Merge pull request #71 from choderalab/data_clean

Adding quickmodel example and a new competition assay modeling notebook.

examples/competition-fluorescence-assay/README.md

@@ -14,8 +14,19 @@ Here is a series of ipython notebooks that walks you through simulation and anal
 
 ## Command line tools 
 
-To plot raw data using `xml2png` navigate into the data folder and run:
+* `xml2png`
+
+To plot raw data using `xml2png`, navigate into the data folder and run:
 
 `xml2png --type singlet_96 *.xml`
 
+* `quickmodel`
+
+To get delta G esimates from competition assay data using our Bayesian modeling framework via the `quickmodel` script, run:
+
+`env PYTHONPATH="./" quickmodel --inputs 'inputs_Gef_bot'`
+
+or
+
+`env PYTHONPATH="./" quickmodel --inputs 'inputs_Gef_App_bot'`
 

examples/competition-fluorescence-assay/inputs_Gef_App_bot.py

@@ -0,0 +1,20 @@
+import json
+import numpy as np
+
+inputs = {
+    'xml_file_path' :  "./data/Abl_Gef_Ima_copy/",
+    'section'       :  '280_BottomRead',
+    'ligand_order'  :  ['Gef-Ima','Gef-Ima','Gef-Ima','Gef-Ima'],
+    'Lstated'       :  np.array([20.0e-6,9.15e-6,4.18e-6,1.91e-6,0.875e-6,0.4e-6,0.183e-6,0.0837e-6,0.0383e-6,0.0175e-6,0.008e-6,0.0001e-6], np.float64), # ligand concentration
+    'protein'       :  'Abl',
+    'Pstated'       :  0.5e-6 * np.ones([12],np.float64), # protein concentration, M
+    'assay_volume'  :  100e-6, # assay volume, L
+    'well_area'     :  0.3969, # well area, cm^2 for 4ti-0203 [http://4ti.co.uk/files/3113/4217/2464/4ti-0201.pdf]
+    }
+
+inputs['Lstated'] = inputs['Lstated'].tolist()
+inputs['Pstated'] = inputs['Pstated'].tolist()
+
+with open('inputs.json', 'w') as fp:
+    json.dump(inputs, fp)
+

examples/competition-fluorescence-assay/inputs_Gef_bot.py

@@ -0,0 +1,19 @@
+import json
+import numpy as np
+
+inputs = {
+    'xml_file_path' :  "./data/Abl_Gef_copy/",
+    'section'       :  '280_BottomRead',
+    'ligand_order'  :  ['Gefitinib','Gefitinib','Gefitinib','Gefitinib'],
+    'Lstated'       :  np.array([20.0e-6,9.15e-6,4.18e-6,1.91e-6,0.875e-6,0.4e-6,0.183e-6,0.0837e-6,0.0383e-6,0.0175e-6,0.008e-6,0.0001e-6], np.float64), # ligand concentration
+    'protein'       :  'Abl',
+    'Pstated'       :  0.5e-6 * np.ones([12],np.float64), # protein concentration, M
+    'assay_volume'  :  100e-6, # assay volume, L
+    'well_area'     :  0.3969, # well area, cm^2 for 4ti-0203 [http://4ti.co.uk/files/3113/4217/2464/4ti-0201.pdf]
+    }
+
+inputs['Lstated'] = inputs['Lstated'].tolist()
+inputs['Pstated'] = inputs['Pstated'].tolist()
+
+with open('inputs.json', 'w') as fp:
+    json.dump(inputs, fp)

examples/direct-fluorescence-assay/README.md

@@ -9,13 +9,27 @@ Here is a series of ipython notebooks that walks you through simulation and anal
 
 ## Command line tools
 
-To plot raw data using `xml2png` navigate into the data folder and run:
+* `xml2png`
+
+To plot raw data using `xml2png`, navigate into the data folder and run:
 
  `xml2png --type singlet_384 p38*.xml`
 
  or
 
  `xml2png --type singlet_96 Gef*.xml`
 
+* `quickmodel`
+
+To get a deltaG estimate from direct fluorescence data using our Bayesian modeling framework, via the `quickmodel` script run:
+
+  `env PYTHONPATH="./" quickmodel --inputs 'inputs_p38_singlet'`
+
+or
+
+  `env PYTHONPATH="./" quickmodel --inputs 'inputs_Gef_WIP' --type 'spectra'`
+
+The two inputs.py files here are required to run these, but they can be changed if you want to run other types of analyses (different sections of the xml file, different wavelenghts, etc.).
+
 
 

examples/direct-fluorescence-assay/inputs_Gef_WIP.py

@@ -0,0 +1,21 @@
+import json
+import numpy as np
+from glob import glob
+
+inputs = {
+    'xml_file_path' :  "./data/",
+    'file_set'      :  {'Src': glob("./data/Gef*.xml")},
+    'ligand_order'  :  ['Gefitinib','Gefitinib','Gefitinib','Gefitinib'],
+    'section'       :  '280_TopRead',
+    'wavelength'    :  '480',
+    'Lstated'       :  np.array([20.0e-6,9.15e-6,4.18e-6,1.91e-6,0.875e-6,0.4e-6,0.183e-6,0.0837e-6,0.0383e-6,0.0175e-6,0.008e-6,0.0001e-6], np.float64), # ligand concentration
+    'Pstated'       :  0.5e-6 * np.ones([12],np.float64), # protein concentration, M
+    'assay_volume'  :  100e-6, # assay volume, L
+    'well_area'     :  0.3969, # well area, cm^2 for 4ti-0203 [http://4ti.co.uk/files/3113/4217/2464/4ti-0201.pdf]
+    }
+
+inputs['Lstated'] = inputs['Lstated'].tolist()
+inputs['Pstated'] = inputs['Pstated'].tolist()
+
+with open('inputs.json', 'w') as fp:
+    json.dump(inputs, fp)

examples/direct-fluorescence-assay/inputs_p38_singlet.py

@@ -0,0 +1,19 @@
+import json
+import numpy as np
+
+inputs = {
+    'xml_file_path' :  "./data/singlet_copy/",
+    'section'       :  '280_480_TOP_120',
+    'ligand_order'  :  ['Bosutinib','Bosutinib Isomer','Erlotinib','Gefitinib','Ponatinib','Lapatinib','Saracatinib','Vandetanib'],
+    'Lstated'       :  np.array([20.0e-6,14.0e-6,9.82e-6,6.88e-6,4.82e-6,3.38e-6,2.37e-6,1.66e-6,1.16e-6,0.815e-6,0.571e-6,0.4e-6,0.28e-6,0.196e-6,0.138e-6,0.0964e-6,0.0676e-6,0.0474e-6,0.0320e-6,0.0240e-6,0.0160e-6,0.0120e-6,0.008e-6,0.00001e-6], np.float64), # ligand concentration, M
+    'protein'       :  'p38',
+    'Pstated'       :  0.5e-6 * np.ones([24],np.float64), # protein concentration, M
+    'assay_volume'  :  50e-6, # assay volume, L
+    'well_area'     :  0.1369, # well area, cm^2 for 4ti-0203 [http://4ti.co.uk/files/3113/4217/2464/4ti-0201.pdf]
+    }
+
+inputs['Lstated'] = inputs['Lstated'].tolist()
+inputs['Pstated'] = inputs['Pstated'].tolist()
+
+with open('inputs.json', 'w') as fp:
+    json.dump(inputs, fp)