This project is about an article published on Nature Method, and the url of this article is here. This article gives us an efficient method about clustering biology information. I reproducted the sources based on the method that the article gave, and I published these on the Github. If there are any mistakes, please point out them for me. I will thank this so much.
If you want to run this project, you are supposed to git clone this project firstly. This project also needs the data set provided by the author of this article, and you can login this website to download the data set.
You have to name the dataSet after "scRNAseq_CountTable.csv" whatever the original name of the data set is.
Now, you have got the data set. We suppose that you have clone this project, and this project consists of three packages:PCA, Units and kmaneslib respectively. You are supposed to move the data set to the same folder that those packages located in.
At last, you can open your cmd and type python ./Units/SC3Unit.py. This program needs about 4.5 hours to run.
I also write a blog about this project published on my blog, you can click hereto know more, and welcome to visit my personal blog IL MARE