#我这里直接从GEO里面下载了peaks结果，它们详情如下：wc -l *bed
6768 GSM1278641_Xu_MUT_rep1_BAF155_MUT.peaks.bed
3660 GSM1278643_Xu_MUT_rep2_BAF155_MUT.peaks.bed
11022 GSM1278645_Xu_WT_rep1_BAF155.peaks.bed
5260 GSM1278647_Xu_WT_rep2_BAF155.peaks.bed
49458 GSM601398_Ini1HeLa-peaks.bed
24477 GSM601398_Ini1HeLa-peaks-stringent.bed
12725 GSM601399_Brg1HeLa-peaks.bed
12316 GSM601399_Brg1HeLa-peaks-stringent.bed
46412 GSM601400_BAF155HeLa-peaks.bed
37920 GSM601400_BAF155HeLa-peaks-stringent.bed
30136 GSM601401_BAF170HeLa-peaks.bed
25432 GSM601401_BAF170HeLa-peaks-stringent.bed

每个BED的peaks记录，本质是就3列是需要我们注意的，就是染色体，以及在该染色体上面的起始和终止坐标，如下：

#PeakID chr start end strand Normalized Tag Count region size findPeaks Score Clonal Fold Change
chr20 52221388 52856380 chr20-8088 41141 +
chr20 45796362 46384917 chr20-5152 31612 +
chr17 59287502 59741943 chr17-2332 29994 +
chr17 59755459 59989069 chr17-667 19943 +
chr20 52993293 53369574 chr20-7059 12642 +
chr1 121482722 121485861 chr1-995 9070 +
chr20 55675229 55855175 chr20-6524 7592 +
chr3 64531319 64762040 chr3-4022 7213 +
chr20 49286444 49384563 chr20-4482 6165 +

我们所谓的peaks注释，就是想看看该peaks在基因组的哪一个区段，看看它们在各种基因组区域(基因上下游，5,3端UTR，启动子，内含子，外显子，基因间区域，microRNA区域)分布情况，但是一般的peaks都有近万个，所以需要批量注释，如果脚本学的好，自己下载参考基因组的GFF注释文件，完全可以自己写一个，我这里会介绍一个R的bioconductor包ChIPpeakAnno来做CHIP-seq的peaks注释，下面的包自带的示例：

library(ChIPpeakAnno)
bed <- system.file("extdata", "MACS_output.bed", package="ChIPpeakAnno")
gr1 <- toGRanges(bed, format="BED", header=FALSE)
## one can also try import from rtracklayer
library(rtracklayer)
gr1.import <- import(bed, format="BED")
identical(start(gr1), start(gr1.import))
gr1[1:2]
gr1.import[1:2] #note the name slot is different from gr1
gff <- system.file("extdata", "GFF_peaks.gff", package="ChIPpeakAnno")
gr2 <- toGRanges(gff, format="GFF", header=FALSE, skip=3)
ol <- findOverlapsOfPeaks(gr1, gr2)
makeVennDiagram(ol)

##还可以用binOverFeature来根据特定的GRanges对象(通常是TSS)来画分布图
## Distribution of aggregated peak scores or peak numbers around transcript start sites.

可以看到这个包使用起来非常简单，只需要把我们做好的peaks文件(GSM1278641_Xu_MUT_rep1_BAF155_MUT.peaks.bed等等)用toGRanges或者import读进去，成一个GRanges对象即可，上面的代码是比较两个peaks文件的overlap。然后还可以根据R很多包都自带的数据来注释基因组特征：

data(TSS.human.GRCh37) ## 主要是借助于这个GRanges对象来做注释，也可以用getAnnotation来获取其它GRanges对象来做注释
## featureType ： TSS, miRNA, Exon, 5'UTR, 3'UTR, transcript or Exon plus UTR
peaks=MUT_rep1_peaks
macs.anno <- annotatePeakInBatch(peaks, AnnotationData=TSS.human.GRCh37,
output="overlapping", maxgap=5000L)

## 得到的macs.anno对象就是已经注释好了的，每个peaks是否在基因上，或者距离基因多远，都是写的清清楚楚
if(require(TxDb.Hsapiens.UCSC.hg19.knownGene)){
aCR<-assignChromosomeRegion(peaks, nucleotideLevel=FALSE,
precedence=c("Promoters", "immediateDownstream",
"fiveUTRs", "threeUTRs",
"Exons", "Introns"),
TxDb=TxDb.Hsapiens.UCSC.hg19.knownGene)
barplot(aCR$percentage)
}

得到的条形图如下，虽然很丑，但这就是peaks注释的精髓，搞清楚每个peaks在基因组的位置特征：

同理，对每个peaks文件，都可以做类似的分析！

但是对多个peaks文件，比如本文中的，想比较野生型和突变型MCF7细胞系的 BAF155 immunoprecipitates的结果的不同，就需要做peaks之间的差异分析，已经后续的差异基因注释啦

当然，值得一提的是peaks注释我更喜欢网页版工具，反正peaks文件非常小，直接上传到别人做好的web tools，就可立即出一大堆可视化图表分析结果啦，大家可以去试试看：

### step6.7 peak calling by BayesPeak(R bioconductor package)
# Bayesian Analysis of ChIP-seq data
## BayesPeak fits a Markov model to the data (the aligned reads) via Markov Chain Monte Carlo (MCMC) techniques.

# 有博客里面提到I've used BayesPeak running in R. It is much easier to install than MACS (failed for me), which require some (strange to me) files.
# 首先要把bowtie2比对好的alignment文件bam格式转换为bed格式： http://bedtools.readthedocs.io/en/latest/content/tools/bamtobed.html
## In particular, the chromosome, start position, end position and DNA strand appear in the 1st, 2nd, 3rd and 6th columns respectively.
#### software : http://bioconductor.org/packages/release/bioc/html/BayesPeak.html
#### readme: http://bioconductor.org/packages/release/bioc/vignettes/BayesPeak/inst/doc/BayesPeak.pdf
学习R的bioconductor系列包很容易，先看看例子即可examples:

library(BayesPeak) ## 一般例子都会读取包自带的测试文件
tFile=file.path(system.file(package='BayesPeak'),'extdata','H3K4me3reduced.bed')
cFile=file.path(system.file(package='BayesPeak'),'extdata','Inputreduced.bed')

raw.output <- bayespeak(tFile, cFile, chr = "chr16", start = 9.2E7, end = 9.5E7, job.size = 6E6)
output <- summarize.peaks(raw.output, method = "lowerbound")
## the function summarize.peaks will do : Filtering of unenriched jobs/Filtering of unenriched bins/Assembly of enriched bins/Conversion of bins to peaks

write.table(as.data.frame(output), file = "H3K4me3output.txt", quote = FALSE)
## write.csv(as.data.frame(output), file = "H3K4me3output.csv", quote = FALSE)
## 可以借助多线程来加快运行速度：
library(parallel)
## 还需要 检查pp这个阈值的选取 # A “potentially enriched” bin is defined as any bin with PP > 0.01.
The output of the algorithm is the Posterior Probability (often abbreviated to PP) of each bin being enriched.
The PP value is useful not only for calling the peaks, but could also be used in downstream analyses - for
example, to weight observations when searching for a novel transcription factor motif. The PP value is not
to be confused with the p value from hypothesis testing

> min.job <- min(raw.output$peaks$job)
> max.job <- max(raw.output$peaks$job)
> par(mfrow = c(2,2), ask = TRUE)
> for(i in min.job:max.job) {plot.PP(raw.output, job = i, ylim = c(0,50))}
When the coverage is sparse and therefore less information is available, the PP values tend to be more
uniformly spread over the interval [0,1], as above. This means that the distinction between peaks and
background is harder to make, which is usually a result of poor enrichment,

raw.output <- bayespeak(tFile, cFile,use.multicore = TRUE, mc.cores = 4)
i <- 324
plot.PP(raw.output, job = i, ylim = c(0,50))

看完了例子，就可以开始处理自己的数据啦：

############ first change bam files to bed files :
ls *sorted.bam |while read id ;do ~/biosoft/bedtools/bedtools2/bin/bedtools bamtobed -i $id > ${id%%.*}.bed ;done
但是要过滤掉特殊染色体(chr6_cox_hap2,chrUn_gl000214)，仅仅保留CHR1-22,X,Y,M
ls *bed |while read id ;do grep -v "_" $id >${id%%.*}.clean_bed;done

下面是我处理自己的数据的完整代码，很简单：

############ Then do peak calling in R by BayesPeak
library(BayesPeak)
library(parallel)
workdir=getwd()
tFile=file.path(workdir,'SRR1042593.clean_bed')
cFile=file.path(workdir,'SRR1042594.clean_bed')
raw.output <- bayespeak(tFile, cFile,use.multicore = TRUE, mc.cores = 8)
output <- summarize.peaks(raw.output, method = "lowerbound")
write.table(as.data.frame(output), file = "Xu_MUT_rep1.txt", quote = FALSE)

该软件有linux二进制版本，所以直接下载解压即可使用，具体代码如下：

## Download and install PeakRanger
cd ~/biosoft
mkdir PeakRanger && cd PeakRanger
wget https://sourceforge.net/projects/ranger/files/PeakRanger-1.18-Linux-x86_64.zip/
## Length: 1517587 (1.4M) [application/octet-stream]
unzip PeakRanger-1.18-Linux-x86_64.zip
~/biosoft/PeakRanger/bin/peakranger -h

下面的笔记是我做自学CHIP-seq数据分析系列教程的，所以中英文夹杂，大家将就着看吧，里面很多链接，大家可以进去自己学习

### step6.8 peak calling by PeakRanger
# PeakRanger is a multi-purporse software suite for analyzing next-generation sequencing (NGS) data. The suite contains the following tools:
# Used by modENCODE, iPlant and many others
# Not just for calling narrow and broad peaks
# Runs fast, together with sleek program options
To measure the significance of the enriched regions, PeakRanger uses binormial distribution to model the relative enrichment of sample over control.
A p value is generated as a result. Users can thus select highly significant peaks by using a smaller -p.
In addition, users can filter peaks by the '-q' option, which controls the FDR of peaks.
For each p-value, the Benjamini-Hochberg procedure is applied to calculate the FDR.
# http://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/refGene.txt.gz ## gunzip refGene.txt.gz ; mv refGene.txt hg19refGene.txt
#### software : http://ranger.sourceforge.net/ go to the root path of the unzipped package and type:make
#### readme: http://ranger.sourceforge.net/manual1.18.html
# http://www.broadinstitute.org/~anshul/projects/encode/preprocessing/peakcalling/peakranger/bin/MANUAL

### ~/biosoft/PeakRanger/bin/peakranger -h  ##我的软件已经安装完毕
nr estimate data quality
lc calculate library complexity
wig generate wiggle files
wigpe generate wiggle files for paired reads
ranger peak calling for sharp peaks
ccat peak calling for broad peaks
bcp peak calling for complex broad peaks

## 上面是该软件的几个用法，它直接各种格式的比对文件，我这里给的bed格式的，就是把sam转为bam再转为bed，，大家没必要那么复杂， 直接用bam格式即可

~/biosoft/PeakRanger/bin/peakranger nr --format bed SRR1042593.clean_bed SRR1042594.clean_bed
~/biosoft/PeakRanger/bin/peakranger ccat --format bed SRR1042593.clean_bed SRR1042594.clean_bed \
Xu_MUT_rep1_ccat_report --report --gene_annot_file hg19refGene.txt -q 0.05 -t 4

很快就出结果，找到的peak非常多，但是需要过滤
844K Jun 30 09:32 Xu_MUT_rep1_ccat_report_details
637K Jun 30 09:32 Xu_MUT_rep1_ccat_report_region.bed
798K Jun 30 09:32 Xu_MUT_rep1_ccat_report_summit.bed
需要重点看到就是details文件，格式如下：很容易理解
#region_chr region_start region_end nearby_genes(6kbp) region_ID region_summits region_fdr region_strand region_treads region_creads
chr1 121482750 121486000 ccat_fdrPassed_0_fdr_0.001 121485025 0.001 + 551 642
chr1 115296600 115302500 CSDE1 ccat_fdrFailed_0_fdr_0.646 115301075 0.646 + 58 217
chr1 114351100 114356850 PTPN22,RSBN1 ccat_fdrFailed_3_fdr_0.646 114355425 0.646 + 48 112

很容易使用，但是具体条件参数，就需要自己看说明书啦
Guide: Peak Calling for ChIP-Seq :　http://epigenie.com/guide-peak-calling-for-chip-seq/

然后下面的各种资料，是针对CHIP-seq流程的各个环境的，还有一些是针对于表观遗传学知识的