Merge pull request #26 from kmansouri/master

v2.6-beta1
NIEHS · May 20, 2020 · 83106bf · 83106bf
2 parents 55ad371 + 9dac811
commit 83106bf
Show file tree

Hide file tree

Showing 12 changed files with 600 additions and 152 deletions.
diff --git a/Install_guide.pdf b/Install_guide.pdf
diff --git a/OPERA_Source_code/OPERA.m b/OPERA_Source_code/OPERA.m
diff --git a/OPERA_Source_code/OPERA_UI.mlapp b/OPERA_Source_code/OPERA_UI.mlapp
diff --git a/OPERA_Source_code/OPERA_par.m b/OPERA_Source_code/OPERA_par.m
diff --git a/OPERA_Source_code/help.txt b/OPERA_Source_code/help.txt
@@ -3,7 +3,7 @@
        _______________________________________________________________________
       |                                                                       |
       |   OPERA models for physchem, environmental fate and tox properties.   |
-      |                 Version 2.5 (January 2020)                            |
+      |                 Version 2.6 (May 2020)                                |
       |_______________________________________________________________________|    
 
 
@@ -28,6 +28,7 @@
    -t, --SaltInfo           Salt IDs to improve melting point predictions. List provided in Salts.xls
    -l, --Labels             Descriptor labels. Necessary if the descriptor file does not contain labels 
                             or contains more than the 1444 PaDEL 2D descriptors.
+   -st, --Standardize		Generate QSAR-ready structures from input structures. 
 
  Output:
    -o, --Output             Output file containing the predictions, applicability domain and accuracy 
@@ -36,7 +37,8 @@
                             (Sim_index) and accuracy estimate (Conf_index).
    -n, --Neighbors          Add 5 nearest neighbors from training set (CAS, InCHiKeys, Observed and predicted values)
    -O, --FullOutput         Output file containing all prediction details and used descriptors in csv format.
-   -x, --Seperate           Separate output file for each endpoint. 
+   -gd, -getDesc			Output file containing used descriptors in csv format.
+   -x, --Separate           Separate output file for each endpoint. 
 
  Miscellaneous:
    -v, --Verbose            Verbose level: 0=silent (default), 1=minimum details,    2=full details.
@@ -67,3 +69,4 @@ For more information about the models and the data:
 [5] JRC QSAR Model Database https://qsardb.jrc.ec.europa.eu/qmrf/endpoint
 [6] Mansouri, K. et al. EHP (2016) https://ehp.niehs.nih.gov/doi/full/10.1289/ehp.1510267
 [7] Mansouri, K. et al. J Cheminform (2019) https://link.springer.com/article/10.1186/s13321-019-0384-1
+[8] Mansouri, K. et al. EHP (2020) https://doi.org/10.1289/EHP5580
diff --git a/OPERA_Source_code/helpP.txt b/OPERA_Source_code/helpP.txt
@@ -3,7 +3,7 @@
        _______________________________________________________________________
       |                                                                       |
       |   OPERA models for physchem, environmental fate and tox properties.   |
-      |                 Version 2.5 (January 2020)                            |
+      |                 Version 2.6 (May 2020)                                |
       |_______________________________________________________________________|    
 
 
@@ -28,6 +28,7 @@
    -t, --SaltInfo           Salt IDs to improve melting point predictions. List provided in Salts.xls
    -l, --Labels             Descriptor labels. Necessary if the descriptor file does not contain labels 
                             or contains more than the 1444 PaDEL 2D descriptors.
+   -st, --Standardize		Generate QSAR-ready structures from input structures.
 
  Output:
    -o, --Output             Output file containing the predictions, applicability domain and accuracy 
@@ -36,7 +37,8 @@
                             (Sim_index) and accuracy estimate (Conf_index).
    -n, --Neighbors          Add 5 nearest neighbors from training set (CAS, InCHiKeys, Observed and predicted values)
    -O, --FullOutput         Output file containing all prediction details and used descriptors in csv format.
-   -x, --Seperate           Separate output file for each endpoint. 
+   -gd, -getDesc			Output file containing used descriptors in csv format.
+   -x, --Separate           Separate output file for each endpoint.  
 
  Miscellaneous:
    -v, --Verbose            Verbose level: 0=silent (default), 1=minimum details,    2=full details.
@@ -67,3 +69,4 @@ For more information about the models and the data:
 [5] JRC QSAR Model Database https://qsardb.jrc.ec.europa.eu/qmrf/endpoint
 [6] Mansouri, K. et al. EHP (2016) https://ehp.niehs.nih.gov/doi/full/10.1289/ehp.1510267
 [7] Mansouri, K. et al. J Cheminform (2019) https://link.springer.com/article/10.1186/s13321-019-0384-1
+[8] Mansouri, K. et al. EHP (2020) https://doi.org/10.1289/EHP5580
diff --git a/OPERA_Source_code/helpP_w.txt b/OPERA_Source_code/helpP_w.txt
@@ -3,7 +3,7 @@
        _______________________________________________________________________
       |                                                                       |
       |   OPERA models for physchem, environmental fate and tox properties.   |
-      |                 Version 2.5 (January 2020)                            |
+      |                 Version 2.6 (May 2020)                                |
       |_______________________________________________________________________|   
 
 
@@ -28,6 +28,7 @@
    -t, --SaltInfo           Salt IDs to improve melting point predictions. List provided in Salts.xls
    -l, --Labels             Descriptor labels. Necessary if the descriptor file does not contain labels 
                             or contains more than the 1444 PaDEL 2D descriptors.
+   -st, --Standardize		Generate QSAR-ready structures from input structures.
 
  Output:
    -o, --Output             Output file containing the predictions, applicability domain and accuracy 
@@ -36,7 +37,8 @@
                             (Sim_index) and accuracy estimate (Conf_index).
    -n, --Neighbors          Add 5 nearest neighbors from training set (CAS, InCHiKeys, Observed and predicted values)
    -O, --FullOutput         Output file containing all prediction details and used descriptors in csv format.
-   -x, --Seperate           Separate output file for each endpoint. 
+   -gd, -getDesc			Output file containing used descriptors in csv format.
+   -x, --Separate           Separate output file for each endpoint.  
 
  Miscellaneous:
    -v, --Verbose            Verbose level: 0=silent (default), 1=minimum details,    2=full details.
@@ -50,7 +52,7 @@
    -exp						Get experimental values, when available. Requires CAS or DTXSID.
    -h, --Help               Display this help file and exit.
    -V, --Version            Version of the application  
-   -P, --Parallel           Number of cpus for the parallel session. If non specified the app will use all cpus available. 
+   -P, --Parallel           Number of cpus for the parallel session (at least 100 chemicals/cpu). If non specified the app will use all cpus available. 
 
 
  Developed by:

diff --git a/OPERA_Source_code/help_w.txt b/OPERA_Source_code/help_w.txt
@@ -3,7 +3,7 @@
        _______________________________________________________________________
       |                                                                       |
       |   OPERA models for physchem, environmental fate and tox properties.   |
-      |                 Version 2.5 (January 2020)                            |
+      |                 Version 2.6 (May 2020)                            |
       |_______________________________________________________________________|   
 
 
@@ -28,15 +28,17 @@
    -t, --SaltInfo           Salt IDs to improve melting point predictions. List provided in Salts.xls
    -l, --Labels             Descriptor labels. Necessary if the descriptor file does not contain labels 
                             or contains more than the 1444 PaDEL 2D descriptors.
+   -st, --Standardize		Generate QSAR-ready structures from input structures. 
 
  Output:
    -o, --Output             Output file containing the predictions, applicability domain and accuracy 
                             information. File extension could be csv or txt. The output will contain by default: 
                             Molecule ID, predicted value (pred), Applicability domain (AD), Similarity index 
                             (Sim_index) and accuracy estimate (Conf_index).
    -n, --Neighbors          Add 5 nearest neighbors from training set (CAS, InCHiKeys, Observed and predicted values)
-   -O, --FullOutput         Output file containing all prediction details and used descriptors in csv format.
-   -x, --Seperate           Separate output file for each endpoint. 
+   -O, --FullOutput         Output file containing all prediction details including NN and used descriptors in csv format.
+   -gd, -getDesc			Output file containing used descriptors in csv format.
+   -x, --Separate           Separate output file for each endpoint. 
 
  Miscellaneous:
    -v, --Verbose            Verbose level: 0=silent (default), 1=minimum details,    2=full details.
@@ -67,4 +69,5 @@ For more information about the models and the data:
 [5] JRC QSAR Model Database https://qsardb.jrc.ec.europa.eu/qmrf/endpoint
 [6] Mansouri, K. et al. EHP (2016) https://ehp.niehs.nih.gov/doi/full/10.1289/ehp.1510267
 [7] Mansouri, K. et al. J Cheminform (2019) https://link.springer.com/article/10.1186/s13321-019-0384-1
+[8] Mansouri, K. et al. EHP (2020) https://doi.org/10.1289/EHP5580
 
diff --git a/OPERA_Source_code/intro.txt b/OPERA_Source_code/intro.txt
@@ -2,7 +2,7 @@
        _______________________________________________________________________
       |                                                                       |
       |   OPERA models for physchem, environmental fate and tox properties.   |
-      |                 Version 2.5 (January 2020)                            |
+      |                 Version 2.6 (May 2020)                                |
       |_______________________________________________________________________|      
 
 
@@ -21,4 +21,4 @@ [email protected]
 ./run_OPERA.sh /mathworks/home/application/v94 -s Sample_50.sdf -o predictions.csv -a -x -n -v 2
 ./run_OPERA.sh /mathworks/home/application/v94 -d Sample_50.csv -o predictions.txt -e logP BCF -v 1
 
-Type OPERA -h or OPERA --help for more info.
+Use -h or --help for more info.
diff --git a/OPERA_Source_code/introP.txt b/OPERA_Source_code/introP.txt
@@ -2,7 +2,7 @@
        _______________________________________________________________________
       |                                                                       |
       |   OPERA models for physchem, environmental fate and tox properties.   |
-      |                 Version 2.5 Parallel (January 2020)                   |
+      |                 Version 2.6 Parallel (May 2020)                       |
       |_______________________________________________________________________|      
 
 
@@ -22,4 +22,4 @@ [email protected]
 ./run_OPERA.sh /mathworks/home/application/v94 -s Sample_50.sdf -o predictions.csv -a -x -n -v 2 -P 16
 ./run_OPERA.sh /mathworks/home/application/v94 -d Sample_50.csv -o predictions.txt -e logP BCF -v 1
 
-Type OPERA -h or OPERA --help for more info.
+Use -h or --help for more info.
diff --git a/OPERA_Source_code/intro_w.txt b/OPERA_Source_code/intro_w.txt
@@ -2,7 +2,7 @@
        _______________________________________________________________________
       |                                                                       |
       |   OPERA models for physchem, environmental fate and tox properties.   |
-      |                 Version 2.5 (January 2020)                            |
+      |                 Version 2.6 (May 2020)                                |
       |_______________________________________________________________________|      
 
 

diff --git a/OPERA_Source_code/svmpredict.mexa64 b/OPERA_Source_code/svmpredict.mexa64