DeepSequence
DeepSequence copied to clipboard
debbiemarkslab
A generative latent variable model for biological sequence families.
Hi there, I'm trying out mutations on a DeepSequence model trained on BLAST_ECOLX. What should be neutral mutations do not seem to give neutral results. For example: `data_helper.delta_elbo(ds_model,[], N_pred_iterations=500)` gives...
Score a whole collection of DMSs, using a CSV containing (DMS file,MSA,mutant_column) mappings. Useful for running e.g. 80 DMSs together.
helper.py: added save_weights and calc_weights Removed default theta (make sure to provide theta when calculating weights) added extra hardcoded datasets loading dataset from alignments_dir instead if specified
Hi, Really appreciate your work, it is very helpful to what I am working on right now. I am kinda newbie in deep learning of protein sequences, forgive me if...
In your dataloader, you have the following lines: ``` self.alphabet = "ACDEFGHIKLMNPQRSTVWY" self.reorder_alphabet = "DEKRHNQSTPGAVILMCFYW" ``` Could you please comment on this alphabet reordering? I guess the ordering orders them...
Hello，I have a question in _Mutation Effect Prediction.ipynb_. When predicting the effects of mutation for a single mutation in PABP, for example [(126,"G","A")], like this: `pabp_data_helper.delta_elbo(pabp_vae_model,[(126,"G","A")], N_pred_iterations=500)` In the function...
Hello, I'm hoping to use DeepSequence to predict the effects of mutations, but can't find an example for how to train a model for alignments other than those tested in...
Metadata
Owner
Metadata
A generative latent variable model for biological sequence families.