| Title: | Pre-trained random forest models obtained using preciseTAD |
|---|---|
| Description: | An experimentdata package to supplement the preciseTAD package containing pre-trained models and the variable importances of each genomic annotation used to build the model parsed into list objects and available in ExperimentHub. In total, preciseTADhub provides access to n=84 random forest classification models optimized to predict TAD/chromatin loop boundary regions and stored as .RDS files. The value, n, comes from the fact that we considered l=2 cell lines {GM12878, K562}, g=2 ground truth boundaries {Arrowhead, Peakachu}, and c=21 autosomal chromosomes {CHR1, CHR2, ..., CHR22} (omitting CHR9). Furthermore, each object is itself a two-item list containing: (1) the model object, and (2) the variable importances for CTCF, RAD21, SMC3, and ZNF143 used to predict boundary regions. Each model is trained via a "holdout" strategy, in which data from chromosomes {CHR1, CHR2, ..., CHRi-1, CHRi+1, ..., CHR22} were used to build the model and the ith chromosome was reserved for testing. See https://doi.org/10.1101/2020.09.03.282186 for more detail on the model building strategy. |
| Authors: | Spiro Stilianoudakis [aut], Mikhail Dozmorov [aut, cre] |
| Maintainer: | Mikhail Dozmorov <[email protected]> |
| License: | MIT + file LICENSE |
| Version: | 1.20.0 |
| Built: | 2026-10-10 11:17:34 UTC |
| Source: | https://github.com/bioc/preciseTADhub |
list objects.preciseTADhub is package that give users access to pre-trained random forest
models that can be leveraged to predict TAD and/or chromatin loop boundaries
using the preciseTAD R package. These data have been parsed into list
objects and RDS files and are available in ExperimentHub.
See the vignette for examples of using these data in predicting precise boundary location at base-level resolution.
browseVignettes("preciseTADhub")
Details of how these data were created are in the scripts/ directory of the source package.
## Not run: library(ExperimentHub) eh <- ExperimentHub() myfiles <- query(eh, "preciseTADhub") CHR1_GM12878_5kb_Arrowhead <- myfiles[[1]] ## End(Not run)## Not run: library(ExperimentHub) eh <- ExperimentHub() myfiles <- query(eh, "preciseTADhub") CHR1_GM12878_5kb_Arrowhead <- myfiles[[1]] ## End(Not run)
preciseTAD::TADrandomForest, built on cell-line
specific CTCF, RAD21, SMC3, and ZNF143 ChIP-seq peak regions.A wrapper function for efficiently reading in user-specified random forest
models generated by preciseTAD::TADrandomForest, built on cell-line
specific CTCF, RAD21, SMC3, and ZNF143 ChIP-seq peak regions.
readEH(chr, cl, gt, source)readEH(chr, cl, gt, source)
chr |
Which chromosome was used as the holdout during the training process. That is, all other chromosomes were combined when building the random forest. |
cl |
The cell line that was used (either "GM12878" or "K562") |
gt |
The ground-truth TAD or chromatin loop boundaries used to construct the binary response vector (either "Arrowhead" or "Peakachu". |
source |
The source of the files stored on ExperimentHub using query(hub, "package_name"). |
A trained model object from caret
# Suppose we want to read in the model that was built using CHR1-CHR21, # on GM12878, using Arrowhead defined TAD boundaries at 5kb resolution. #Initialize ExperimentHub library(ExperimentHub) hub <- ExperimentHub() query(hub, "preciseTADhub") myfiles <- query(hub, "preciseTADhub") CHR22_GM12878_5kb_Arrowhead <- readEH(chr = "CHR22", cl = "GM12878", gt = "Arrowhead", source = myfiles)# Suppose we want to read in the model that was built using CHR1-CHR21, # on GM12878, using Arrowhead defined TAD boundaries at 5kb resolution. #Initialize ExperimentHub library(ExperimentHub) hub <- ExperimentHub() query(hub, "preciseTADhub") myfiles <- query(hub, "preciseTADhub") CHR22_GM12878_5kb_Arrowhead <- readEH(chr = "CHR22", cl = "GM12878", gt = "Arrowhead", source = myfiles)