x or 'CONTAMINANT' in x)]
+        uniprot_df = df['proteins'].apply(lambda uniprot: re.search(r'\)\)\(\((.*?)\)\)', uniprot).group(1) 
+                                          if re.search(r'\)\)\(\((.*?)\)\)', uniprot) else None) # Found the uniprot id with a ))((.*)) pattern
+        uniprot_df = uniprot_df.value_counts().to_frame().reset_index()
+        uniprot_df = uniprot_df.merge(lengths, left_on='proteins', right_on='Entry')
+        uniprot_df = uniprot_df[uniprot_df['Length'] != np.nan]
+        uniprot_df['count'] = uniprot_df['count'].astype(float)
+        uniprot_df['Length'] = uniprot_df['Length'].astype(float)
+        uniprot_df['SAF'] = uniprot_df['count']/uniprot_df['Length']
+        total_SAF = uniprot_df['SAF'].sum()
+        uniprot_df['NSAF'] = uniprot_df['SAF']/total_SAF
+        return uniprot_df
+
+def MLMarker_Arnaud_quant(prot_list):
+    data = uniprot_df.pivot_table(columns='proteins', values='NSAF', aggfunc='sum')
+    data = data.fillna(0)
+    test = MLMarker(data.iloc[0:1, :], binary=False)
+    prediction = MLMarker.adjusted_shap_values_df(test, penalty_factor=0.5, n_preds=100)
+    prediction = prediction.sum(axis=1).sort_values(ascending=False)
+    df_predi = pd.DataFrame(prediction).transpose()
+    return df_predi
+
+
+if __name__ == "__main__":
+    for pxd in get_human_projects(sys.argv[1]):
+        result_files = csv_path(f"/public/conode*/PRIDE_DATA/{pxd}/IONBOT_v0.11.3")
+        lengths = pd.read_csv('./uniprot_reviewed_lengths.tsv', sep='/t')
+        df = MLMarker_to_Dataframe(result_files, lengths)
+        df.to_csv(os.path.join(os.path.join(sys.argv[2], f"{pxd}.csv")), header=True, index=False)