Hello,

Within SNPRelate, I have been trying to compute a dissimilarity matrix from input VCF data using the snpgdsDiss function. The resulting matrix, though, has NaN values for a small number of the 80 or so input samples, and I cannot proceed to compute a clustering (snpgdsHCluster). The VCF data ranges from 1-219 variants per sample, but the lower-sized samples are not exclusively the ones affected. Other than removing the affected samples from the study, is there anything else I can do to create a complete dissimilarity matrix? 

vcf_data<- file.path("VCFSorts","multisample.vcf")

gds_data <- file.path("VCFSorts","multisample.gds")
if(file.exists(gds_data)){file.remove(gds_data)}
snpgdsVCF2GDS(vcf_data, gds_data, method="biallelic.only")
snpgdsSummary(gds_data)
geno_data <- snpgdsOpen(gds_data)

pop_data <- read.xls("Sample Sheet.xlsx", sheet=1,header=TRUE)
pop_code <- pop_data[["Group"]]
pop_list <- read.gdsn(index.gdsn(geno_data, path="sample.id")) 

# show that the sample order is the same as the population order
print(cbind(pop_data, pop_code, pop_list))


# # run PCA - THIS WORKS FINE
pca<-snpgdsPCA(geno_data, num.thread=8)
pc.percent <- pca$varprop*100
head(round(pc.percent, 2))
 
# make a data.frame
tab <- data.framesample.id = pca$sample.id,
                 pop = factor(pop_code)[match(pca$sample.id, pop_list)],
                 EV1 = pca$eigenvect[,1],    # the first eigenvector
                 EV2 = pca$eigenvect[,2],    # the second eigenvector
                 stringsAsFactors = FALSE)
plot(tab$EV2, tab$EV1, pch=16, cex=2, col=as.integer(tab$pop), xlab="eigenvector 2", ylab="eigenvector 1")
legend("topright", legend=levels(tab$pop), pch=15, cex=1.5 , col=1:nlevels(tab$pop))



# Hierarchical Clustering  - FAIL
diss<-snpgdsDiss(geno_data, sample.id=NULL,snp.id=NULL,autosome.only=TRUE,remove.monosnp=TRUE,maf=NaN,missing.rate=NaN,num.thread=6,verbose=TRUE)
hc<-snpgdsHCluster(diss, sample.id=NULL,need.mat=TRUE,hang=0.25)

Error in hclust(as.dist(dist), method = "average") : 
  NA/NaN/Inf in foreign function call (arg 11)

> sessionInfo()
R version 3.2.2 (2015-08-14)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 15.10

locale:
 [1] LC_CTYPE=en_GB.UTF-8       LC_NUMERIC=C               LC_TIME=en_IE.UTF-8        LC_COLLATE=en_GB.UTF-8     LC_MONETARY=en_IE.UTF-8   
 [6] LC_MESSAGES=en_GB.UTF-8    LC_PAPER=en_IE.UTF-8       LC_NAME=C                  LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_IE.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] SNPRelate_1.4.0 gdsfmt_1.6.2    gdata_2.17.0   

loaded via a namespace (and not attached):
[1] tools_3.2.2  gtools_3.5.0

Are you able to run snpgdsIBS Identity-By-State analysis? Is there any missing value in the result of IBS analysis also?