selene
selene copied to clipboard
FunctionLab
a framework for training sequence-level deep learning networks
Selene encounters an error when the user provides an empty bed file as input to `get_predictions_for_bed_file` (or an empty fasta file for `get_predictions_for_fasta_file`). Specifically, the value `i` (as used on...
From discussion with @aaronkw & others. This will be an optional parameter that results in added column outputs for TSV/HDF5 labels file in variant effect prediction. Users can specify whether...
In the yml configuration file for `quickstart_training` tutorial, it specifies that `male.hg19.fasta` should be used as the reference sequence, but the archive from zenodo (https://zenodo.org/record/1319886/files/selene_quickstart_tutorial.tar.gz) includes `hg19.fasta`. Interestingly, this file...
We would like to add a method to the API (that can be used through Selene's CLI) that can help user create a model directory formatted correctly for export to...
PR #58 allows users to use the `selene_sdk.samplers.file_samplers.MatFileSampler` for models that predict on continuous-valued outputs (e.g. regression models). Before this PR, the MatFileSampler only supported integer labels, and all other...
At present, Selene assumes chromosomal linearity. Many prokaryotes have circular chromosomes. In the case of circular chromosomes, Selene should allow a sequence feature to wrap from the chromosome "end" in...
Currently, we only assign labels to the center "bin" of the sequence. With larger sequence contexts, we may want to retrieve the labels for multiple bins in a sequence to...
This is needed to begin supporting more RNA and protein sequence models.
Add code for in silico mutagenesis and test cases. This method should be able to accept an input sequence and output sequences where N=1 number of bases have been mutated...
This is something I'd like to consider implementing, in the hopes that it would be used in one of the examples for the paper. It might not be necessary, but...
Metadata
Owner
Metadata
a framework for training sequence-level deep learning networks