Added "Model building" notebook.

Author: CMargreitter

environment.yml

@@ -1,149 +1,153 @@
 name: ReinventCommunity
 channels:
   - conda-forge
+  - omnia
+  - plotly
+  - pytorch
+  - openeye
+  - anaconda
+  - rdkit
   - defaults
 dependencies:
-  - _libgcc_mutex=0.1
-  - _openmp_mutex=4.5
-  - attrs=19.3.0
-  - backcall=0.1.0
-  - bleach=3.1.4
-  - boost=1.72.0
-  - boost-cpp=1.72.0
-  - bzip2=1.0.8
-  - ca-certificates=2020.4.5.1
-  - cairo=1.16.0
-  - certifi=2020.4.5.1
-  - cycler=0.10.0
-  - dbus=1.13.6
-  - decorator=4.4.2
-  - defusedxml=0.6.0
-  - entrypoints=0.3
-  - expat=2.2.9
-  - fontconfig=2.13.1
-  - freetype=2.10.1
-  - gettext=0.19.8.1
-  - glib=2.58.3
-  - gst-plugins-base=1.14.5
-  - gstreamer=1.14.5
-  - icu=64.2
-  - importlib-metadata=1.6.0
-  - importlib_metadata=1.6.0
-  - ipykernel=5.2.0
-  - ipython=7.13.0
-  - ipython_genutils=0.2.0
-  - ipywidgets=7.5.1
-  - jedi=0.16.0
-  - jinja2=2.11.1
-  - jpeg=9c
-  - jsonschema=3.2.0
-  - jupyter=1.0.0
-  - jupyter_client=6.1.2
-  - jupyter_console=6.1.0
-  - jupyter_core=4.6.3
-  - kiwisolver=1.2.0
-  - ld_impl_linux-64=2.34
-  - libblas=3.8.0
-  - libcblas=3.8.0
-  - libclang=9.0.1
-  - libffi=3.2.1
-  - libgcc-ng=9.2.0
-  - libgfortran-ng=7.3.0
-  - libgomp=9.2.0
-  - libiconv=1.15
-  - liblapack=3.8.0
-  - libllvm9=9.0.1
-  - libopenblas=0.3.7
-  - libpng=1.6.37
-  - libsodium=1.0.17
-  - libstdcxx-ng=9.2.0
-  - libtiff=4.1.0
-  - libuuid=2.32.1
-  - libwebp-base=1.1.0
-  - libxcb=1.13
-  - libxkbcommon=0.10.0
-  - libxml2=2.9.10
-  - lz4-c=1.8.3
-  - markupsafe=1.1.1
-  - matplotlib=3.2.1
-  - matplotlib-base=3.2.1
-  - mistune=0.8.4
-  - molvs=0.1.1
-  - nbconvert=5.6.1
-  - nbformat=5.0.4
-  - ncurses=6.1
-  - notebook=6.0.3
-  - nspr=4.25
-  - nss=3.47
-  - numpy=1.18.1
-  - olefile=0.46
-  - openssl=1.1.1g
-  - pandas=1.0.3
-  - pandoc=2.9.2
-  - pandocfilters=1.4.2
-  - parso=0.6.2
-  - patsy=0.5.1
-  - pcre=8.44
-  - pexpect=4.8.0
-  - pickleshare=0.7.5
-  - pillow=7.1.1
-  - pip=20.0.2
-  - pixman=0.38.0
-  - prometheus_client=0.7.1
-  - prompt-toolkit=3.0.5
-  - prompt_toolkit=3.0.5
-  - pthread-stubs=0.4
-  - ptyprocess=0.6.0
-  - py4j=0.10.7
-  - pycairo=1.19.1
-  - pygments=2.6.1
-  - pyparsing=2.4.7
-  - pyqt=5.12.3
-  - pyrsistent=0.16.0
-  - pyspark=2.4.5
-  - python=3.7.6
-  - python-dateutil=2.8.1
-  - python_abi=3.7
-  - pytz=2019.3
-  - pyzmq=19.0.0
-  - qt=5.12.5
-  - qtconsole=4.7.2
-  - qtpy=1.9.0
-  - rdkit=2020.03.1
-  - readline=8.0
-  - scipy=1.4.1
-  - seaborn=0.10.0
-  - send2trash=1.5.0
-  - setuptools=46.1.3
-  - six=1.14.0
-  - sqlite=3.30.1
-  - statsmodels=0.11.1
-  - terminado=0.8.3
-  - testpath=0.4.4
-  - tk=8.6.10
-  - tornado=6.0.4
-  - traitlets=4.3.3
-  - wcwidth=0.1.9
-  - webencodings=0.5.1
-  - wheel=0.34.2
-  - widgetsnbextension=3.5.1
-  - xorg-kbproto=1.0.7
-  - xorg-libice=1.0.10
-  - xorg-libsm=1.2.3
-  - xorg-libx11=1.6.9
-  - xorg-libxau=1.0.9
-  - xorg-libxdmcp=1.1.3
-  - xorg-libxext=1.3.4
-  - xorg-libxrender=0.9.10
-  - xorg-renderproto=0.11.1
-  - xorg-xextproto=7.3.0
-  - xorg-xproto=7.0.31
-  - xz=5.2.5
-  - zeromq=4.3.2
-  - zipp=3.1.0
-  - zlib=1.2.11
-  - zstd=1.4.4
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=0_gnu
+  - attrs=19.3.0=py_0
+  - backcall=0.1.0=py_0
+  - bleach=3.1.4=pyh9f0ad1d_0
+  - boost=1.72.0=py37h9de70de_0
+  - boost-cpp=1.72.0=h8e57a91_0
+  - bzip2=1.0.8=h516909a_2
+  - ca-certificates=2020.6.20=hecda079_0
+  - cairo=1.16.0=hcf35c78_1003
+  - certifi=2020.6.20=py37hc8dfbb8_0
+  - cycler=0.10.0=py_2
+  - dbus=1.13.6=he372182_0
+  - decorator=4.4.2=py_0
+  - defusedxml=0.6.0=py_0
+  - entrypoints=0.3=py37hc8dfbb8_1001
+  - expat=2.2.9=he1b5a44_2
+  - fontconfig=2.13.1=h86ecdb6_1001
+  - freetype=2.10.1=he06d7ca_0
+  - gettext=0.19.8.1=hc5be6a0_1002
+  - glib=2.58.3=py37he00f558_1003
+  - gst-plugins-base=1.14.5=h0935bb2_2
+  - gstreamer=1.14.5=h36ae1b5_2
+  - icu=64.2=he1b5a44_1
+  - importlib-metadata=1.6.0=py37hc8dfbb8_0
+  - importlib_metadata=1.6.0=0
+  - ipykernel=5.2.0=py37h43977f1_1
+  - ipython=7.13.0=py37hc8dfbb8_2
+  - ipython_genutils=0.2.0=py_1
+  - ipywidgets=7.5.1=py_0
+  - jedi=0.16.0=py37hc8dfbb8_1
+  - jinja2=2.11.1=py_0
+  - joblib=0.16.0=py_0
+  - jpeg=9c=h14c3975_1001
+  - jsonschema=3.2.0=py37hc8dfbb8_1
+  - jupyter=1.0.0=py_2
+  - jupyter_client=6.1.2=py_0
+  - jupyter_console=6.1.0=py_1
+  - jupyter_core=4.6.3=py37hc8dfbb8_1
+  - kiwisolver=1.2.0=py37h99015e2_0
+  - ld_impl_linux-64=2.34=h53a641e_0
+  - libblas=3.8.0=14_openblas
+  - libcblas=3.8.0=14_openblas
+  - libclang=9.0.1=default_hde54327_0
+  - libffi=3.2.1=he1b5a44_1007
+  - libgcc-ng=9.2.0=h24d8f2e_2
+  - libgfortran-ng=7.3.0=hdf63c60_5
+  - libgomp=9.2.0=h24d8f2e_2
+  - libiconv=1.15=h516909a_1006
+  - liblapack=3.8.0=14_openblas
+  - libllvm9=9.0.1=hc9558a2_0
+  - libopenblas=0.3.7=h5ec1e0e_6
+  - libpng=1.6.37=hed695b0_1
+  - libsodium=1.0.17=h516909a_0
+  - libstdcxx-ng=9.2.0=hdf63c60_2
+  - libtiff=4.1.0=hc7e4089_6
+  - libuuid=2.32.1=h14c3975_1000
+  - libwebp-base=1.1.0=h516909a_3
+  - libxcb=1.13=h14c3975_1002
+  - libxkbcommon=0.10.0=he1b5a44_0
+  - libxml2=2.9.10=hee79883_0
+  - lz4-c=1.8.3=he1b5a44_1001
+  - markupsafe=1.1.1=py37h8f50634_1
+  - matplotlib=3.2.1=0
+  - matplotlib-base=3.2.1=py37h30547a4_0
+  - mistune=0.8.4=py37h516909a_1000
+  - nbconvert=5.6.1=py37_0
+  - nbformat=5.0.4=py_0
+  - ncurses=6.1=hf484d3e_1002
+  - notebook=6.0.3=py37_0
+  - nspr=4.25=he1b5a44_0
+  - nss=3.47=he751ad9_0
+  - numpy=1.18.1=py37h8960a57_1
+  - olefile=0.46=py_0
+  - openssl=1.1.1g=h516909a_1
+  - pandas=1.0.3=py37h0da4684_0
+  - pandoc=2.9.2=0
+  - pandocfilters=1.4.2=py_1
+  - parso=0.6.2=py_0
+  - patsy=0.5.1=py_0
+  - pcre=8.44=he1b5a44_0
+  - pexpect=4.8.0=py37hc8dfbb8_1
+  - pickleshare=0.7.5=py37hc8dfbb8_1001
+  - pillow=7.1.1=py37h718be6c_0
+  - pip=20.0.2=py_2
+  - pixman=0.38.0=h516909a_1003
+  - prometheus_client=0.7.1=py_0
+  - prompt-toolkit=3.0.5=py_0
+  - prompt_toolkit=3.0.5=0
+  - pthread-stubs=0.4=h14c3975_1001
+  - ptyprocess=0.6.0=py_1001
+  - pycairo=1.19.1=py37h01af8b0_3
+  - pygments=2.6.1=py_0
+  - pyparsing=2.4.7=pyh9f0ad1d_0
+  - pyqt=5.12.3=py37hcca6a23_1
+  - pyrsistent=0.16.0=py37h8f50634_0
+  - python=3.7.6=h8356626_5_cpython
+  - python-dateutil=2.8.1=py_0
+  - python_abi=3.7=1_cp37m
+  - pytz=2019.3=py_0
+  - pyzmq=19.0.0=py37hac76be4_1
+  - qt=5.12.5=hd8c4c69_1
+  - qtconsole=4.7.2=pyh9f0ad1d_0
+  - qtpy=1.9.0=py_0
+  - rdkit=2020.03.1=py37hdd87690_1
+  - readline=8.0=hf8c457e_0
+  - scikit-learn=0.21.3=py37hcdab131_0
+  - scipy=1.4.1=py37ha3d9a3c_2
+  - seaborn=0.10.0=py_1
+  - send2trash=1.5.0=py_0
+  - setuptools=46.1.3=py37hc8dfbb8_0
+  - six=1.14.0=py_1
+  - sqlite=3.30.1=hcee41ef_0
+  - statsmodels=0.11.1=py37h8f50634_1
+  - terminado=0.8.3=py37hc8dfbb8_1
+  - testpath=0.4.4=py_0
+  - tk=8.6.10=hed695b0_0
+  - tornado=6.0.4=py37h8f50634_1
+  - traitlets=4.3.3=py37hc8dfbb8_1
+  - wcwidth=0.1.9=pyh9f0ad1d_0
+  - webencodings=0.5.1=py_1
+  - wheel=0.34.2=py_1
+  - widgetsnbextension=3.5.1=py37_0
+  - xorg-kbproto=1.0.7=h14c3975_1002
+  - xorg-libice=1.0.10=h516909a_0
+  - xorg-libsm=1.2.3=h84519dc_1000
+  - xorg-libx11=1.6.9=h516909a_0
+  - xorg-libxau=1.0.9=h14c3975_0
+  - xorg-libxdmcp=1.1.3=h516909a_0
+  - xorg-libxext=1.3.4=h516909a_0
+  - xorg-libxrender=0.9.10=h516909a_1002
+  - xorg-renderproto=0.11.1=h14c3975_1002
+  - xorg-xextproto=7.3.0=h14c3975_1002
+  - xorg-xproto=7.0.31=h14c3975_1007
+  - xz=5.2.5=h516909a_0
+  - zeromq=4.3.2=he1b5a44_2
+  - zipp=3.1.0=py_0
+  - zlib=1.2.11=h516909a_1006
+  - zstd=1.4.4=h3b9ef0a_2
   - pip:
     - pyqt5-sip==4.19.18
     - pyqtwebengine==5.12.1
-

notebooks/Complete_Use-Case-DRD2_Demo.ipynb

@@ -651,7 +651,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

notebooks/Data_Preparation.ipynb

@@ -15,7 +15,7 @@
     "\n",
     "\n",
     "# `REINVENT 2.0`: Data Preparation demo\n",
-    "This demo illustrates how can data from ChEMBL or other sources be processed, analysed and filtered. \n",
+    "This demo illustrates how data from ChEMBL or other sources be processed, analysed and filtered. \n",
     "\n",
     "To proceed, please update the following code block such that it reflects your system's installation and execute it."
    ]
@@ -2509,13 +2509,6 @@
     "chembl_filtered_df.write.parquet(filtered_parquet_file)\n",
     "chembl_filtered_df.select(\"smiles\").toPandas().to_csv(filtered_csv_file, index=False, header=False)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -2534,7 +2527,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,