HAL

Authors: Alexander B. Rosenberg , Rupali P. Patwardhan , Jay Shendure , Georg Seelig

Version: 0.1

License: MIT

Contributed by: Jun Cheng , Ziga Avsec

Cite as: https://doi.org/10.1016/j.cell.2015.09.054

Trained on: MPRA data of 2M synthetic alternatively spliced mini-genes

Model from Rosenberg et al: Learning the Sequence Determinants of Alternative Splicing from Millions of Random Sequences

Create a new conda environment with all dependencies installed

kipoi env create HAL
source activate kipoi-HAL

Install model dependencies into current environment

kipoi env install HAL

Test the model

kipoi test HAL --source=kipoi

Make a prediction

cd ~/.kipoi/models/HAL
kipoi predict HAL \
  --dataloader_args='{'gtf_file': 'example_files/hg19.chr22.gtf', 'fasta_file': 'example_files/hg19.chr22.fa'}' \
  -o '/tmp/HAL.example_pred.tsv'
# check the results
head '/tmp/HAL.example_pred.tsv'

Get the model

import kipoi
model = kipoi.get_model('HAL')

Make a prediction for example files

pred = model.pipeline.predict_example()

Use dataloader and model separately

# setup the example dataloader kwargs
dl_kwargs = {'gtf_file': 'example_files/hg19.chr22.gtf', 'fasta_file': 'example_files/hg19.chr22.fa'}
import os; os.chdir(os.path.expanduser('~/.kipoi/models/HAL'))
# Get the dataloader and instantiate it
dl = model.default_dataloader(**dl_kwargs)
# get a batch iterator
it = dl.batch_iter(batch_size=4)
# predict for a batch
batch = next(it)
model.predict_on_batch(batch['inputs'])

Make predictions for custom files directly

pred = model.pipeline.predict(dl_kwargs, batch_size=4)

Get the model

library(reticulate)
kipoi <- import('kipoi')
model <- kipoi$get_model('HAL')

Make a prediction for example files

predictions <- model$pipeline$predict_example()

Use dataloader and model separately

# Get the dataloader
setwd('~/.kipoi/models/HAL')
dl <- model$default_dataloader(gtf_file='example_files/hg19.chr22.gtf', fasta_file='example_files/hg19.chr22.fa')
# get a batch iterator
it <- dl$batch_iter(batch_size=4)
# predict for a batch
batch <- iter_next(it)
model$predict_on_batch(batch$inputs)

Make predictions for custom files directly

pred <- model$pipeline$predict(dl_kwargs, batch_size=4)

Schema

Inputs

Single numpy array

Name: seq

Shape: ()

Doc: K-mer counts

Targets

Single numpy array

Name: psi

Shape: (1,)

Doc: Predicted 3' psi

Dataloader

Relative path: .

Version: 0.1

Doc: Model from Rosenberg

Authors: Jun Cheng , Ziga Avsec

Type: Dataset

License: MIT

Arguments

gtf_file : file path; Genome annotation GTF file

fasta_file : Reference Genome sequence in fasta format

overhang (optional): Length of sequence overhang to take around splice junction

MISO_AS (optional): Whether the given annotation file is MISO alternative splicing annotation. Default False.

Model dependencies

conda:

numpy

pip:

Dataloader dependencies

conda:

bioconda::pysam
python=3.5

pip: