Command Line Tools

sequence_unet also contains several convinience scripts to help work with trained models.

sequence_unet

Generate model predictions from Sequence UNET like models.

Three modes are supported:

ClinVar: Use –proteinnet path/to/protiennet, –clinvar and –tsv path/to/clinvar_tsv where: the ClinVar TSV is formated like the output of extract_clinvar.R. The ProteinNet file must contain the PDB ids specified in the TSV for predictions to be generated for them.
Fasta: Use –fasta path/to/fasta and optionally –tsv to specify a list of variants: to keep predictions for, where the TSV has columns gene, position, wt, mut and genes match the fasta IDs.
ProteinNet: Use –proteinnet path/to/protiennet and optionally –tsv path/to/tsv to specify: predictions to keep, where the TSV has columns pdb_id, chain, position, wt, mut.

usage: sequence_unet [-h] [--tsv TSV] [--proteinnet PROTEINNET]
                     [--fasta FASTA] [--contacts] [--layers LAYERS] [--wide]
                     [--pssm] [--model_dir MODEL_DIR] [--download]
                     M

Positional Arguments

M: Model to predict with

Input Data

--tsv, -t: TSV file containing variants of interest
--proteinnet, -p: ProteinNet file
--fasta, -f: Fasta file

Options

--contacts, -c

Use contact graph input

Default: False

--layers, -l

Number of layers in bottom UNET model

Default: 6

--wide, -w

Output a wide table

Default: False

--pssm, -s

Convert output frequency predictions to PSSMs

Default: False

--model_dir, -m

Directory to locate/download model files to

--download, -d

Download model if not located

Default: False

filter_fasta

Filter a Fasta file to only include records based on a list of IDs

usage: filter_fasta [-h] [--gzip] [--uniprot] [--iupac] F I

Positional Arguments

F: Fasta file
I: File containing a list of IDs

Named Arguments

--gzip, -g

Fasta file is gzipped

Default: False

--uniprot, -u

Fasta file is Uniprot formatted and ID list contains Uniprot IDs

Default: False

--iupac, -i

Filter to only include cannonical amino acids

Default: False

split_fasta

Split a fasta file into sub-files

usage: split_fasta [-h] [--outdir OUTDIR] [--files FILES] [--seqs SEQS] F

Positional Arguments

F: Fasta file to split

Named Arguments

--outdir, -o

Output directory

Default: “.”

--files, -n

Number of files to split into

Default: 0

--seqs, -s

Number of sequences per file

Default: 0