I am working on a small data frame, (result, element1, element2), and I want to correlate the impact of these elements on the result using python. These elements are amino acids residue and result is the binding affinity. I am new to this topic, I have no idea where to begin with.
9.9 Trp Trp 9.2 Phe Phe 9.2 Trp Phe 9.1 Phe Trp 9.1 Trp Arg 8.9 Arg Trp 8.9 Gln Trp 8.9 Trp Ala 8.9 Tyr Trp 8.8 Ala Trp
I just finished creating the data frame.
you can simply use one of the KNN methods and then measure the Euclidian distance to have the closest to the centroid.
if you send me more detailed data I may help you.
The database that I'm working on it. Each drug candidate has some attributes such as the presence specific amino acid residue, the surface, the volume, the binding affinity, the calculated logP also can be added and etc. V0L is the drug that I'm trying to propose some alternative for. I want to systematically pick some of that fit in the best in all of area, via correlating these data.
really appreciate it Dr. Saad Hameed Abid
- Badges
- Science topic