A supervised learning framework for chromatin loop detection in genome-wide contact maps.
Project description
NOTE: Peakachu (version>=1.1.2) now supports both .hic and .cool formats.
Introduction
Accurately predicting chromatin loops from genome-wide interaction matrices such as Hi-C data is critical to deepening our understanding of proper gene regulation. Current approaches are mainly focused on searching for statistically enriched dots on a genome-wide map. However, given the availability of orthogonal data types such as ChIA-PET, HiChIP, Capture Hi-C, and high-throughput imaging, a supervised learning approach could facilitate the discovery of a comprehensive set of chromatin interactions. Here, we present Peakachu, a Random Forest classification framework that predicts chromatin loops from genome-wide contact maps. We compare Peakachu with current enrichment-based approaches, and find that Peakachu identifies a unique set of short-range interactions. We show that our models perform well in different platforms, across different sequencing depths, and across different species. We apply this framework to predict chromatin loops in 56 Hi-C datasets, and release the results at the 3D Genome Browser.
Citation
Salameh, T.J., Wang, X., Song, F. et al. A supervised learning framework for chromatin loop detection in genome-wide contact maps. Nat Commun 11, 3428 (2020). https://doi.org/10.1038/s41467-020-17239-9
Installation
Peakachu requires Python3 and several scientific packages to run. It is best to first set up the environment using conda and then install Peakachu from PyPI:
conda config --add channels defaults
conda config --add channels bioconda
conda config --add channels conda-forge
conda create -n peakachu cooler numba scikit-learn=1.1.2 joblib=1.1.0
conda activate peakachu
pip install -U peakachu hic-straw==0.0.6
Peakachu should now be installed as a command-line tool within the new environment. Options for all peakachu commands and sub-commands can be accessed with the -h option.
peakachu -h
usage: peakachu [-h] {train,score_chromosome,score_genome,depth,pool} ...
Unveil Hi-C Anchors and Peaks.
positional arguments:
{train,score_chromosome,score_genome,depth,pool}
train Train RandomForest model per chromosome
score_chromosome Calculate interaction probability per pixel for a chromosome
score_genome Calculate interaction probability per pixel for the whole genome
depth Calculate the total number of intra-chromosomal chromatin contacts and select the most appropriate pre-trained model
for you.
pool Print centroid loci from score_genome/score_chromosome output
options:
-h, --help show this help message and exit
Example: predicting loops in GM12878 Hi-C
The following example will download an example cooler file containing the GM12878 Hi-C data at the 10kb resolution, train a series of models using H3K27ac HiChIP interactions, and then predict loops using the trained models.
Data preparation
Peakachu requires the contact map to be a .cool file or a .hic file and any training input to be a text file in bedpe format. Example training data can be found at the training-sets subfolder. Cooler files may be found at the 4DN data portal.
wget http://3dgenome.fsm.northwestern.edu/peakachu/test_file/Rao2014-GM12878-MboI-allreps-filtered.10kb.cool
Train a model and predict loops
It is always a good idea to call the help function immediately before entering a command:
peakachu train -h
usage: peakachu train [-h] [-r RESOLUTION] [-p PATH] [--balance] [-b BEDPE] [-w WIDTH] [--nproc NPROC] [-O OUTPUT]
options:
-h, --help show this help message and exit
-r RESOLUTION, --resolution RESOLUTION
Resolution in bp (default 10000)
-p PATH, --path PATH Path to a .cool URI string or a .hic file.
--balance Whether or not using the ICE/KR-balanced matrix.
-b BEDPE, --bedpe BEDPE
Path to the bedpe file containing positive training set.
-w WIDTH, --width WIDTH
Number of bins added to center of window. default width=5 corresponds to 11x11 windows
--nproc NPROC Number of worker processes that will be allocated for training. (default 4)
-O OUTPUT, --output OUTPUT
Folder path to store trained models.
peakachu train -r 10000 -p Rao2014-GM12878-MboI-allreps-filtered.10kb.cool --balance -O models -b gm12878.mumbach.h3k27ac-hichip.hg19.bedpe
This will train 23 random forest models, each labeled by a chromosome. The model for every chromosome was trained using interactions from all the other 22 chromosomes in the provided bedpe file. The purpose of this is to avoid Peakachu to predict loops from the same map it used for training, without overfitting. To use these models, you may either use the score_chromosome function to predict loops in only one chromosome, or the score_genome function to perform a genome-wide prediction.
peakachu score_chromosome -h
usage: peakachu score_chromosome [-h] [-r RESOLUTION] [-p PATH] [--balance] [-C CHROM] [-m MODEL] [-l LOWER] [-u UPPER]
[--minimum-prob MINIMUM_PROB] [-O OUTPUT]
options:
-h, --help show this help message and exit
-r RESOLUTION, --resolution RESOLUTION
Resolution in bp (default 10000)
-p PATH, --path PATH Path to a .cool URI string or a .hic file.
--balance Whether or not using the ICE/KR-balanced matrix.
-C CHROM, --chrom CHROM
Chromosome label. Only contact data within the specified chromosome will be considered.
-m MODEL, --model MODEL
Path to pickled model file.
-l LOWER, --lower LOWER
Lower bound of distance between loci in bins (default 6).
-u UPPER, --upper UPPER
Upper bound of distance between loci in bins (default 300).
--minimum-prob MINIMUM_PROB
Only output pixels with probability score greater than this value (default 0.5)
-O OUTPUT, --output OUTPUT
Output file name.
peakachu score_chromosome -r 10000 -p Rao2014-GM12878-MboI-allreps-filtered.10kb.cool --balance -O GM12878-chr2-scores.bedpe -C chr2 -m models/chr2.pkl
peakachu pool -r 10000 -i GM12878-chr2-scores.bedpe -o GM12878-chr2-loops.bedpe -t .9
The pool function serves to select the most significant non-redundant results from per-pixel probabilities calculated by the score functions. It is recommended to try different probability thresholds to achieve the best sensitivity-specificity tradeoff. The output is a standard bedpe file with the 7th and the final column containing the predicted probability from the random forest model and the interaction frequency extracted from the contact matrix, respectively, to support further filtering. The results can be visualized in juicebox or higlass by loading as 2D annotations. Here is an example screenshot of predicted GM12878 loops in juicer:
Using Peakachu as a standard loop caller
Models for predicting loops in Hi-C have been trained using CTCF ChIA-PET interactions, H3K27ac HiChIP interactions, and a high-confidence loop set (loops that can be detected by at least two orthogonal methods from CTCF ChIA-PET, Pol2 ChIA-PET, Hi-C, CTCF HiChIP, H3K27ac HiChIP, SMC1A HiChIP, H3K4me3 PLAC-Seq, and TrAC-Loop) as positive training samples, at a variety of read depths. Simply download the appropriate model file and directly run the score_genome/score_chromosome function if you want to detect chromatin loops on your own Hi-C or Micro-C maps.
If you are using Peakachu>=2.0, please select a model from the following table:
Instead, if you are using an older Peakachu version (<2.0), please select a model from this table:
Total intra reads | CTCF Models (10kb) | H3K27ac Model (10kb) |
---|---|---|
2 billion | CTCF total | H3K27ac total |
1.8 billion | CTCF 90% | H3K27ac 90% |
1.6 billion | CTCF 80% | H3K27ac 80% |
1.4 billion | CTCF 70% | H3K27ac 70% |
1.2 billion | CTCF 60% | H3K27ac 60% |
1 billion | CTCF 50% | H3K27ac 50% |
800 million | CTCF 40% | H3K27ac 40% |
600 million | CTCF 30% | H3K27ac 30% |
400 million | CTCF 20% | H3K27ac 20% |
200 million | CTCF 10% | H3K27ac 10% |
30 million | CTCF 1.5% | H3K27ac 1.5% |
To make it clear, let's download another Hi-C dataset:
wget -O SKNAS-MboI-allReps-filtered.mcool -L https://www.dropbox.com/s/f80bgn11d7wfgq8/SKNAS-MboI-allReps-filtered.mcool?dl=0
Peakachu provides a handy function peakachu depth
to extract the total number of intra-chromosomal pairs in your data and help you select the most appropriate pre-trained model:
peakachu depth -p SKNAS-MboI-allReps-filtered.mcool::resolutions/1000000
The output of above command will be:
num of intra reads in your data: 141955751
num of intra reads in a human with matched sequencing coverage: 139325229
suggested model: 150 million
Therefore, we recommend using the 7.5% models (trained with ~150 million intra reads) to predict loops on this data.
peakachu score_genome -r 10000 --balance -p SKNAS-MboI-allReps-filtered.mcool::resolutions/10000 -O SKNAS-peakachu-10kb-scores.bedpe -m high-confidence.150million.10kb.w6.pkl
peakachu pool -r 10000 -i SKNAS-peakachu-10kb-scores.bedpe -o SKNAS-peakachu-10kb-loops.0.95.bedpe -t 0.95
Not just Hi-C
In addition to Hi-C, Peakachu has also been trained on other 3D genomic platforms with good results, including Micrco-C (Krietenstein et al. 2020), DNA SPRITE (Quinodoz et al. 2018), ChIA-PET (Fullwood et al. 2009), HiChIP (Mumbach et al. 2016), TrAC-loop (Lai et al. 2018), and HiCAR (Wei et al. 2022), etc.
If you want to predict loops on HiCAR contact matrices, please select a model from the following table. The models were trained with a high-confidence loop set and a series of downsampled versions of a HiCAR dataset in H1ESC cells. As these models were trained using the raw contact values (rather than the ICE-normalized contact values as we did for Hi-C), please do not specify "--balance" when you run "peakachu score_genome" or "peakachu score_chromosome".
If you want to predict loops on TrAC-loop contact matrices, please select a model from the following table. The models were trained with a high-confidence loop set and a series of downsampled versions of a TrAC-loop dataset in H1ESC cells. Again, do not specify "--balance" when you run "peakachu score_genome" or "peakachu score_chromosome".
If you want to predict chromatin loops on CTCF ChIA-PET contact matrices, please select a model from the following table. The models were trained with a high-confidence loop set and downsampled versions of a CTCF ChIA-PET dataset in H1ESC cells. Do not specify "--balance" when you run "peakachu score_genome" or "peakachu score_chromosome".
If you want to predict loops on Pol2 (RNA Polymerase II) ChIA-PET contact matrices, please select a model from the following table. The models were trained with a high-confidence loop set and downsampled versions of a Pol2 ChIA-PET dataset in WTC11 cells. Do not specify "--balance" when you run "peakachu score_genome" or "peakachu score_chromosome".
If you want to predict loops on H3K27ac HiChIP/PLAC-Seq contact matrices, please select a model from the following table. The models were trained with a high-confidence loop set and downsampled versions of a H3K27ac HiChIP dataset in GM12878 cells. Do not specify "--balance" when you run "peakachu score_genome" or "peakachu score_chromosome".
If you want to predict loops on H3K4me3 HiChIP/PLAC-Seq contact matrices, please select a model from the following table. The models were trained with a high-confidence loop set and downsampled versions of a H3K4me3 PLAC-Seq dataset in GM12878 cells. Do not specify "--balance" when you run "peakachu score_genome" or "peakachu score_chromosome".
If you want to predict loops on CTCF HiChIP/PLAC-Seq contact matrices, please select a model from the following table. The models were trained with a high-confidence loop set and downsampled versions of a CTCF HiChIP dataset in GM12878 cells. Do not specify "--balance" when you run "peakachu score_genome" or "peakachu score_chromosome".
If you want to predict loops on SMC1A HiChIP/PLAC-Seq contact matrices, please select a model from the following table. The models were trained with a high-confidence loop set and downsampled versions of a SMC1A HiChIP dataset in GM12878 cells. Do not specify "--balance" when you run "peakachu score_genome" or "peakachu score_chromosome".
Release Notes
Version 2.1 (11/28/2022)
- Fixed a bug regarding model training using the raw contact values
Version 2.0 (09/06/2022)
- Re-trained the models using the latest scikit-learn v1.1.2
- Used the distance-normalized signals instead of original contact signals
- Added a 2D Gaussian filter followed by min-max scaling to pre-process each training image
- Optimized the computation efficiency using numba and matrix operations.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.