Comments (4)
It looks like there's a bug in the trim code. I uploaded a new version of the script that should fix it.
from basset.
Looks better thanks!
The TOMTOM html report is now generated nicely.
However, still worrying messages from the log ... :
Processing query 235 out of 235
Estimating pi_0 from all 1468 observed p-values.
Estimating pi_0.
Estimated pi_0=1
/home/ron/anaconda2/lib/python2.7/site-packages/sklearn/preprocessing/data.py:167: UserWarning: Numerical issues were encountered when centering the data and might not be solved. Dataset may contain too large values. You may need to prescale your features.
warnings.warn("Numerical issues were encountered "
/home/ron/anaconda2/lib/python2.7/site-packages/sklearn/preprocessing/data.py:184: UserWarning: Numerical issues were encountered when scaling the data and might not be solved. The standard deviation of the data is probably very close to 0.
warnings.warn("Numerical issues were encountered "
basset_motifs_predict.lua dnase_with_prim_erythroid_cnn_best.decuda.th motifs_out/sample.h5 motifs_out/model_out.h5
Filter 0
Filter 1
##########################################
Filter 296
Filter 297
Filter 298
Filter 299
6 segments of length 97
6 segments of length 97
Traceback (most recent call last):
File "/home/ron/tools/Basset/src/basset_motifs.py", line 668, in
main()
File "/home/ron/tools/Basset/src/basset_motifs.py", line 192, in main
plot_filter_seg_heat(filter_outs, '%s/filter_segs_raw.pdf'%options.out_dir, whiten=False)
File "/home/ron/tools/Basset/src/basset_motifs.py", line 516, in plot_filter_seg_heat
sns.clustermap(filter_seqs[:,seqs_i], metric=dist, row_cluster=True, col_cluster=True, linewidths=0, xticklabels=False, vmin=hmin, vmax=hmax)
File "/home/ron/anaconda2/lib/python2.7/site-packages/seaborn/matrix.py", line 1169, in clustermap
**kwargs)
File "/home/ron/anaconda2/lib/python2.7/site-packages/seaborn/matrix.py", line 1008, in plot
row_linkage=row_linkage, col_linkage=col_linkage)
File "/home/ron/anaconda2/lib/python2.7/site-packages/seaborn/matrix.py", line 941, in plot_dendrograms
axis=1, ax=self.ax_col_dendrogram, linkage=col_linkage)
File "/home/ron/anaconda2/lib/python2.7/site-packages/seaborn/matrix.py", line 684, in dendrogram
label=label, rotate=rotate)
File "/home/ron/anaconda2/lib/python2.7/site-packages/seaborn/matrix.py", line 502, in init
self.dendrogram = self.calculate_dendrogram()
File "/home/ron/anaconda2/lib/python2.7/site-packages/seaborn/matrix.py", line 582, in calculate_dendrogram
color_threshold=-np.inf)
File "/home/ron/anaconda2/lib/python2.7/site-packages/scipy/cluster/hierarchy.py", line 2230, in dendrogram
is_valid_linkage(Z, throw=True, name='Z')
File "/home/ron/anaconda2/lib/python2.7/site-packages/scipy/cluster/hierarchy.py", line 1412, in is_valid_linkage
name_str)
ValueError: Linkage 'Z' contains negative indices.
################
from basset.
I know I've seen that before, but I can't replicate it at the moment. I would guess that one of the filters isn't activating at all and causing the statistical code to choke. I never got much value out of those heat map plots, so I'm going to turn them off by default and keep my eye out for an opportunity to fix the bug next time that I see it.
from basset.
Sorry for the delay and thanks for the workaround, the same example now runs without complaints.
from basset.
Related Issues (20)
- Training aways converges after 2 or 3 epochs HOT 4
- Training takes too long HOT 3
- Pre-trained Weights? HOT 1
- Torch-HDF5 Failure during Writing Output by basset_motifs_predict.lua HOT 3
- First Epoch Loss is Bigger than Expected HOT 2
- Nucleotide Order in Motif Heatmap Reversed HOT 1
- how are filters combined HOT 2
- Error in running basset_sat_vcf.py HOT 1
- Convolutional layers - padding and bias HOT 1
- input and target size mismatch when running test.lua HOT 3
- Citation on README HOT 1
- Prediction tasks specification HOT 1
- install_data.py requires more than 30 GiB of memory HOT 2
- Docker image Lua and Python setups wrong
- how to install 'convnet' module HOT 1
- ENUM error when running basset_train.lua HOT 7
- preprocess_features.py file is generating empty output bed files HOT 2
- bedtools getfasta skipping problem HOT 1
- Used in non human species HOT 1
- Original dataset Basset is trained on HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from basset.