Error in if (mlikconv)

[bharatij]

Hi, I have zero-inflated RNA Seq count data and performing simultaneous shrinkage using ShrinkSeq() with a fix parameter and zero-inflated negative binomial. All other parameters are have default values. I encounter following error. Is it possible that my data doesn't follow underlying data distribution assumption and causing this error?

Library INLA loaded. Library INLA loaded in cluster.

[1] "Exporting to slaves" [1] "Exporting done" [1] "Started fitting"

Stopping cluster

[1] "ntags not used: 100" [1] "Many non-used tags: switching mode" [1] "ntags not used: 100" [1] "ntags not used: 100" [1] "Many non-used tags: switching mode" [1] "ntags not used: 100" [1] NaN [1] NaN Error in if (mlikconv) { : missing value where TRUE/FALSE needed

Its ran on R version 3.2.2 (2015-08-14) Platform: x86_64-pc-linux-gnu (64-bit) Running under: Ubuntu 14.04.3 LTS

Thanks, BJ

[bharatij]

Hi, I switched from INLA_0.0-1483776432 to NLA_0.0-1468872408 and everything went well. But still wondering why the latest release has problem with this step and older version did not. Thanks, BJ

[markvdwiel]

BJ, thanks for letting me know. I will need to check this. Mark

[markvdwiel]

BJ, I reinstalled INLA, version 0.0-1485844051, and ran the try-out example below. No problems. So, Im not sure why you receive errors....

data(CAGEdata10000) data(design_brain) cd <- CAGEdata10000[1:50,] pers <- design_brain$pers #persons batch<-design_brain$batch #batch groupfac <- design_brain$groupfac #group (= brain region) ncpus2use <- 2 groupfac <- BaselineDef("groupfac",baselinegroup="1") lincombvec <- AllComp("groupfac") form = y ~ 1 + groupfac + batch + f(pers,model="iid") #'batch' and 'group' as fixed effect, 'pers' as random effect shrinksimul <- ShrinkSeq(form=form, dat=cd,shrinkfixed="groupfac", shrinkrandom="pers",ncpus=ncpus2use, maxiter=2,ntag=c(10))

[bharatij]

Hi Mark, Thanks for checking it. I upgraded INLA to version 0.0-1485844051 and ran the above code as is. I still encounter the same error as previous

'Error in if (mlikconv) { : missing value where TRUE/FALSE needed'

Following are the details of R environment

sessionInfo() R version 3.2.2 (2015-08-14) Platform: x86_64-pc-linux-gnu (64-bit) Running under: Ubuntu 14.04.3 LTS

locale: [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8 [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8 [7] LC_PAPER=en_US.UTF-8 LC_NAME=C [9] LC_ADDRESS=C LC_TELEPHONE=C [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C

attached base packages: [1] splines stats4 stats graphics grDevices utils datasets [8] methods base

other attached packages: [1] ShrinkBayes_2.13.4 rgl_0.97.0 XML_3.98-1.5 [4] Iso_0.0-17 logcondens_2.1.5 mclust_5.2.2 [7] VGAM_1.0-3 INLA_0.0-1485844051 Matrix_1.2-2 [10] sp_1.2-4 snowfall_1.84-6.1 snow_0.4-2 [13] dplyr_0.5.0

loaded via a namespace (and not attached): [1] Rcpp_0.12.9 knitr_1.15.1 magrittr_1.5 misc3d_0.8-4 [5] xtable_1.8-2 lattice_0.20-33 R6_2.2.0 tools_3.2.2 [9] grid_3.2.2 KernSmooth_2.23-15 DBI_0.5-1 htmltools_0.3.5 [13] assertthat_0.1 digest_0.6.12 tibble_1.2 shiny_1.0.0 [17] codetools_0.2-14 ks_1.10.5 htmlwidgets_0.8 mime_0.5 [21] multicool_0.1-10 jsonlite_1.3 mvtnorm_1.0-6 httpuv_1.3.3

I am not sure why it is not working for me. Is one of the dependent package not compatible INLA?

Thanks, Bharati

[ghost]

I had the same error :

Error in if (mlikconv) { : missing value where TRUE/FALSE needed Calls: ShrinkSeq Execution halted

and found some discussion on INLA with the suggestion to revert to a static library due to old linux version, which is true in my case (Ubuntu 14.04.5 LTS) , by calling:

INLA:::inla.dynload.workaround()

See also original link: https://groups.google.com/forum/#!topic/r-inla-discussion-group/fyk2gJ46Rec

[bharatij]

I am not able to get rid of the error with

INLA:::inla.dynload.workaround()

Is there anything else you need to set up?

[markvdwiel]

Im not sure, but it seems an INLA error, so you better post your question at www.r-inla.org