Static folder location update

.gitignore

@@ -1,6 +1,13 @@
 app/tools
-app/static/images/*
+app/static/images
 app/__pycache__/*
 __pycache__/
 immunolyser-data/*
-lenv/*
+lenv/*
+results.sqlite
+.vscode/launch.json
+test.py
+data_files/*
+data_files_2/*
+tools/*
+test.ipynb

Dockerfile

@@ -0,0 +1,179 @@
+FROM python:3.12-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install build tools, R, tcsh, and other required dependencies
+RUN apt-get update && apt-get install -y \
+    git \
+    tar \
+    build-essential \
+    wget \
+    libssl-dev \
+    libbz2-dev \
+    libreadline-dev \
+    libsqlite3-dev \
+    zlib1g-dev \
+    r-base \
+    man-db \
+    ncompress \
+    tcsh \
+    && \
+    wget https://github.com/ArtifexSoftware/ghostpdl-downloads/releases/download/gs926/ghostscript-9.26.tar.gz && \
+    tar -xzf ghostscript-9.26.tar.gz && \
+    cd ghostscript-9.26 && \
+    ./configure && make && make install && \
+    pip3 install --no-cache-dir gdown && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# Clone the repository
+RUN git clone https://github.com/prmunday/Immunolyser /app/Immunolyser
+
+# Change to the repository directory
+WORKDIR /app/Immunolyser
+
+# Checkout the develop branch
+RUN git fetch origin develop && \
+    git checkout develop && \
+    git pull
+
+# Copy the seq2logo tar.gz file from the local tools folder to the container
+COPY /tools/seq2logo-2.1.all.tar.gz /app/Immunolyser/app/tools/
+
+# Create a tools directory and extract the tar.gz file there
+RUN mkdir -p /app/Immunolyser/app/tools && \
+    tar -xzf /app/Immunolyser/app/tools/seq2logo-2.1.all.tar.gz -C /app/Immunolyser/app/tools && \
+    rm /app/Immunolyser/app/tools/seq2logo-2.1.all.tar.gz
+
+# Copy the gibbscluster tar.gz file to the container
+COPY /tools/gibbscluster-2.0f.Linux.tar.gz /app/Immunolyser/app/tools/
+
+# Extract gibbscluster tar.gz
+RUN mkdir -p /app/Immunolyser/app/tools && \
+    tar -xvf /app/Immunolyser/app/tools/gibbscluster-2.0f.Linux.tar.gz -C /app/Immunolyser/app/tools && \
+    rm /app/Immunolyser/app/tools/gibbscluster-2.0f.Linux.tar.gz
+
+# Update GIBBS path in the gibbscluster file
+RUN sed -i 's|setenv\s*GIBBS .*|setenv GIBBS /app/Immunolyser/app/tools/gibbscluster-2.0|' /app/Immunolyser/app/tools/gibbscluster-2.0/gibbscluster
+
+# Comment out the line containing '$resdir .= "/$prefix";' in GibbsCluster-2.0e_SA.pl; command update for seq2logo and gibbs
+RUN sed -i \
+    -e 's|^\(\s*\$resdir .= "/\$prefix";\)|# \1  # Comment or remove this line|' \
+    -e 's|^\(my \$barplot = "\$resdir/images/\$prefix.gibbs.KLDvsCluster.barplot.png";\)|my \$barplot = "\$resdir/images/gibbsKLDvsCluster.barplot.JPG";|' \
+    -e '530s@.*@$cmd .= "$seq2logo -f $corefile -o $logofile -I 2 --format [JPEG] -b $wlc -C 2 -S 2 -t $title \&>/dev/null; ";@' \
+    /app/Immunolyser/app/tools/gibbscluster-2.0/GibbsCluster-2.0e_SA.pl
+
+# Copy the netMHCpan tar.gz file to the container
+COPY /tools/netMHCpan-4.2b.Linux.tar.gz /app/Immunolyser/app/tools/
+
+# Uncompress and untar the netMHCpan package
+RUN mkdir -p /app/Immunolyser/app/tools && \
+    cat /app/Immunolyser/app/tools/netMHCpan-4.2b.Linux.tar.gz | gunzip | tar xvf - -C /app/Immunolyser/app/tools && \
+    rm /app/Immunolyser/app/tools/netMHCpan-4.2b.Linux.tar.gz && \
+    mkdir -p /app/Immunolyser/app/tools/netMHCpan-4.2/tmp
+
+# Copy the netMHCIIpan tar.gz file to the container
+COPY /tools/netMHCIIpan-4.3i.Linux.tar.gz /app/Immunolyser/app/tools/
+
+# Uncompress and untar the netMHCIIpan package
+RUN mkdir -p /app/Immunolyser/app/tools && \
+    tar -xvf /app/Immunolyser/app/tools/netMHCIIpan-4.3i.Linux.tar.gz -C /app/Immunolyser/app/tools && \
+    rm /app/Immunolyser/app/tools/netMHCIIpan-4.3i.Linux.tar.gz && \
+    man -d /app/Immunolyser/app/tools/netMHCIIpan-4.3/netMHCIIpan.1 | compress > /app/Immunolyser/app/tools/netMHCIIpan-4.3/netMHCIIpan.Z
+
+# Update netMHCIIpan configuration to use the correct NMHOME path
+RUN sed -i 's|setenv\s*NMHOME\s*/tools/src/netMHCIIpan-4.3|setenv NMHOME ${PWD}/app/tools/netMHCIIpan-4.3|' \
+    /app/Immunolyser/app/tools/netMHCIIpan-4.3/netMHCIIpan
+
+# Update netMHCpan configuration to use the correct NMHOME and TMPDIR paths
+RUN sed -i \
+    -e 's|setenv\s*NMHOME\s*/net/sund-nas.win.dtu.dk/storage/services/www/packages/netMHCpan/4.1/netMHCpan-4.2|setenv NMHOME ${PWD}/app/tools/netMHCpan-4.2|' \
+    -e 's|setenv\s*TMPDIR\s*/tmp|setenv TMPDIR $NMHOME/tmp|' \
+    /app/Immunolyser/app/tools/netMHCpan-4.2/netMHCpan
+
+# Clone MixMHCpred repository
+RUN git clone https://github.com/GfellerLab/MixMHCpred.git /app/Immunolyser/app/tools/MixMHCpred && \
+    chmod +x /app/Immunolyser/app/tools/MixMHCpred/MixMHCpred
+
+RUN wget https://github.com/GfellerLab/MixMHC2pred/releases/download/v2.0.2.2/MixMHC2pred-2.0.zip -P /app/Immunolyser/app/tools && \
+    unzip -o /app/Immunolyser/app/tools/MixMHC2pred-2.0.zip -d /app/Immunolyser/app/tools/MixMHC2pred-2.0 && \
+    rm /app/Immunolyser/app/tools/MixMHC2pred-2.0.zip
+
+# Download Alleles_list_Mouse.txt and put it in PWMdef directory
+RUN wget http://ec2-18-188-210-66.us-east-2.compute.amazonaws.com:4000/data/Alleles_lists/Alleles_list_Mouse.txt -P /app/Immunolyser/app/tools/MixMHC2pred-2.0/PWMdef
+
+# Clone MHC-TP and switch to netmhcpan-data-update-2025 branch
+RUN git clone https://github.com/PurcellLab/MHC-TP.git /app/Immunolyser/app/tools/MHC-TP && \
+    cd /app/Immunolyser/app/tools/MHC-TP && \
+    git fetch origin netmhcpan-data-update-2025 && \
+    git checkout netmhcpan-data-update-2025
+
+# Set up Python 3.11 virtual environment and install the package
+RUN cd /app/Immunolyser/app/tools/MHC-TP && \
+    python3 -m venv hlapepclust-env && \
+    /bin/bash -c "source hlapepclust-env/bin/activate && pip install -e . && deactivate"
+
+# Download the large ref_data zip file and unzip it
+RUN mkdir -p /app/Immunolyser/app/tools/MHC-TP/data/ref_data && \
+    cd /app/Immunolyser/app/tools/MHC-TP/data/ref_data && \
+    python3 -m gdown 'https://drive.google.com/uc?id=1iAAvir1woMOnURkP46zr_ETqpW2oUgGD' && \
+    unzip Gibbs_motifs_human.zip && \
+    rm Gibbs_motifs_human.zip
+
+# Install mhcflurry
+RUN pip install mhcflurry
+
+# Fetch mhcflurry downloads
+RUN mhcflurry-downloads fetch
+
+# Create a virtual environment for Python 3
+RUN python3 -m venv lenv
+
+# Install dependencies for Python 2 and Python 3
+RUN /bin/bash -c "source lenv/bin/activate && \
+    pip install -r requirements_python2.txt && \
+    pip install -r requirements_python3.txt"
+
+# Install Celery, sqlacheny
+RUN /bin/bash -c "pip install celery"
+RUN /bin/bash -c "pip install SQLAlchemy==2.0.31"
+
+# Run the hotfix script
+RUN /bin/bash -c "python hotfix_package_files.py"
+
+# Download and extract Python 2.7.18
+RUN wget https://www.python.org/ftp/python/2.7.18/Python-2.7.18.tgz && \
+    tar xvf Python-2.7.18.tgz
+
+# Build and install Python 2.7.18
+WORKDIR Python-2.7.18
+RUN ./configure && \
+    make && \
+    make install
+
+# Install pip for Python 2.7
+RUN wget https://bootstrap.pypa.io/pip/2.7/get-pip.py && \
+    python2 get-pip.py
+
+# Install numpy for Python 2.7
+RUN python2 -m pip install numpy
+
+# Change to the repository directory
+WORKDIR /app/Immunolyser
+
+# Expose Flask and Celery ports
+EXPOSE 5000
+EXPOSE 5555
+
+# Set a default environment variable for IMMUNOLYSER_DATA
+ENV IMMUNOLYSER_DATA=/app/data
+
+# Copy entrypoint script
+COPY entrypoint.sh /entrypoint.sh
+RUN chmod +x /entrypoint.sh
+
+# Create the results.sqlite file
+RUN touch /results.sqlite
+
+# Set the entrypoint script
+ENTRYPOINT ["/entrypoint.sh"]

README.md

@@ -0,0 +1,13 @@
+## Documentation
+
+- Main Documentation
+- [Immunolyser 2.0 Offline Setup Guide](Documentation/Immunolyser_2.0_Offline_Setup_Guide.md)
+
+<h4>Demo and example input</h4>
+<p>
+    A demo report has been generated to demonstrate the organisation and features of analysis results. It can be accessed by clicking on the <a href="https://immunolyser.erc.monash.edu/demo">Demo</a> tab. To test the pipeline end-to-end, the example files (exported from PEAKs) can be downloaded from <a href="https://immunolyser.erc.monash.edu/static/temp/Study%20by%20Son,%20Eric%20T.,%20et%20al.zip" target="_blank"> here</a> and uploaded in the demo <a href="https://immunolyser.erc.monash.edu/initialiser">initialiser</a> module to run the analysis. The dataset provided and used to generate the demo report are from the recent immunopeptidomic study by Son, Eric T., et al. In addition, we attached <a href="https://immunolyser.erc.monash.edu/static/temp/demo%20data%20from%20multiple%20softwares.zip" target="_blank"> example input files</a> exported from other search engines, including Skyline, ProteinPilot, Spectronaut, and DIA-NN. 
+</p>
+
+<p>
+    The input files used to generate figures in the manuscript can be accessed <a href="https://drive.google.com/drive/folders/14bICyGjIlZl3dCtV3qYZ7GKDNCORyB9U?usp=drive_link" target="_blank">here</a>.
+</p>

app/Pepscan.py

@@ -1,14 +1,11 @@
 import pandas as pd
 import numpy as np
-
 from matplotlib import pyplot as plt
+import matplotlib
+matplotlib.use('agg')
 import seaborn as sns
-
 import io
-import base64
 import os
-from matplotlib.backends.backend_agg import FigureCanvasAgg as FigureCanvas
-
 
 project_root = os.path.dirname(os.path.realpath(os.path.join(__file__, "..")))
 
@@ -63,6 +60,15 @@ def clean(self):
         #clean_frame["Peptide"] = clean_frame["Peptide"].str.replace(r'\(.*\.\d*\)', '')
         clean_frame["Peptide"] = clean_frame["Peptide"].str.replace(r'\(.{4,7}\)', '')
         clean_frame = clean_frame.dropna(subset = ["Accession"]).reset_index(drop = True)
+
+        # Calculate the initial number of rows
+        initial_count = len(clean_frame)
+        clean_frame = clean_frame[~clean_frame['Accession'].str.contains('CONTAM|DECOY', na=False)].reset_index(drop=True)
+        # Calculate the number of rows dropped
+        rows_dropped = initial_count - len(clean_frame)
+        # Print the number of rows dropped
+        print(f"Number of rows dropped where Accession had 'CONTAN' or 'DECOY' marked,: {rows_dropped}")
+
         self.peptide_frame = clean_frame
 
     def get_locs(self):
@@ -91,7 +97,7 @@ def get_rel_locs(self):
                 rel_locs.append(self.protein_frame["Location"][row]/len(self.protein_frame["Sequence"][row]))
         return rel_locs
 
-    def search_proteome(self, peptide_file, proteome_file = "uniprot-proteome_UP000005640.fasta",accessionsids='accessionsids'):
+    def search_proteome(self, peptide_file, proteome_file = "uniprot-proteome_UP000005640.fasta"):
         """Searches a proteome (proteome_file) and retrieves all protein sequences referenced by protein IDs corresponding to peptides stored in a PEAKS output csv (peptide_file)
 
         Keyword Arguments:
@@ -107,9 +113,6 @@ def search_proteome(self, peptide_file, proteome_file = "uniprot-proteome_UP0000
         ids = []
         use_id = []
 
-        # Importing unique accession ids for reference
-        accessionids = pd.read_csv(accessionsids)['ID'].to_list()
-
         #Retrieve most confident accession for each peptide
         for all_accession in self.peptide_frame["Accession"]:
             all_accession = all_accession.split(":")
@@ -136,8 +139,18 @@ def search_proteome(self, peptide_file, proteome_file = "uniprot-proteome_UP0000
         self.peptide_frame["Location"] = "No protein found"
         #Add peptide count column to proteome to keep track of peptides/protein
         proteome_frame["Peptides"] = 0
-        #join peptide and protein dataframes
-        self.protein_frame = self.peptide_frame[["ID", "Peptide"]].join(proteome_frame[["ID", "Sequence"]].set_index("ID"), on = "ID", how = "inner", lsuffix = "_pep", rsuffix = "_prot")
+
+        # Keep only rows with valid string/int IDs
+        valid_peptide_frame = self.peptide_frame[self.peptide_frame["ID"].apply(lambda x: isinstance(x, (str, int)))]
+
+        self.protein_frame = valid_peptide_frame[["ID", "Peptide"]].join(
+            proteome_frame[["ID", "Sequence"]].set_index("ID"),
+            on="ID",
+            how="inner",
+            lsuffix="_pep",
+            rsuffix="_prot"
+        )
+
         #retrieve locations for all peptides
         self.protein_frame.reset_index(drop = True, inplace = True)
         self.protein_frame["Location"] = self.get_locs()
@@ -155,8 +168,14 @@ def protein_dist(self, protein):
         peptides = self.protein_frame[self.protein_frame["ID"] == protein]
         peptides.reset_index(drop = True, inplace = True)
         locations = [0]*100
+
         #calculate relative length of peptides
         for pep in range(len(peptides)):
+
+            # Ammend by Prithvi: Skipping adding the location of the peptide if peptide not found in the protein
+            if peptides["Location"][pep] == "No Position Found": 
+                continue
+
             start = int(peptides["Relative Location"][pep]//0.01)
             end = int(((int(peptides["Location"][pep]) + len(peptides["Peptide"][pep]) - 1)/len(peptides["Sequence"][pep]))//0.01)
             #increment count for each relative position
@@ -196,27 +215,5 @@ def peptide_dist(self, proteins, taskId):
     #search proteome file for source proteins of peptide file
     # scanner.search_proteome(peptide_file = "VMM1_1st_nil_DT9_peptide_C0303_NetMHCpan_binders.csv", proteome_file = "uniprot-proteome_UP000005640.fasta")
     scanner.search_proteome(peptide_file = "elutiondata.csv", proteome_file = "uniprot-proteome_UP000005640.fasta")
-    #display plot
-#     scanner.peptide_dist(['P01903',
-#  'P30504',
-#  'Q6ZS81',
-#  'A0A0G2JMH6',
-#  'P49327',
-#  'P19320',
-#  'A0A0U1RQF0',
-#  'Q9UIQ6',
-#  'P20273',
-#  'P18583',
-#  'Q15751',
-#  'P30505',
-#  'E7EPN9',
-#  'Q29865',
-#  'Q9Y520',
-#  'A0A1W2PR11',
-#  'Q01082',
-#  'P13284',
-#  'A0A1W2PRZ0',
-#  'Q95604'])
+
     scanner.peptide_dist(["Q96C19", "P04818", "F8W6I7", "A0A0U1RQF0"])
-    #view peptide/source protein table
-    #print(scanner.protein_frame)

app/__init__.py

@@ -1,6 +1,23 @@
 from flask import Flask, render_template
 from flask_restplus import Api
 from config import Config
+from celery import Celery
+import os
+
+def make_celery(app):
+    celery = Celery(
+        app.import_name,
+        backend=app.config['CELERY_RESULT_BACKEND'],
+        broker=app.config['CELERY_BROKER_URL']
+    )
+    celery.conf.update(app.config)
+
+    class ContextTask(celery.Task):
+        def __call__(self, *args, **kwargs):
+            with app.app_context():
+                return self.run(*args, **kwargs)
+    celery.Task = ContextTask
+    return celery
 
 api = Api()
 
@@ -12,8 +29,10 @@ def index():
 
 app.config.from_object(Config)
 
+celery = make_celery(app)
+
 api.init_app(app)
 
 from app import routes
 
-app.run(host='0.0.0.0', port=5000)
+# app.run(debug=True)