Hi, I analyzed an Agilent microarray with limma and wanted to calculate differentially expressed genes for the condition of interest as shown below.

# Differential expression
fit<-lmFit(filt, design)
fit<-eBayes(fit)
results<-decideTests(fit[,2], method='global')
summary(results)
topTable(fit, coef=2, sort.by='p')

The output, however, included some probes labeled as NAs which I can not explain as probes were filtered for those that have a symbol annotation.

Can someone explain what I am doing wrong?

> sessionInfo()
R version 4.1.2 (2021-11-01)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 19045)

Matrix products: default

locale:
[1] LC_COLLATE=English_United Kingdom.1252  LC_CTYPE=English_United Kingdom.1252    LC_MONETARY=English_United Kingdom.1252
[4] LC_NUMERIC=C                            LC_TIME=English_United Kingdom.1252    
system code page: 65001

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

other attached packages:
[1] org.Hs.eg.db_3.14.0  AnnotationDbi_1.56.2 IRanges_2.28.0       S4Vectors_0.32.3     limma_3.50.0         GEOquery_2.62.2     
[7] Biobase_2.54.0       BiocGenerics_0.40.0 

loaded via a namespace (and not attached):
 [1] Rcpp_1.0.7             XVector_0.34.0         GenomeInfoDb_1.30.0    pillar_1.8.0           compiler_4.1.2        
 [6] R.methodsS3_1.8.1      R.utils_2.12.2         zlibbioc_1.40.0        bitops_1.0-7           tools_4.1.2           
[11] bit_4.0.4              RSQLite_2.2.9          memoise_2.0.1          lifecycle_1.0.1        tibble_3.1.8          
[16] png_0.1-7              pkgconfig_2.0.3        rlang_1.0.4            DBI_1.1.1              cli_3.1.0             
[21] rstudioapi_0.13        curl_4.3.2             fastmap_1.1.0          GenomeInfoDbData_1.2.7 httr_1.4.2            
[26] dplyr_1.0.9            xml2_1.3.3             Biostrings_2.62.0      generics_0.1.3         vctrs_0.4.1           
[31] hms_1.1.1              bit64_4.0.5            tidyselect_1.1.2       glue_1.6.2             data.table_1.14.2     
[36] R6_2.5.1               fansi_0.5.0            tzdb_0.2.0             readr_2.1.2            purrr_0.3.4           
[41] tidyr_1.1.4            blob_1.2.2             magrittr_2.0.1         ellipsis_0.3.2         KEGGREST_1.34.0       
[46] assertthat_0.2.1       utf8_1.2.2             RCurl_1.98-1.5         cachem_1.0.6           crayon_1.4.2          
[51] R.oo_1.24.0 

Thanks in advance!

limma doesn't introduce NAs so the NAs must have already been in the filt object before limma was run.

Agilent ProbeNames should never be NA so there must have been a mistake in preparation of the data object.