R 按组排除连续行上的非重叠范围

我有如下数据框：

df1 <- data.frame(Group = c("scaf1", "scaf1", "scaf1", "scaf2", "scaf2", "scaf2", "scaf3", "scaf3", "scaf4", "scaf4"),
                  Start = c(10, 40, 90, 50, 80, 95, 600, 800, 70, 100),
                  End = c(50, 70, 120, 70, 100, 150, 700, 850, 100, 145))

df1
# group  start  End
# scaf1  10     50
# scaf1  40     70 
# scaf1  90     120
# scaf2  50     70
# scaf2  80     100
# scaf2  95     150
# scaf3  600    700
# scaf3  800    850
# scaf4  70     100
# scaf4  100    145

我尝试执行以下命令，但失败：

setDT(df1)[ , .((start[2] < End[1])[-.N], by = group]

setDT（df1）[，.（（开始[2]<结束[1]）[-.N]，由=组]

提前谢谢。

给你：

df1=data.frame(Group=c("scaf1","scaf1","scaf1","scaf2","scaf2","scaf2","scaf3","scaf3","scaf4","scaf4"),Start=c(10,40,90,50,80,95,600,800,70,100),End=c(50,70,120,70,100,150,700,850,100,145))

df1$filter = F

for(k in 2:nrow(df1)){
    if(df1$Group[k]==df1$Group[k-1] && df1$Start[k]<=df1$End[k-1]){
        df1$filter[k-1]=T
        df1$filter[k]=T
    }
}

df2 = df1[df1$filter==T,]
df2$filter = NULL

---

获取输出的另一种方法是使用GenomicRanges包定义的范围

library(GenomicRanges)
# create a GRanges object
df1_gr <- GRanges(df1$Group, IRanges(df1$Start, df1$End))
# find the overlaps
gr <- as.data.frame(findOverlaps(df1_gr))
# remove self-overlapping
gr <- gr[gr$queryHits != gr$subjectHits,]
# final dataset
df1[ gr$queryHits, ]
Group Start End
1: scaf1    10  50
2: scaf1    40  70
3: scaf2    80 100
4: scaf2    95 150
5: scaf4    70 100
6: scaf4   100 145

库（基因组范围）
#创建GRanges对象
df1_gr请检查您的预期输出。可能需要一些更正为什么scaf2上的50 70不在输出中，因为10 50第一行在那里正如akrun已经评论过的那样，您的输出似乎被破坏了。但是您可以尝试以下方法：
unlist（lapply（split）（df1，df1$Group），function（x）c（TRUE，sapply（1:（length（x$Start）-1），function（y）x$Start[y+1]
这一行发生了什么事？
scaf2 50 70
和
scaf3
？可能
df1%>%groupby（group）%%>%filter（（Start>=lag（Start）&Start Try
setDT（df1）[df1[，.I[（Start>=shift（Start，fill=0）]&Start
> df2
   Group Start End
1  scaf1    10  50
2  scaf1    40  70
5  scaf2    80 100
6  scaf2    95 150
9  scaf4    70 100
10 scaf4   100 145

library(GenomicRanges)
# create a GRanges object
df1_gr <- GRanges(df1$Group, IRanges(df1$Start, df1$End))
# find the overlaps
gr <- as.data.frame(findOverlaps(df1_gr))
# remove self-overlapping
gr <- gr[gr$queryHits != gr$subjectHits,]
# final dataset
df1[ gr$queryHits, ]
Group Start End
1: scaf1    10  50
2: scaf1    40  70
3: scaf2    80 100
4: scaf2    95 150
5: scaf4    70 100
6: scaf4   100 145