diff --git a/README.md b/README.md
index 9f82dec..790bbf0 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,6 @@
 # OnionNet
-A multiple-layer inter-molecular contact based deep neural network for protein-ligand binding affinity prediction. The testing set is CASF-2013 benchmark. The protein-ligand binding affinity is directly predicted.
+A multiple-layer inter-molecular contact based deep neural network for protein-ligand binding affinity prediction.
+The testing set is CASF-2013 benchmark and PDBbind v2016 coreset. The protein-ligand binding affinity is directly predicted.
 
 The model could be applied for re-scoring the docking results.
 
@@ -65,10 +66,7 @@ Using the "generate_features.py" script to generate the features for OnionNet pr
     python generate_features.py -h
     python generate_features.py -inp input_complexes.dat -out output_features.csv
 
-    # or run the script with MPI, cpu 4 cores
-    mpirun -np 4 python generate_features.py -inp input_complexes.dat -out output_features.py 
-
-The input file contatins the absolute or relative pathes of the protein-ligand complexes pdb files.
+The input file contains the absolute or the path of the protein-ligand complexes pdb files.
 The content of the "input_complexes.dat" file could be:
  
     ./10gs/10gs_complex.pdb
diff --git a/onionnet_environments.yml b/onionnet_environments.yml
deleted file mode 100644
index d316869..0000000
--- a/onionnet_environments.yml
+++ /dev/null
@@ -1,171 +0,0 @@
-name: onionnet
-channels:
-  - omnia
-  - rdkit
-  - anaconda
-  - soumith
-  - conda-forge
-  - defaults
-dependencies:
-  - _tflow_select=2.3.0=mkl
-  - absl-py=0.6.1=py36_0
-  - asn1crypto=0.24.0=py36_0
-  - astor=0.7.1=py36_0
-  - biopython=1.72=py36h04863e7_0
-  - boto=2.49.0=py36_0
-  - boto3=1.9.35=py36_0
-  - botocore=1.12.35=py36_0
-  - c-ares=1.15.0=h7b6447c_1
-  - cffi=1.11.5=py36he75722e_1
-  - chardet=3.0.4=py36_1
-  - docutils=0.14=py36_0
-  - gast=0.2.0=py36_0
-  - gensim=3.4.0=py36h14c3975_0
-  - h5py=2.8.0=py36h989c5e5_3
-  - hdf5=1.10.2=hba1933b_1
-  - idna=2.7=py36_0
-  - intel-openmp=2019.1=144
-  - jmespath=0.9.3=py36_0
-  - keras=2.2.4=0
-  - keras-applications=1.0.6=py36_0
-  - keras-base=2.2.4=py36_0
-  - keras-preprocessing=1.0.5=py36_0
-  - libgcc-ng=8.2.0=hdf63c60_1
-  - libgfortran-ng=7.3.0=hdf63c60_0
-  - libprotobuf=3.6.1=hd408876_0
-  - libstdcxx-ng=8.2.0=hdf63c60_1
-  - markdown=3.0.1=py36_0
-  - mkl=2019.1=144
-  - networkx=2.2=py36_1
-  - protobuf=3.6.1=py36he6710b0_0
-  - pycparser=2.19=py36_0
-  - pyopenssl=18.0.0=py36_0
-  - pysocks=1.6.8=py36_0
-  - python-dateutil=2.7.5=py36_0
-  - pyyaml=3.13=py36h14c3975_0
-  - requests=2.20.1=py36_0
-  - s3transfer=0.1.13=py36_0
-  - six=1.11.0=py36_1
-  - smart_open=1.7.1=py36_0
-  - tensorboard=1.12.0=py36hf484d3e_0
-  - tensorflow=1.12.0=mkl_py36h69b6ba0_0
-  - tensorflow-base=1.12.0=mkl_py36h3c3e929_0
-  - termcolor=1.1.0=py36_1
-  - urllib3=1.23=py36_0
-  - werkzeug=0.14.1=py36_0
-  - yaml=0.1.7=h96e3832_1
-  - attrs=18.2.0=py_0
-  - backcall=0.1.0=py_0
-  - binutils_impl_linux-64=2.31.1=h6176602_1
-  - binutils_linux-64=2.31.1=h6176602_3
-  - blosc=1.15.1=hf484d3e_1002
-  - bzip2=1.0.6=h14c3975_1002
-  - ca-certificates=2018.11.29=ha4d7672_0
-  - cairo=1.14.12=h80bd089_1005
-  - certifi=2018.11.29=py36_1000
-  - cycler=0.10.0=py_1
-  - decorator=4.3.0=py_0
-  - expat=2.2.5=hfc679d8_2
-  - fontconfig=2.13.1=h65d0f4c_0
-  - freetype=2.9.1=h6debe1e_4
-  - gcc_impl_linux-64=7.3.0=habb00fd_1
-  - gcc_linux-64=7.3.0=h553295d_3
-  - gettext=0.19.8.1=h5e8e0c9_1
-  - glib=2.56.2=h464dc38_1
-  - gxx_impl_linux-64=7.3.0=hdf63c60_1
-  - gxx_linux-64=7.3.0=h553295d_3
-  - icu=58.2=hfc679d8_0
-  - ipykernel=5.1.0=py36h24bf2e0_1001
-  - ipython=7.2.0=py36h24bf2e0_1000
-  - ipython_genutils=0.2.0=py_1
-  - jedi=0.13.2=py36_1000
-  - jpeg=9c=h470a237_1
-  - jsonschema=3.0.0a3=py36_1000
-  - kiwisolver=1.0.1=py36h2d50403_2
-  - libffi=3.2.1=hfc679d8_5
-  - libgfortran=3.0.0=1
-  - libgpuarray=0.7.6=h14c3975_1003
-  - libiconv=1.15=h470a237_3
-  - libpng=1.6.36=ha92aebf_0
-  - libsodium=1.0.16=h470a237_1
-  - libtiff=4.0.10=h9022e91_1002
-  - libuuid=2.32.1=h470a237_2
-  - libxcb=1.13=h470a237_2
-  - libxml2=2.9.8=h422b904_5
-  - lzo=2.10=h14c3975_1000
-  - mako=1.0.7=py_1
-  - markupsafe=1.1.0=py36h14c3975_1000
-  - matplotlib=3.0.2=py36h8a2030e_1
-  - matplotlib-base=3.0.2=py36h20b835b_1
-  - mkl_fft=1.0.10=py36_0
-  - mkl_random=1.0.2=py36_0
-  - nbformat=4.4.0=py_1
-  - ncurses=6.1=hfc679d8_2
-  - numexpr=2.6.9=py36h637b7d7_1000
-  - olefile=0.46=py_0
-  - openblas=0.3.3=ha44fe06_1
-  - openssl=1.1.1a=h14c3975_1000
-  - pandas=0.23.4=py36hf8a1672_0
-  - parso=0.3.1=py_0
-  - pexpect=4.6.0=py36_1000
-  - pickleshare=0.7.5=py36_1000
-  - pillow=5.4.1=py36h00a061d_1000
-  - pip=18.1=py36_1000
-  - pixman=0.34.0=h14c3975_1003
-  - plotly=3.6.1=py_0
-  - prompt_toolkit=2.0.7=py_0
-  - pthread-stubs=0.4=h470a237_1
-  - ptyprocess=0.6.0=py36_1000
-  - pygments=2.3.1=py_0
-  - pygpu=0.7.6=py36h3010b51_1000
-  - pyparsing=2.3.0=py_0
-  - pyqt=5.6.0=py36h8210e8a_8
-  - pyrsistent=0.14.10=py36h14c3975_0
-  - pytables=3.4.4=py36h4f72b40_1
-  - pytz=2018.7=py_0
-  - pyzmq=17.1.2=py36hae99301_1
-  - readline=7.0=haf1bffa_1
-  - retrying=1.3.3=py_2
-  - setuptools=40.6.3=py36_0
-  - sip=4.18.1=py36hfc679d8_0
-  - sqlite=3.26.0=hb1c47c0_0
-  - theano=1.0.4=py36hf484d3e_1000
-  - tk=8.6.9=ha92aebf_0
-  - tornado=5.1.1=py36h470a237_0
-  - traitlets=4.3.2=py36_1000
-  - wcwidth=0.1.7=py_1
-  - wheel=0.32.3=py36_0
-  - xorg-kbproto=1.0.7=h14c3975_1002
-  - xorg-libice=1.0.9=h14c3975_1004
-  - xorg-libsm=1.2.3=h4937e3b_1000
-  - xorg-libx11=1.6.6=h14c3975_1000
-  - xorg-libxau=1.0.8=h470a237_6
-  - xorg-libxdmcp=1.1.2=h470a237_7
-  - xorg-libxext=1.3.3=h14c3975_1004
-  - xorg-libxrender=0.9.10=h14c3975_1002
-  - xorg-renderproto=0.11.1=h14c3975_1002
-  - xorg-xextproto=7.3.0=h14c3975_1002
-  - xorg-xproto=7.0.31=h14c3975_1007
-  - xz=5.2.4=h470a237_1
-  - zeromq=4.2.5=hfc679d8_6
-  - zlib=1.2.11=h470a237_3
-  - zstd=1.3.3=1
-  - blas=1.0=mkl
-  - cryptography=2.5=py36h1ba5d50_0
-  - dbus=1.13.2=h714fa37_1
-  - grpcio=1.16.1=py36hf8bcb03_1
-  - gst-plugins-base=1.14.0=hbbd80ab_1
-  - gstreamer=1.14.0=hb453b48_1
-  - libboost=1.65.1=habcd387_4
-  - libopenblas=0.3.3=h5a2b251_3
-  - mkl-service=1.1.2=py36he904b0f_5
-  - numpy=1.15.4=py36h7e9f1db_0
-  - numpy-base=1.15.4=py36hde5b4d6_0
-  - pcre=8.42=h439df22_0
-  - py-boost=1.65.1=py36hf484d3e_4
-  - python=3.6.8=h0371630_0
-  - qt=5.6.3=h8bf5577_3
-  - scikit-learn=0.20.2=py36hd81dba3_0
-  - scipy=1.1.0=py36h7c811a0_2
-  - mdtraj=1.9.1=py36_0
-  - rdkit=2018.09.1.0=py36h71b666b_1
diff --git a/tutorials/PDB_samples/README.md b/tutorials/PDB_samples/README.md
index 8345e94..b937374 100644
--- a/tutorials/PDB_samples/README.md
+++ b/tutorials/PDB_samples/README.md
@@ -28,7 +28,7 @@ Example commands:
 ## 4. Make the prediction
 
     python predict_pKa.py -h
-    python predict_pKa.py -fn docking_complexes_features.csv -model ./models/OnionNet_HFree.model \
-    -scaler models/StandardScaler.model -out predicted_pka_values.csv
+    python predict_pKa.py -fn docking_complexes_features.csv -model ../../models/OnionNet_HFree.model \
+    -scaler ../../models/StandardScaler.model -out predicted_pka_values.csv
 
 Note: The larger the pka value is, the stronger it binds to a receptor.
diff --git a/tutorials/docking_samples/README.md b/tutorials/docking_samples/README.md
index 8345e94..b937374 100644
--- a/tutorials/docking_samples/README.md
+++ b/tutorials/docking_samples/README.md
@@ -28,7 +28,7 @@ Example commands:
 ## 4. Make the prediction
 
     python predict_pKa.py -h
-    python predict_pKa.py -fn docking_complexes_features.csv -model ./models/OnionNet_HFree.model \
-    -scaler models/StandardScaler.model -out predicted_pka_values.csv
+    python predict_pKa.py -fn docking_complexes_features.csv -model ../../models/OnionNet_HFree.model \
+    -scaler ../../models/StandardScaler.model -out predicted_pka_values.csv
 
 Note: The larger the pka value is, the stronger it binds to a receptor.