This dataset contains term names and estimates for logistic regression model to predict chromatin looping interactions. The estimate represent an average of the 10 best performing models out of 124 transcription factor ChIP-seq data sets from ENCODE.
modelBest10Avg
An object of class data.frame with 7 rows and 2 columns
holding the term name and estimate.
The intercept of the logistic regression model.
The genomic distance between the centers of motifs in base pairs (bp).
Orientation of motif pairs. 1 if divergent 0 if not.
Orientation of motif pairs. 1 if forward 0 if not.
Orientation of motif pairs. 1 if reverse 0 if not.
Minimum of motif hit score between both motifs in pair. The motif score is defined as -log_10 of the p-value of the motif hit as reported by JASPAR motif tracks. The unit is -log_10(p) where p is the p-value of the motif hit.
Pearson correlation coefficient of ChIP-seq signals across +/- 500 bp around CTCF motif centers.
Each of 124 transcription factor (TF) ChIP-seq data sets from ENCODE in
GM12878 cells were used to train a logistic regression model. All CTCF motifs
in motif.hg19.CTCF within a distance of 1 Mb were used as
candidates. A given pair was labled as true loop interactions, if it has
interaction support based on loops from Hi-C in human GM12878 cells from Rao
et al. 2014 or ChIA-PET loops from Tang et al. 2015 in the same cell type.
The 10 best performing models were selected based on the average area under
the precision-recall-curve in 10-fold cross-validation.
The parameters were than averaged across the 10 best performig models.
Suhas S.P. Rao, Miriam H. Huntley, Neva C. Durand, Elena K. Stamenova, Ivan D. Bochkov, James T. Robinson, Adrian L. Sanborn, Ido Machol, Arina D. Omer, Eric S. Lander, Erez Lieberman Aiden, A 3D Map of the Human Genome at Kilobase Resolution Reveals #' Principles of Chromatin Looping, Cell, Volume 159, Issue 7, 18 December 2014, Pages 1665-1680, ISSN 0092-8674, https://doi.org/10.1016/j.cell.2014.11.021.
Zhonghui Tang, Oscar Junhong Luo, Xingwang Li, Meizhen Zheng, Jacqueline Jufen Zhu, Przemyslaw Szalaj, Pawel Trzaskoma, Adriana Magalska, Jakub Wlodarczyk, Blazej Ruszczycki, Paul Michalski, Emaly Piecuch, Ping Wang, Danjuan Wang, Simon Zhongyuan Tian, May Penrad-Mobayed, Laurent M. Sachs, Xiaoan Ruan, Chia-Lin Wei, Edison T. Liu, Grzegorz M. Wilczynski, Dariusz Plewczynski, Guoliang Li, Yijun Ruan, CTCF-Mediated Human 3D Genome Architecture Reveals Chromatin Topology for Transcription, Cell, Volume 163, Issue 7, 17 December 2015, Pages 1611-1627, ISSN 0092-8674, https://doi.org/10.1016/j.cell.2015.11.024.