Trevor Tanner
Trevor Tanner
Since docassemble seems amenable for collecting personally identifiable information, I am just curious if it has had any formal security audits.
I was just looking at the ["Source code for elasticluster.providers.gce"](http://elasticluster.readthedocs.org/en/latest/_modules/elasticluster/providers/gce.html) page and it appears that there isn't any native support for [startup scripts](https://cloud.google.com/compute/docs/startupscript). Such functionality would, of course, be very...
As a YANK newbie, it seems the existing ligand parameterization pipeline doesn't use any ab initio QM calculations. Since Schrodinger runs their force field builder and Jaguar to fill in...
LogP calculations for the 50k dataset. Same order as original SMILES file.
For schedulers like SLURM,[ preemptible jobs](https://slurm.schedmd.com/preempt.html) are really nice. Many University computing resources have a lot of spare computing power for preemptible jobs and having functionality from future.batchtools to support...
It would just be nice to have a pseudo-substructure search available on fingerprints with the asymmetric tversky similarity metric.
I was just trying to test SCITE on an extremely sparse genotype matrix, but it fails with "Segmentation fault: 11". A copy of my test data may be found here...
It would be really nice, especially for large files, if pdbio could run in a fast, parallelized mode.
The unlearning challenge could benefit from accounting for the impact of network architecture and training methods on unlearning performance. Some neural network architectures and training methods, like [recursive cortical networks](https://towardsdatascience.com/examining-the-performance-of-rcns-on-popular-datasets-1d6a2a8852c1)...