hemberg-lab / sc3s Goto Github PK
View Code? Open in Web Editor NEWSingle Cell Consensus Clustering with Speed
License: GNU General Public License v3.0
Single Cell Consensus Clustering with Speed
License: GNU General Public License v3.0
would be useful to give an option to run on reduced dimensions that are not PCA
For example 'X_scVI'
Wondering if the data set I'm working with has to have the same structure as the sample data set, I ran into this problem with my own data
Traceback (most recent call last):
File "D:/Code/SC3/SC3s/run.py", line 7, in
sc.pp.filter_genes(adata, min_cells=10)
File "C:\Users\ThinkPad.conda\envs\Tensor1\lib\site-packages\scanpy\preprocessing_simple.py", line 259, in filter_genes
X if min_cells is None and max_cells is None else X > 0, axis=0
TypeError: '>' not supported between instances of 'File' and 'int'
Is there a way to quantify how stable clusters are with different number of runs? We find that in our data, certain clusters are very stable, and appear regardless of how many itterations are performed. The appearance of others seem to vary, even if we do hundreds of itterations, suggesting that the algorithm does converge, which I suppose suggests the number of populations to detect needs to be tuned. Can you suggest any best practices for approaching these types of problems?
Hi Hemberg Lab,
I have an issue when I install sc3s via pip to run alongside scanpy.
After installing, if I attempt to import scanpy in the script, I get the following new error:
---------------------------------------------------------------------------
ImportError Traceback (most recent call last)
<ipython-input-1-5422b1ae3fb8> in <module>
1 import numpy as np
2 import pandas as pd
----> 3 import scanpy as sc
4 sc.settings.verbosity = 3
5 sc.settings.set_figure_params(dpi=100, color_map='OrRd')
~\anaconda3\lib\site-packages\scanpy\__init__.py in <module>
12 # (start with settings as several tools are using it)
13 from ._settings import settings, Verbosity
---> 14 from . import tools as tl
15 from . import preprocessing as pp
16 from . import plotting as pl
~\anaconda3\lib\site-packages\scanpy\tools\__init__.py in <module>
15 from ._leiden import leiden
16 from ._louvain import louvain
---> 17 from ._sim import sim
18 from ._score_genes import score_genes, score_genes_cell_cycle
19 from ._dendrogram import dendrogram
~\anaconda3\lib\site-packages\scanpy\tools\_sim.py in <module>
21 from anndata import AnnData
22
---> 23 from .. import _utils, readwrite, logging as logg
24 from .._settings import settings
25 from .._compat import Literal
~\anaconda3\lib\site-packages\scanpy\readwrite.py in <module>
8 import pandas as pd
9 from matplotlib.image import imread
---> 10 import tables
11 import anndata
12 from anndata import (
~\anaconda3\lib\site-packages\tables\__init__.py in <module>
60 # Import the user classes from the proper modules
61 from .exceptions import *
---> 62 from .file import File, open_file, copy_file
63 from .node import Node
64 from .group import Group
~\anaconda3\lib\site-packages\tables\file.py in <module>
31 import numpy
32
---> 33 from . import hdf5extension
34 from . import utilsextension
35 from . import parameters
ImportError: DLL load failed while importing hdf5extension: The specified procedure could not be found.
I am working with a fresh install of the newest version of anaconda and scanpy.
I have seen on StackOverflow this error can sometimes be resolved by uninstalling and re-installing the tables package. This allowed me to load scanpy again, but when I do a 'b' character is introduced in every member of any dataframe I load, signaling to me an issue with decoding.
Furthermore, this error with scanpy is not resolved by uninstalling sc3s. The only solution I could find that worked was to uninstall and re-install anaconda from scratch, though a more experienced troubleshooter may have found a simpler one.
Please let me know if anything can be done to resolve this or if you have any further questions for me.
Thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.