JonathanShor / DoubletDetection

Doublet detection in single-cell RNA-seq data.

Home Page:https://doubletdetection.readthedocs.io/en/stable/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Loading in raw matrix

BridgetPK opened this issue · comments

Hi,
The current notebook tutorial shows using the h5 file rather than the matrix.mtx. However, the code on the readme shows that you can use the matrix by loading in as raw counts per the code below. When I do this, I get an error that states "ValueError: could not convert string to float: 'matrix.mtx'". Can you please provide info/code on how to load in the matrix? I am working with a dataset where I do not have the h5 file.

raw_counts is a cells by genes count matrix

labels = clf.fit(raw_counts).predict()

what is the format that you have? Scanpy has a number of ways to load data in the anndata format, which could then be used exactly as in the tutorial.

https://scanpy.readthedocs.io/en/stable/api.html#reading

Closing this issue due to inactivity.