DDIMDL icon indicating copy to clipboard operation
DDIMDL copied to clipboard

Published 20 hours ago • verified publisher icon YifanDengWHU

Request of Raw Data set

Open asadkhanmaharvi opened this issue 4 years ago • 5 comments

Hye hope so you are doing well, can you share with us a raw data that is purely available on DrugBank rather than these 4 processes tables? Thank you I am waiting for a positive response from your side.

asadkhanmaharvi avatar Sep 17 '20 11:09 asadkhanmaharvi

Hi. What does raw data mean? I collected data from DrugBank with a spider program. After the collection, the data is nearly the same as you see in the current database. What I mainly do is to clean some of the data to make them work better. For example, some drug pairs may have multi labels (at that time, it seems that they don't have multi labels now) so we remove them. I don't think the raw data with noise will help you. If you want, I can upload the spider program to the repo and you can collect data on your own.

YifanDengWHU avatar Sep 17 '20 12:09 YifanDengWHU

raw means is data in the actual form is not available as we download the dataset from Kaggle etc. are you grab data with web scrapping means interaction from drug bank.

asadkhanmaharvi avatar Sep 17 '20 12:09 asadkhanmaharvi

Hi, I have uploaded the spider program. You can see the code and collect the raw data.

YifanDengWHU avatar Sep 17 '20 13:09 YifanDengWHU

Just FYI the Drug Interactions are available in a downloadable XML file here: https://go.drugbank.com/releases/latest. It should be pretty straightforward to parse out.

cknoxrun avatar Oct 06 '20 21:10 cknoxrun

Just FYI the Drug Interactions are available in a downloadable XML file here: https://go.drugbank.com/releases/latest. It should be pretty straightforward to parse out.

Thanks for the official answer!

YifanDengWHU avatar Oct 07 '20 03:10 YifanDengWHU