Updated README

anurag
1 parent 0b1de22152
Showing 1 changed file with 13 additions and 1 deletions Show diff stats
README
 ###### Decription of the files on GitHub ######
  
-1) nbi_simulation_new_for_git.ipynb : The NBI code snippet contains comments that would help the researchers with their own data. All the researchers have to do is upload their DTIs (as given in the new_dt_from_go_and_db_unique_latest.csv) and run the python code.
+1) nbi_simulation_new_for_git.ipynb : The NBI code snippet contains comments that would help the researchers with their own data. All the researchers have to do is upload their DTIs (GO mapped) and run the python code.
 				      The code will first generate an adjacent matrix using the input file and then create a prediction matrix called NBIscore which will be a m x n matrix.
 				      The output file (predicted_targets_for_all_drugs_using_percent_diff_0.20_new.csv) will be created which will contain predicted DTIs having scores within 20% of the max score for each Target.
  
@@ -14,3 +14,15 @@
 5) predicted_targets_for_all_drugs_using_percent_diff_0.20_new.csv: This is the final output file generated using our input file and contains the prioritized list of predicted DTIs with the predicted scores.
 								    If you are uploading your own input file containing the DTIs, you might need to change the name of the output file in the python code provided.
  
+IMPORTANT POINTS:
+
+1) Since we are not providing the GO mapping algorithm here (in-house script), while using your own DTI files to get predictions you would have to first map the GO terms with the targets. Here are the steps:
+
+a) A GO <=> Uniprot ID mapping file is provided here (uniprot_go_annotations_mf_strong_evidence_new.csv)
+b) First identify which targets in your DTI list share the same GO terms using the file above
+c) Then create a new DTI by assigning same drugs to all the proteins that share the same GO term
+d) Make a unique list of DTIs as provided in the uniprot_go_annotations_mf_strong_evidence_new.csv file to be used as an input to NBI
+
+2) The file uniprot_go_annotations_mf_strong_evidence_new.csv provided by us is already GO mapped and can be used directly in the code.
+
+
1	1	###### Decription of the files on GitHub ######
2	2
3		-1) nbi_simulation_new_for_git.ipynb : The NBI code snippet contains comments that would help the researchers with their own data. All the researchers have to do is upload their DTIs (as given in the new_dt_from_go_and_db_unique_latest.csv) and run the python code.
	3	+1) nbi_simulation_new_for_git.ipynb : The NBI code snippet contains comments that would help the researchers with their own data. All the researchers have to do is upload their DTIs (GO mapped) and run the python code.
4	4	The code will first generate an adjacent matrix using the input file and then create a prediction matrix called NBIscore which will be a m x n matrix.
5	5	The output file (predicted_targets_for_all_drugs_using_percent_diff_0.20_new.csv) will be created which will contain predicted DTIs having scores within 20% of the max score for each Target.
6	6
...	...	@@ -14,3 +14,15 @@
14	14	5) predicted_targets_for_all_drugs_using_percent_diff_0.20_new.csv: This is the final output file generated using our input file and contains the prioritized list of predicted DTIs with the predicted scores.
15	15	If you are uploading your own input file containing the DTIs, you might need to change the name of the output file in the python code provided.
16	16
	17	+IMPORTANT POINTS:
	18	+
	19	+1) Since we are not providing the GO mapping algorithm here (in-house script), while using your own DTI files to get predictions you would have to first map the GO terms with the targets. Here are the steps:
	20	+
	21	+a) A GO <=> Uniprot ID mapping file is provided here (uniprot_go_annotations_mf_strong_evidence_new.csv)
	22	+b) First identify which targets in your DTI list share the same GO terms using the file above
	23	+c) Then create a new DTI by assigning same drugs to all the proteins that share the same GO term
	24	+d) Make a unique list of DTIs as provided in the uniprot_go_annotations_mf_strong_evidence_new.csv file to be used as an input to NBI
	25	+
	26	+2) The file uniprot_go_annotations_mf_strong_evidence_new.csv provided by us is already GO mapped and can be used directly in the code.
	27	+
	28	+
...	...