Merge pull request #548 from MannLabs/develop

Develop 0.5.0

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.9
+current_version = 0.5.0
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?

.github/workflows/quick_test.yml

@@ -27,8 +27,8 @@ jobs:
     - name: Run Alphapept on Thermo (IRT_Thermo_Win)
       run: |
         conda activate alphapept
-        python test_ci.py "${{ env.TMP_FOLDER }}" thermo_irt "${{ secrets.MONGODB_PW }}"
+        python test_ci.py "${{ env.TMP_FOLDER }}" thermo_irt
     - name: Run Alphapept on Bruker (IRT_Bruker_Win)
       run: |
         conda activate alphapept
-        python test_ci.py "${{ env.TMP_FOLDER }}" bruker_irt "${{ secrets.MONGODB_PW }}"
+        python test_ci.py "${{ env.TMP_FOLDER }}" bruker_irt

.gitignore

@@ -149,3 +149,6 @@ checklink/cookies.txt
 logs
 _docs/
 sidebar.yml
+
+_proc/
+

Dockerfile

@@ -0,0 +1,27 @@
+FROM jupyter/base-notebook:python-3.8
+
+USER root
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+    apt-utils \
+    build-essential \
+    libgomp1 \
+    gnupg \
+    ca-certificates \
+    && apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 3FA7E0328081BFF6A14DA29AA6A19B38D3D831EF \
+    && echo "deb https://download.mono-project.com/repo/ubuntu stable-focal main" | sudo tee /etc/apt/sources.list.d/mono-official-stable.list \
+    && apt update \
+    && apt install -y mono-devel \
+    && wget https://github.com/MannLabs/alphapept/blob/master/alphapept/ext/bruker/FF/linux64/libtbb.so.2 \
+    && mv libtbb.so.2 /usr/lib/
+
+RUN conda install -c anaconda pytables==3.6.1
+RUN conda install -c conda-forge pythonnet
+RUN conda install numba==0.55.2 numpy==1.20.3 pandas==1.4.3
+
+COPY . .
+RUN pip install ".[stable,gui-stable]"
+
+
+CMD ["bash"]

Dockerfile_bruker

@@ -1,14 +1,16 @@
 FROM ubuntu:20.04
 
 RUN apt-get update && apt-get install build-essential -y
-RUN apt-get install python3-pip -y
+RUN apt-get install python3-pip procps -y
 
-WORKDIR /home/alphapept/
-COPY . .
-
-RUN pip install .
+RUN pip install "alphapept[stable,gui-stable]"
 
 RUN apt-get install libgomp1 -y
-RUN cp  /usr/local/lib/python3.8/dist-packages/alphapept/ext/bruker/FF/linux64/libtbb.so.2 /usr/lib/libtbb.so.2
+
+ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib/python3.8/dist-packages/alphapept/ext/bruker/FF/linux64/
 RUN chmod 555 -R  /usr/local/lib/python3.8/dist-packages/alphapept/ext/bruker/FF/linux64/uff-cmdline2
+
+RUN pip install "numpy<1.24.0"
+RUN pip install "sqlalchemy<2.0"
+
 CMD ["bash"]

Dockerfile_thermo

@@ -1,24 +1,25 @@
-FROM python:3.8.3
+FROM jupyter/base-notebook:python-3.8
 
-# Mono: 5.20
+USER root
 
-RUN apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 3FA7E0328081BFF6A14DA29AA6A19B38D3D831EF \
-  && echo "deb http://download.mono-project.com/repo/debian stretch/snapshots/5.20 main" > /etc/apt/sources.list.d/mono-official.list \
-  && apt-get update \
-  && apt-get install -y clang \
-  && apt-get install -y mono-devel=5.20\* \
-  && rm -rf /var/lib/apt/lists/* /tmp/*
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+    apt-utils \
+    build-essential \
+    libgomp1 \
+    gnupg \
+    ca-certificates \
+    && apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 3FA7E0328081BFF6A14DA29AA6A19B38D3D831EF \
+    && echo "deb https://download.mono-project.com/repo/ubuntu stable-focal main" | sudo tee /etc/apt/sources.list.d/mono-official-stable.list \
+    && apt update \
+    && apt install -y mono-devel \
+    && wget https://github.com/MannLabs/alphapept/blob/master/alphapept/ext/bruker/FF/linux64/libtbb.so.2 \
+    && mv libtbb.so.2 /usr/lib/
 
-# Pythonnet: 2.5.0 (from PyPI)
-# Note: pycparser must be installed before pythonnet can be built
+RUN conda install -c anaconda pytables==3.6.1
+RUN conda install -c conda-forge pythonnet>=2.5.0
+RUN conda install numba==0.55.2 numpy==1.20.3 pandas==1.4.3
 
-RUN pip install pycparser \
-  && pip install pythonnet==2.5.0
+RUN pip install "alphapept[stable,gui-stable]"
 
-WORKDIR /home/alphapept/
-COPY . .
-
-RUN pip install -r requirements.txt
-RUN pip install .
-
-CMD ["bash"]
+CMD ["bash"]

README.md

@@ -141,7 +141,7 @@ AlphaPept as a package within the environment; see below.
     Linux](https://www.mono-project.com/download/stable/#download-lin).
     NOTE, the installed mono version should be at least 6.10, which
     requires you to add the ppa to your trusted sources!
-6.  Install pythonnet with `pip install pythonnet==2.5.2`
+6.  Install pythonnet with `pip install pythonnet>=2.5.2`
 
 ------------------------------------------------------------------------
 
@@ -172,7 +172,7 @@ AlphaPept as a package within the environment; see below.
   Make sure that the Path matches to your version (Here 6.12.0)
 - Save everything and execute `. ~/.zshrc`
 
-4.  Install pythonnet with `pip install pythonnet==2.5.2`
+4.  Install pythonnet with `pip install pythonnet>=2.5.2`
 
 ------------------------------------------------------------------------
 
@@ -227,6 +227,33 @@ installed on Windows machines via a one-click installer. Download the
 latest version
 [here](https://github.com/MannLabs/alphapept/releases/latest).
 
+## Docker
+
+It is possible to run AlphaPept in a docker container. For this, we
+provide two Dockerfiles: `Dockerfile_thermo` and `Dockerfile_bruker`,
+depending on which filetypes you want to analyse. They are split because
+of drastically different requirements.
+
+To run, navigate to the AlphaPept repository and rename the dockerfile
+you want to use, e.g. `Dockerfile_thermo` to `Dockerfile`.
+
+- Build the image with: `docker build -t docker-alphapept:latest .`
+- To run use
+  `docker run -p 8505:8505 -v /Users/username/Desktop/docker:/home/alphapept/ docker-alphapept:latest alphapept gui`
+  (Note that -v maps a local folder for convient file transfer)
+- Access the AlphaPept GUI via `localhost:8505` in your browser.
+- Note 1: The Thermo Dockerfile is built on a Jupyter image, so you can
+  also start a jupyter instance:
+  `docker run -p 8888:8888 -v /Users/username/Desktop/docker:/home/jovyan/ docker-alphapept:latest jupyter notebook --allow-root`
+
+### Docker Troubleshooting on M1-Mac
+
+- The Thermo dockerfile was tested on an M1-Mac. Resources were set to
+  18GB RAM and 2 CPUs, 200 GB disk
+- It was possible to build the Bruker dockerfile with the platform tag
+  `--platform linux/amd64`. However, it was very slow and the Bruker
+  file is not recommended for an M1-Mac. Windows worked nicely.
+
 ## Additional Documentation
 
 The documentation is automatically built based on the jupyter notebooks

alphapept/__init__.py

@@ -1,7 +1,8 @@
-__version__ = "0.4.9"
+__version__ = "0.5.0"
 
 __requirements__ = {
     "": "requirements/requirements.txt",
     "develop": "requirements/requirements_develop.txt",
     "gui": "requirements/requirements_gui.txt",
+    "legacy": "requirements/requirements_legacy.txt",
 }

alphapept/__version__.py

@@ -33,7 +33,7 @@
 AUTHOR_EMAIL = "straussmaximilian@gmail.com"
 COPYRIGHT = "Mann Labs"
 BRANCH = "master"
-VERSION_NO = "0.4.9"
+VERSION_NO = "0.5.0"
 MIN_PYTHON = "3.6"
 MAX_PYTHON = "4"
 AUDIENCE = "Developers"

alphapept/_modidx.py

@@ -18,6 +18,7 @@
                                 'alphapept.chem.get_average_formula': ('chem.html#get_average_formula', 'alphapept/chem.py'),
                                 'alphapept.chem.mass_to_dist': ('chem.html#mass_to_dist', 'alphapept/chem.py'),
                                 'alphapept.chem.numba_bin': ('chem.html#numba_bin', 'alphapept/chem.py')},
+            'alphapept.clr_utils': {},
             'alphapept.constants': { 'alphapept.constants.Isotope': ('constants.html#isotope', 'alphapept/constants.py'),
                                      'alphapept.constants.Isotope.__init__': ('constants.html#isotope.__init__', 'alphapept/constants.py'),
                                      'alphapept.constants.get_mass_dict': ('constants.html#get_mass_dict', 'alphapept/constants.py')},
@@ -260,10 +261,12 @@
                               'alphapept.io.get_local_intensity': ('io.html#get_local_intensity', 'alphapept/io.py'),
                               'alphapept.io.get_most_abundant': ('io.html#get_most_abundant', 'alphapept/io.py'),
                               'alphapept.io.get_peaks': ('io.html#get_peaks', 'alphapept/io.py'),
+                              'alphapept.io.import_sciex_as_alphapept': ('io.html#import_sciex_as_alphapept', 'alphapept/io.py'),
                               'alphapept.io.index_ragged_list': ('io.html#index_ragged_list', 'alphapept/io.py'),
                               'alphapept.io.list_to_numpy_f32': ('io.html#list_to_numpy_f32', 'alphapept/io.py'),
                               'alphapept.io.load_bruker_raw': ('io.html#load_bruker_raw', 'alphapept/io.py'),
                               'alphapept.io.load_mzml_data': ('io.html#load_mzml_data', 'alphapept/io.py'),
+                              'alphapept.io.load_sciex_raw': ('io.html#load_sciex_raw', 'alphapept/io.py'),
                               'alphapept.io.load_thermo_raw': ('io.html#load_thermo_raw', 'alphapept/io.py'),
                               'alphapept.io.one_over_k0_to_CCS': ('io.html#one_over_k0_to_ccs', 'alphapept/io.py'),
                               'alphapept.io.parse_mq_seq': ('io.html#parse_mq_seq', 'alphapept/io.py'),

alphapept/clr_utils.py

@@ -0,0 +1,42 @@
+import clr
+import os
+import numpy as np
+
+clr.AddReference('System')
+# from System.Runtime.InteropServices import Marshal
+# from System import IntPtr, Int64
+# def DotNetArrayToNPArray(src):
+#     '''
+#     See https://github.com/mobiusklein/ms_deisotope/blob/90b817d4b5ae7823cfe4ad61c57119d62a6e3d9d/ms_deisotope/data_source/thermo_raw_net.py#L217
+#     '''
+#     if src is None:
+#         return np.array([], dtype=np.float64)
+#     dest = np.empty(len(src), dtype=np.float64)
+#     Marshal.Copy(
+#         src, 0,
+#         IntPtr.__overloads__[Int64](dest.__array_interface__['data'][0]),
+#         len(src))
+#     return dest
+
+from System.Runtime.InteropServices import GCHandle, GCHandleType
+import ctypes
+def DotNetArrayToNPArray(src):
+    '''
+    See https://mail.python.org/pipermail/pythondotnet/2014-May/001527.html
+    '''
+    if src is None:
+        return np.array([], dtype=np.float64)
+    src_hndl = GCHandle.Alloc(src, GCHandleType.Pinned)
+    try:
+        src_ptr = src_hndl.AddrOfPinnedObject().ToInt64()
+        bufType = ctypes.c_double*len(src)
+        cbuf = bufType.from_address(src_ptr)
+        dest = np.frombuffer(cbuf, dtype=cbuf._type_).copy()
+    finally:
+        if src_hndl.IsAllocated: src_hndl.Free()
+        return dest
+
+ext_dir = os.path.join(
+    os.path.dirname(__file__),
+    'ext'
+)

alphapept/constants.py

@@ -189,6 +189,7 @@ def __init__(self, m0:int, dm:int, intensities:np.ndarray):
 protease_dict["trypsin_exception"] = "((?<=[CD])K(?=D))|((?<=C)K(?=[HY]))|((?<=C)R(?=K))|((?<=R)R(?=[HR]))"
 protease_dict["non-specific"] = "()"
 protease_dict["trypsin"] = "([KR](?=[^P]))"
+protease_dict["trypsin/p"] = "[KR]"
 
 # %% ../nbs/10_constants.ipynb 25
 from numba.typed import Dict

alphapept/fasta.py

@@ -24,7 +24,7 @@ def get_missed_cleavages(sequences:list, n_missed_cleavages:int) -> list:
         list (of str): the sequences with missed cleavages.
     """
     missed = []
-    for k in range(len(sequences)-n_missed_cleavages):
+    for k in range(len(sequences)-n_missed_cleavages+1):
         missed.append(''.join(sequences[k-1:k+n_missed_cleavages]))
 
     return missed

alphapept/feature_finding.py

@@ -1875,6 +1875,8 @@ def find_features(to_process:tuple, callback:Union[Callable, None] = None, paral
             datatype='bruker'
         elif ext.lower() == '.mzml':
             datatype='mzml'
+        elif ext.lower() == '.wiff':
+            datatype='sciex'
         else:
             raise NotImplementedError('File extension {} not understood.'.format(ext))
 
@@ -1905,7 +1907,7 @@ def find_features(to_process:tuple, callback:Union[Callable, None] = None, paral
             if not settings['workflow']["find_features"]:
                 features = query_data_to_features(query_data)
             else:
-                if datatype in ['thermo','mzml']:
+                if datatype in ['thermo','mzml','sciex']:
 
                     from alphapept.constants import averagine_aa, isotopes
 

alphapept/gui/constants.py

@@ -5,7 +5,7 @@
 import alphapept.constants
 import alphapept.settings
 
-@st.cache
+@st.cache_data
 def load_mods(path):
     df = pd.read_csv(path, delimiter="\t")
     return df