生成网络图以查看组之间的相似性

Question

我有一些数据

CM

（如下），其中包含 6 个基因组。图中的一些基因重叠。我创建了一个维恩图，但我的主管希望数据以不同的格式呈现。他们希望面板之间的重叠由网络图表示。他们希望节点大小指的是基因面板的大小，边缘指的是面板之间共享的基因，其中线的粗细对应于共享基因的数量。

我完全不知所措，我什至不知道需要如何操作数据才能适应 igraph 这样的东西。

为了分解它，我可以计算每组中的基因数量：

CM %>% group_by(Panel) %>% tally()

我还可以看看重叠部分：

table(CM$Gene.Symbol, CM$Panel)

然后我就陷入困境了...请对我宽容一些，我是一名临床医生！

> dput(CM)
structure(list(Gene.Symbol = c("DES", "DSC2", "DSG2", "DSP", 
"FLNC", "JUP", "LMNA", "PKP2", "PLN", "TMEM43", "ANK2", "CDH2", 
"CAVIN4", "CTNNA3", "LDB3", "RBM20", "RYR2", "SCN5A", "TGFB3", 
"TTN", "AARS2", "ABCC9", "ACAD9", "ACADVL", "ACTA1", "ACTC1", 
"ACTN2", "AGK", "ALMS1", "ALPK3", "BAG3", "CACNA1C", "CDH2", 
"COA5", "COA6", "COX10", "COX15", "CPT2", "CSRP3", "DES", "DMD", 
"DNAJC19", "DOLK", "DSC2", "DSG2", "DSP", "EMD", "EPG5", "FHL1", 
"FHOD3", "FKTN", "FLNC", "GAA", "GUSB", "HADHA", "HADHB", "HRAS", 
"IDH2", "IDUA", "JPH2", "JUP", "KRAS", "LAMP2", "LMNA", "LZTR1", 
"MAP2K1", "MAP2K2", "MLYCD", "MRAS", "MRPL44", "MUT", "MYBPC3", 
"MYH6", "MYH7", "MYL2", "MYL3", "MYLK3", "MYPN", "NDUFA11", "NDUFA2", 
"NDUFAF1", "NDUFB11", "NDUFS2", "NDUFS8", "NDUFV2", "NEXN", "NKX2-5", 
"NONO", "NRAP", "NRAS", "PCCA", "PCCB", "PKP2", "PLD1", "PLN", 
"PPA2", "PPCS", "PPP1CB", "PPP1R13L", "PRKAG2", "PTPN11", "RAF1", 
"RBM20", "RIT1", "RYR2", "SCN5A", "SCO1", "SCO2", "SHOC2", "SLC22A5", 
"SLC25A20", "SLC25A4", "SOS1", "SOS2", "SPEG", "TAZ", "TMEM43", 
"TMEM70", "TNNC1", "TNNI3", "TNNI3K", "TNNT2", "TPM1", "TSFM", 
"TTN", "TTR", "VCL", "AGL", "ANK2", "ARSB", "ATP5D", "ATPAF2", 
"BRAF", "CBL", "COX14", "COX20", "COX6B1", "COX7B", "CRYAB", 
"EYA4", "FAH", "FASTKD2", "FKRP", "FLII", "FNIP1", "FOXRED1", 
"GATA6", "GLA", "GLB1", "GSN", "HCN4", "HFE", "HGSNAT", "IDS", 
"LDB3", "LRPPRC", "MIB1", "MMACHC", "MT-TI", "NAA15", "NAGLU", 
"NDUFA1", "NDUFA10", "NDUFA4", "NDUFAF2", "NDUFAF3", "NDUFAF4", 
"NDUFAF5", "NDUFB3", "NDUFB8", "NDUFS1", "NDUFS3", "NDUFS4", 
"NDUFS6", "NDUFS7", "NDUFV1", "NF1", "NUBPL", "PDLIM3", "PET100", 
"PNPLA2", "RASA2", "RHBDF1", "RNF220", "RPL3L", "SDHA", "SDHAF1", 
"SDHD", "SGCD", "SGSH", "SHMT2", "SLC30A5", "SPRED2", "SURF1", 
"TMEM126B", "TOR1AIP1", "UQCC2", "ANKRD1", "APOPT1", "B3GAT3", 
"BCS1L", "BTK", "COA7", "COX6A1", "CPS1", "CTF1", "CYC1", "DHCR7", 
"DTNA", "ETFA", "ETFB", "ETFDH", "GALNS", "GBE1", "GLRA1", "GNS", 
"ILK", "KIF20A", "LAMA4", "LYRM7", "MCM10", "NDUFA6", "NDUFA9", 
"NDUFAF6", "NDUFAF8", "NEBL", "SPRED1", "TAB2", "TACO1", "TCAP", 
"TGFB3", "TMPO", "TTC19", "UQCRB", "", "ACTC1", "ACTN2", "BAG3", 
"CDH2", "DES", "DMD", "DOLK", "DSC2", "DSG2", "DSP", "EMD", "FLNC", 
"JUP", "LAMP2", "LMNA", "MYBPC3", "MYH7", "NEXN", "NKX2-5", "PKP2", 
"PLN", "RBM20", "RYR2", "SCN5A", "TMEM43", "TNNC1", "TNNI3", 
"TNNI3K", "TNNT2", "TPM1", "TTN", "VCL", "ANK2", "ANKRD1", "CRYAB", 
"CSRP3", "FKRP", "FKTN", "FLII", "GATA6", "LDB3", "MYH6", "MYLK3", 
"MYPN", "NRAP", "PRDM16", "RHBDF1", "RPL3L", "SGCD", "SLC6A6", 
"SPEG", "TBX20", "TBX5", "TCAP", "ABCC9", "EYA4", "FHOD3", "GATAD1", 
"ABCC9", "ACTC1", "ACTN2", "BAG3", "CSRP3", "DES", "DMD", "DSP", 
"EPG5", "EYA4", "HAMP", "HFE", "HFE2", "IDH2", "LMNA", "MYBPC3", 
"MYH6", "MYH7", "NEXN", "PLN", "PPP1R13L", "RBM20", "SCN5A", 
"SGCD", "SLC40A1", "SPEG", "TAZ", "TCAP", "TFR2", "TNNC1", "TNNI3", 
"TNNT2", "TPM1", "TTN", "VCL", "ANKRD1", "CRYAB", "FKTN", "FLNC", 
"GATAD1", "LDB3", "MYPN", "PRDM16", "PSEN1", "PSEN2", "SCN1B", 
"ACTA1", "ALMS1", "CAVIN4", "CTF1", "DMPK", "DNAJC19", "DOLK", 
"DSC2", "DSG2", "EMD", "FHL1", "FHL2", "GLA", "ILK", "JUP", "LAMA4", 
"LAMP2", "MPO", "MYL2", "MYL3", "NEBL", "NKX2-5", "NPPA", "PDLIM3", 
"PKP2", "PRKAG2", "RAB3GAP2", "RAF1", "RYR2", "SDHA", "SGCB", 
"SYNE1", "SYNE2", "TBX20", "TMEM43", "TMPO", "TTR", "TXNRD2", 
"XK", "ACTC1", "ACTN2", "CACNA1C", "CSRP3", "FHL1", "FHOD3", 
"FLNC", "GLA", "JPH2", "LAMP2", "MYBPC3", "MYH7", "MYL2", "MYL3", 
"PLN", "PRKAG2", "TNNC1", "TNNI3", "TNNT2", "TPM1", "TRIM63", 
"TTR", "ALPK3", "ATAD3A", "GYG1", "MT-TI", "MYLK2", "MYPN", "ACADVL", 
"ACTA1", "AGL", "ANKRD1", "ATP5E", "BRAF", "CALR3", "CASQ2", 
"CAV3", "COA5", "CRYAB", "DES", "FOXRED1", "FXN", "GAA", "GLB1", 
"GUSB", "HRAS", "KCNQ1", "KLF10", "LDB3", "LMNA", "LZTR1", "MAP2K1", 
"MAP2K2", "MRPL3", "MT-TL1", "MYH6", "MYO6", "MYOM1", "MYOZ2", 
"NEXN", "NRAS", "PDLIM3", "PTPN11", "RAF1", "SCO2", "SHOC2", 
"SLC25A3", "SLC25A4", "SOS1", "TCAP", "TMEM70", "TSFM", "TTN", 
"VCL", "ACTC1", "MYBPC3", "MYH7", "TAZ", "TNNT2", "TPM1", "CASQ2", 
"DNAJC19", "DTNA", "LDB3", "LMNA", "MIB1", "MYPN", "PRDM16", 
"SDHA", "TNNI3"), Panel = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L), levels = c("Arrhythmogenic cardiomyopathy", 
"Cardiomyopathies - including childhood onset", "Dilated cardiomyopathy - adult and teen", 
"Dilated Cardiomyopathy and conduction defects", "Hypertrophic cardiomyopathy - teen and adult", 
"Left Ventricular Noncompaction Cardiomyopathy"), class = "factor")), row.names = c(NA, 
-468L), class = "data.frame")

Answer 1

在我看来，您正在描述一个二分网络，其中面板是一种节点类型，而基因是另一种。

library(igraph)
#> 
#> Attaching package: 'igraph'
#> The following objects are masked from 'package:stats':
#> 
#>     decompose, spectrum
#> The following object is masked from 'package:base':
#> 
#>     union
g <- graph_from_data_frame(CM)
V(g)$type <- bipartite.mapping(g)$type       # assign node-types
g2 <- bipartite.projection(g)[[2]]           # project onto the panels 
plot(g2, 
     edge.width = sqrt(E(g2)$weight),        # number of genes shared
     vertex.size = sqrt(strength(g2)),       # total of genes 
     edge.label = E(g2)$weight,              # optional labelling
     vertex.color = as.factor(V(g2)$name))   # optional color

^{创建于 2023-12-12，使用 reprex v2.0.2}