hbctraining-05_peak_calling_macs2

算法，参数，输出。

Peak calling

ChIP-seq实验，从比对文件中观察到正/负链上以结合位点为中心的非对称reads
密度。
For ChIP-seq experiments, what we observe from the alignment files is a strand asymmetry with read densities on the +/- strand, centered around the binding site. The 5’ ends of the selected fragments will form groups on the positive- and negative-strand. The distributions of these groups are then assessed using statistical measures and compared against background (input or mock IP samples) to determine if the site of enrichment is likely to be a real binding site.

ChIP-seq analysis algorithms are specialized in identifying one of two types of enrichment (or have specific methods for each): broad peaks or broad domains (i.e. histone modifications that cover entire gene bodies) or narrow peaks ( transcription factor binding). Narrow peaks are easier to detect as we are looking for regions that have higher amplitude and are easier to distinguish from the background, compared to broad or dispersed marks. There are also ‘mixed’ binding profiles which can be hard for algorithms to discern. An example of this is the binding properties of PolII, which binds at promotor and across the length of the gene resulting in mixed signals (narrow and broad).

NOTE：ChIP-seq的分析方法可以鉴定两种类型的富集模式：broad domains和narrow peaks。broad domains，如组蛋白修饰在整个基因body区域的分布；narrow peak，如转录因子的结合。narrow peak相对于broad 或者分散的marks更易被检测到。也有一些混合的结合图谱，如PolII包括narrow和broad信号。

MACS2

MACS2是最常用的call peaks工具。 The MACS algorithm captures the influence of genome complexity to evaluate the significance of enriched ChIP regions。全称Model-based Analysis of ChIP-Seq，最初设计用来鉴定转录因子结合位点（also suited for larger regions），也可用于其他类型的富集方式测序。
MACS通过整合序列标签位置信息和方向信息提高结合位点的空间分辨率（ improves the spatial resolution of binding sites through combining the information of both sequencing tag position and orientation）。单独使用或加对照（ increases specificity of the peak calls）。

1. Remove redundancy

Why worry about duplicates? Reads with the same start position are considered duplicates. These duplicates can arise from experimental artifacts, but can also contribute to genuine ChIP-signal. (相同起点的reads被认为是duplicates，可能由于实验误差造成，也可能是ChIP信号)

• 坏 duplicates: If initial starting material is low this can lead to overamplification of this material before sequencing. Any biases in PCR will compound this problem and can lead to artificially enriched regions. Also blacklisted (repeat) regions with ultra high signal will also be high in duplicates. Masking these regions prior to analysis can help remove this problem。 实验材料量少，过度扩增，PCR偏差，人为富集区域。blacklist（重复）区域？怎么获得，屏蔽该区域。
• 好 duplicates: