-
The default doc_m2m_threshold is 0.05 according to the global options, but it seems to be 0.01 in the newer experiment. In the network, 0.05 is prefilled and thus the degrees do not match within the m…
-
For a ConvNet it can be interesting to find the norm-bounded input that maximizes the activity of a single conv. filter as a way to [visualize the filters](http://igva2012.wikispaces.asu.edu/file/view…
-
We can automatically analyse the molecular network and try to find clusters that potentially correspond to xenobiotic compounds. Perhaps this can be used for the motifs from LDA as well.
The cytosc…
-
Hi,
As mentioned in my comment in issue #820 , I'm not able to run `Tests/test_KDTree.py` or the related class in the `Bio` folder.
Following @peterjc suggestion, I've run the `python setup.py i…
-
I've been using DragoNN to create homework problems for my bioinformatics class, and it has really excellent overall. There were two aspects of simulating data that confused me at first and could per…
-
http://biorxiv.org/content/biorxiv/early/2016/05/27/055715.full.pdf
> Recent technological advances have enabled assaying DNA methylation in single cells. Current protocols are limited by incomplet…
-
New Issue for sst-elements
--------------------------
1 - Detailed description of problem or enhancement
Ember FFT3D is failing on the latest devel branch.
sst: mpi/motifs/emberfft3d.cc:273: v…
-
https://doi.org/10.1101/103929
> Motivation: Comparing the human genome to the genomes of closely related mammalian species has been a powerful tool for discovering functional elements in the human…
-
Hello,
I've tried cMonkey2 on my dataset with the following command but it gives me an error that you can see below. Could you please help me with this? Thanks.
./cmonkey.py --organism mtu --ratios …
-
Hello!
I was looking my network weights, when I realize that all my bias values on a Dense layer were 0s. I saw on the Dense Layer initialization: self.b = shared_zeros((self.output_dim)). Shouldn't …