This package contains several pre-trained models for different on-target
activity prediction algorithms to be used in the package crisprScore.
We can access the file paths of the different pre-trained models
directly with named functions:
# For DeepHF model:
DeepWt.hdf5()
## snapshotDate(): 2022-08-23
## see ?crisprScoreData and browseVignettes('crisprScoreData') for documentation
## loading from cache
## EH6123
## "/Users/fortinj2/Library/Caches/org.R-project.R/R/ExperimentHub/f2d463daf223_6166"
DeepWt_T7.hdf5()
## snapshotDate(): 2022-08-23
## see ?crisprScoreData and browseVignettes('crisprScoreData') for documentation
## loading from cache
## EH6124
## "/Users/fortinj2/Library/Caches/org.R-project.R/R/ExperimentHub/f2d43b4f0b0c_6167"
DeepWt_U6.hdf5()
## snapshotDate(): 2022-08-23
## see ?crisprScoreData and browseVignettes('crisprScoreData') for documentation
## loading from cache
## EH6125
## "/Users/fortinj2/Library/Caches/org.R-project.R/R/ExperimentHub/1646f4d5dfe8e_6168"
esp_rnn_model.hdf5()
## snapshotDate(): 2022-08-23
## see ?crisprScoreData and browseVignettes('crisprScoreData') for documentation
## loading from cache
## EH6126
## "/Users/fortinj2/Library/Caches/org.R-project.R/R/ExperimentHub/f2d4425e5f3f_6169"
hf_rnn_model.hdf5()
## snapshotDate(): 2022-08-23
## see ?crisprScoreData and browseVignettes('crisprScoreData') for documentation
## loading from cache
## EH6127
## "/Users/fortinj2/Library/Caches/org.R-project.R/R/ExperimentHub/f2d441bf4323_6170"
# For Lindel model:
Model_weights.pkl()
## snapshotDate(): 2022-08-23
## see ?crisprScoreData and browseVignettes('crisprScoreData') for documentation
## loading from cache
## EH6128
## "/Users/fortinj2/Library/Caches/org.R-project.R/R/ExperimentHub/f2d473d0d08d_6171"
Or we can access them using the ExperimentHub interface:
eh <- ExperimentHub()
## snapshotDate(): 2022-08-23
query(eh, "crisprScoreData")
## ExperimentHub with 9 records
## # snapshotDate(): 2022-08-23
## # $dataprovider: Fudan University, UCSF, University of Washington, New York ...
## # $species: NA
## # $rdataclass: character
## # additional mcols(): taxonomyid, genome, description,
## # coordinate_1_based, maintainer, rdatadateadded, preparerclass, tags,
## # rdatapath, sourceurl, sourcetype
## # retrieve records with, e.g., 'object[["EH6123"]]'
##
## title
## EH6123 | DeepWt.hdf5
## EH6124 | DeepWt_T7.hdf5
## EH6125 | DeepWt_U6.hdf5
## EH6126 | esp_rnn_model.hdf5
## EH6127 | hf_rnn_model.hdf5
## EH6128 | Model_weights.pkl
## EH7304 | CRISPRa_model.pkl
## EH7305 | CRISPRi_model.pkl
## EH7356 | RFcombined.rds
eh[["EH6127"]]
## see ?crisprScoreData and browseVignettes('crisprScoreData') for documentation
## loading from cache
## EH6127
## "/Users/fortinj2/Library/Caches/org.R-project.R/R/ExperimentHub/f2d441bf4323_6170"
For details on the source of these files, and on their construction see
?crisprScoreData and the scripts:
crisprScoreData
Authors: Jean-Philippe Fortin
Installation from Bioconductor
crisprScoreDatacan be installed from the Bioconductor devel branch using the following commands in a fresh R session:Exploring the different data in crisprScoreData
We first load the
crisprScoreDatapackage:This package contains several pre-trained models for different on-target activity prediction algorithms to be used in the package crisprScore.
We can access the file paths of the different pre-trained models directly with named functions:
Or we can access them using the ExperimentHub interface:
For details on the source of these files, and on their construction see
?crisprScoreDataand the scripts:inst/scripts/make-metadata.Rinst/scripts/make-data.Rmd