source("https://bioconductor.org/biocLite.R")
biocLite("BgeeDB")
## 
## The downloaded binary packages are in
##  /var/folders/8b/_0z6s_zn66l674ylzs59d1n00000gn/T//RtmpR6fPaq/downloaded_packages
# additional packages for installation
biocLite(c("edgeR", "Mfuzz", "biomaRt"))
## 
## The downloaded binary packages are in
##  /var/folders/8b/_0z6s_zn66l674ylzs59d1n00000gn/T//RtmpR6fPaq/downloaded_packages
library(BgeeDB)
# list the species
listBgeeSpecies()
## 
## Querying Bgee to get release information...
## 
## Building URL to query species in Bgee release 13_2...
## 
## Submitting URL to Bgee webservice... (http://r13_2.bgee.org/?page=species&display_type=tsv)
## 
## Query to Bgee webservice successful!
##       ID           GENUS SPECIES_NAME COMMON_NAME AFFYMETRIX   EST IN_SITU
## 1   6239  Caenorhabditis      elegans   c.elegans       TRUE FALSE    TRUE
## 2   7227      Drosophila melanogaster    fruitfly       TRUE  TRUE    TRUE
## 3   7955           Danio        rerio   zebrafish       TRUE  TRUE    TRUE
## 4   8364         Xenopus   tropicalis     xenopus      FALSE  TRUE    TRUE
## 5   9031          Gallus       gallus     chicken      FALSE FALSE   FALSE
## 6   9258 Ornithorhynchus     anatinus    platypus      FALSE FALSE   FALSE
## 7   9544          Macaca      mulatta     macaque      FALSE FALSE   FALSE
## 8   9593         Gorilla      gorilla     gorilla      FALSE FALSE   FALSE
## 9   9597             Pan     paniscus      bonobo      FALSE FALSE   FALSE
## 10  9598             Pan  troglodytes  chimpanzee      FALSE FALSE   FALSE
## 11  9606            Homo      sapiens       human       TRUE  TRUE   FALSE
## 12  9823             Sus       scrofa         pig      FALSE FALSE   FALSE
## 13  9913             Bos       taurus         cow      FALSE FALSE   FALSE
## 14 10090             Mus     musculus       mouse       TRUE  TRUE    TRUE
## 15 10116          Rattus   norvegicus         rat      FALSE FALSE   FALSE
## 16 13616     Monodelphis    domestica     opossum      FALSE FALSE   FALSE
## 17 28377          Anolis carolinensis      anolis      FALSE FALSE   FALSE
##    RNA_SEQ
## 1     TRUE
## 2    FALSE
## 3    FALSE
## 4     TRUE
## 5     TRUE
## 6     TRUE
## 7     TRUE
## 8     TRUE
## 9     TRUE
## 10    TRUE
## 11    TRUE
## 12    TRUE
## 13    TRUE
## 14    TRUE
## 15    TRUE
## 16    TRUE
## 17    TRUE
# specify species and data type
bgee_affymetrix <- Bgee$new(species="Mus_musculus", dataType="affymetrix", release="13.2")
## 
## Querying Bgee to get release information...
## 
## Building URL to query species in Bgee release 13_2...
## 
## Submitting URL to Bgee webservice... (http://r13_2.bgee.org/?page=species&display_type=tsv)
## 
## Query to Bgee webservice successful!
## 
## API key built: 696a8ee5f27f212d71349c131d413fb0de7947e688c95fcdd001689789c7333dbdf6fad8d4d48c239a3e0f4e60a3e74cd5b98398d6a3f93286288211920ddbdc
# retrieve annotation of all mouse affymetrix datasets in Bgee 
annotation_bgee_mouse_affymetrix <- getAnnotation(bgee_affymetrix)
## 
## Downloading annotation files...
## 
## Saved annotation files in /Users/jroux/Dropbox/RpackagePaper/Mus_musculus_Bgee_13_2 folder.
str(annotation_bgee_mouse_affymetrix)
## List of 2
##  $ sample.annotation    :'data.frame':   6077 obs. of  20 variables:
##   ..$ Experiment.ID                                   : chr [1:6077] "GSE3594" "GSE3594" "GSE3594" "GSE3594" ...
##   ..$ Chip.ID                                         : chr [1:6077] "GSM82907" "GSM82908" "GSM82959" "GSM82960" ...
##   ..$ Anatomical.entity.ID                            : chr [1:6077] "UBERON:0000007" "UBERON:0000007" "UBERON:0000007" "UBERON:0000007" ...
##   ..$ Anatomical.entity.name                          : chr [1:6077] "pituitary gland" "pituitary gland" "pituitary gland" "pituitary gland" ...
##   ..$ Stage.ID                                        : chr [1:6077] "MmusDv:0000052" "MmusDv:0000052" "MmusDv:0000052" "MmusDv:0000052" ...
##   ..$ Stage.name                                      : chr [1:6077] "8 weeks (mouse)" "8 weeks (mouse)" "8 weeks (mouse)" "8 weeks (mouse)" ...
##   ..$ IQRray.score                                    : num [1:6077] NA NA NA NA NA NA NA NA NA NA ...
##   ..$ MAS5.percent.present                            : num [1:6077] 41.1 46.6 44.9 45 51.5 ...
##   ..$ Normalization.type                              : chr [1:6077] "MAS5" "MAS5" "MAS5" "MAS5" ...
##   ..$ Scan.date                                       : chr [1:6077] NA NA NA NA ...
##   ..$ Chip.type.ID                                    : chr [1:6077] "A-AFFY-6" "A-AFFY-6" "A-AFFY-6" "A-AFFY-6" ...
##   ..$ CDF.name                                        : chr [1:6077] "MG_U74Av2" "MG_U74Av2" "MG_U74Av2" "MG_U74Av2" ...
##   ..$ Chip.type.name                                  : chr [1:6077] "Affymetrix GeneChip Murine Genome U74Av2" "Affymetrix GeneChip Murine Genome U74Av2" "Affymetrix GeneChip Murine Genome U74Av2" "Affymetrix GeneChip Murine Genome U74Av2" ...
##   ..$ IQRray.score.threshold.for.the.chip.type        : num [1:6077] 44246 44246 44246 44246 44246 ...
##   ..$ MAS5.percent.present.threshold.for.the.chip.type: num [1:6077] 26.7 26.7 26.7 26.7 26.7 ...
##   ..$ Data.source                                     : chr [1:6077] "GEO" "GEO" "GEO" "GEO" ...
##   ..$ Data.source.URL                                 : chr [1:6077] "http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM82907" "http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM82908" "http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM82959" "http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM82960" ...
##   ..$ Bgee.normalized.data.URL                        : chr [1:6077] "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Aff"| __truncated__ "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Aff"| __truncated__ "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Aff"| __truncated__ "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Aff"| __truncated__ ...
##   ..$ Bgee.normalized.data.file                       : chr [1:6077] "Mus_musculus_probesets_GSE3594_A-AFFY-6_MAS5.tsv" "Mus_musculus_probesets_GSE3594_A-AFFY-6_MAS5.tsv" "Mus_musculus_probesets_GSE3594_A-AFFY-6_MAS5.tsv" "Mus_musculus_probesets_GSE3594_A-AFFY-6_MAS5.tsv" ...
##   ..$ Bgee.raw.file.URL                               : chr [1:6077] "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/mas5_files/GSE3594/GSM82907" "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/mas5_files/GSE3594/GSM82908" "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/mas5_files/GSE3594/GSM82959" "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/mas5_files/GSE3594/GSM82960" ...
##  $ experiment.annotation:'data.frame':   694 obs. of  11 variables:
##   ..$ Experiment.ID           : chr [1:694] "GSE3594" "GSE7759" "GSE10744" "GSE16496" ...
##   ..$ Chip.count              : int [1:694] 129 110 108 102 91 87 69 67 65 63 ...
##   ..$ Condition.count         : int [1:694] 34 13 6 46 45 7 10 21 6 25 ...
##   ..$ Organ.count             : int [1:694] 34 3 6 46 45 7 1 21 1 7 ...
##   ..$ Stage.count             : int [1:694] 1 5 1 1 2 1 10 3 6 12 ...
##   ..$ Data.source             : chr [1:694] "GEO" "GEO" "GEO" "GEO" ...
##   ..$ Data.source.URL         : chr [1:694] "http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3594" "http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7759" "http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10744" "http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE16496" ...
##   ..$ Bgee.normalized.data.URL: chr [1:694] "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Aff"| __truncated__ "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Aff"| __truncated__ "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Aff"| __truncated__ "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Aff"| __truncated__ ...
##   ..$ Bgee.raw.files.URL      : chr [1:694] "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/mas5_files/GSE3594/" "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/GSE7759/" "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/GSE10744/" "ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/GSE16496/" ...
##   ..$ Experiment.name         : chr [1:694] "Transcription profiling of twenty four mouse neural tissues from three inbred strains to build a gene expression-based brain ma"| __truncated__ "Transcription profiling of mouse facial prominences in the C57BL/6J mouse strain between embryonic (E) day 10.0 and 12.5" "Transcription profiling and comparative geenomic hybridization of mouse C57BL/6J, DBA2/J, AKR/J, A/J and C3HeB/FeJ strains for "| __truncated__ "Expression profile of adult mouse 51 CNS regions" ...
##   ..$ Experiment.description  : chr [1:694] "The current model to explain the organization of the mammalian nervous system is based on studies of anatomy, embryology, and e"| __truncated__ "Growth and patterning of the face relies on several small buds of tissue, the facial prominences, which surround the primitive "| __truncated__ "Copy number variation (CNV) of DNA segments has recently been identified as a major source of genetic diversity, but a more com"| __truncated__ "The adult mammalian brain is composed of distinct regions that have specialized roles. To dissect molecularly this complex stru"| __truncated__ ...
# retrieve annotation of samples and experiments
sample_annotation <- annotation_bgee_mouse_affymetrix$sample.annotation
experiment_annotation <- annotation_bgee_mouse_affymetrix$experiment.annotation

# list experiments including a zygote sample
selected_experiments <- 
    unique(sample_annotation$Experiment.ID[sample_annotation$Stage.ID == "UBERON:0000106"])
experiment_annotation[experiment_annotation$Experiment.ID %in% selected_experiments,]
##     Experiment.ID Chip.count Condition.count Organ.count Stage.count
## 24        GSE1749         42               5           4           5
## 32      E-MEXP-51         35               9           5           7
## 113      GSE18290         12               4           3           4
##      Data.source
## 24           GEO
## 32  ArrayExpress
## 113          GEO
##                                                Data.source.URL
## 24   http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1749
## 32     http://www.ebi.ac.uk/arrayexpress/experiments/E-MEXP-51
## 113 http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE18290
##                                                                                                                                           Bgee.normalized.data.URL
## 24    ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_GSE1749.zip
## 32  ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 113  ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_GSE18290.zip
##                                                                    Bgee.raw.files.URL
## 24   ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/mas5_files/GSE1749/
## 32  ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/
## 113  ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/GSE18290/
##                                                                                                                                                         Experiment.name
## 24                                                           Transcription profiling of mouse embryo to assess gene expression during preimplantation mouse development
## 32  Transcription profiling of mouse pre-implantation development over twelve time points from the germinal vesicle (GV) stage oocyte to the late (expanded) blastocyst
## 113                                                                                                          Transcription profiling of human, mouse, Bos taurus embryo
##                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     Experiment.description
## 24  Studies using low-resolution methods to assess gene expression during preimplantation mouse development indicate that changes in gene expression either precede or occur concomitantly with the major morphological transitions, that is, conversion of the oocyte to totipotent 2-cell blastomeres, compaction, and blastocyst formation. Using microarrays, we characterized global changes in gene expression and used Expression Analysis Systematic Explorer (EASE) to identify biological and molecular processes that accompany and likely underlie these transitions. The analysis confirmed previously described processes or events, but more important, EASE revealed new insights. Response to DNA damage and DNA repair genes are overrepresented in the oocyte compared to 1-cell through blastocyst stages and may reflect the oocyte's response to selective pressures to insure genomic integrity; fertilization results in changes in the transcript profile in the 1-cell embryo that are far greater than previously recognized; and genome activation during 2-cell stage may not be as global and promiscuous as previously proposed, but rather far more selective, with genes involved in transcription and RNA processing being preferentially expressed. These results validate this hypothesis-generating approach by identifying genes involved in critical biological processes that can be the subject of a more traditional hypothesis-driven approach.
## 32                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            The goal of the experiments was to profile and analyze gene activity during murine pre-implantation development. Samples were collected at twelve time points from the germinal vesicle (GV) stage oocyte to the late (expanded) blastocyst.
## 113                                                                                                                                                                                                                                                                                                                                                                                                                                                        The process of early development of mammals is subtly and accurately controlled by the regulation networks of embryo cells. Time course expression data measured at different stages during early embryo development process can give us valuable information by revealing the dynamic expression patterns of genes in genome wide scale. In this study, bovine embryo expression data were generated at oocyte, one cell stage, two cell stage, four cell stage, eight cell stage, sixteen cell stage, morula, and blastocyst; Human embryo expression data were generated at one cell stage, two cell stage, four cell stage, eight cell stage, morula, and blastocyst; Mouse embryo expression data were generated at one cell stage, two cell stage, four cell stage, eight cell stage, morula, and blastocyst. Experiment Overall Design: Bovine, Human, and Mouse embryos were harvested at successive stage from oocyte to blastocyste. Total RNAs were extracted, amplified and hybridized onto Affymetrix microarrays.
# stages sampled in each of these experiments
unique(sample_annotation[sample_annotation$Experiment.ID %in% selected_experiments, c(1,6)])
##      Experiment.ID                Stage.name
## 1536       GSE1749                life cycle
## 1540       GSE1749            blastula stage
## 1543       GSE1749              zygote stage
## 1546       GSE1749  Theiler stage 02 (mouse)
## 1550       GSE1749  Theiler stage 03 (mouse)
## 1836     E-MEXP-51              zygote stage
## 1840     E-MEXP-51 post-juvenile adult stage
## 1847     E-MEXP-51  Theiler stage 03 (mouse)
## 1849     E-MEXP-51  Theiler stage 02 (mouse)
## 1862     E-MEXP-51  Theiler stage 04 (mouse)
## 1866     E-MEXP-51  Theiler stage 05 (mouse)
## 1868     E-MEXP-51  Theiler stage 06 (mouse)
## 3447      GSE18290            blastula stage
## 3449      GSE18290              zygote stage
## 3452      GSE18290  Theiler stage 02 (mouse)
## 3456      GSE18290  Theiler stage 03 (mouse)
# List all samples from E-MEXP-51 in Bgee
sample_annotation[sample_annotation$Experiment.ID == "E-MEXP-51",]
##      Experiment.ID          Chip.ID Anatomical.entity.ID
## 1836     E-MEXP-51          Zygote1           CL:0000365
## 1837     E-MEXP-51          Zygote2           CL:0000365
## 1838     E-MEXP-51          Zygote3           CL:0000365
## 1839     E-MEXP-51          Zygote4           CL:0000365
## 1840     E-MEXP-51        GVoocyte1           CL:0000654
## 1841     E-MEXP-51        GVoocyte2           CL:0000654
## 1842     E-MEXP-51        GVoocyte3           CL:0000654
## 1843     E-MEXP-51        GVoocyte4           CL:0000654
## 1844     E-MEXP-51       MIIoocyte1           CL:0000655
## 1845     E-MEXP-51       MIIoocyte2           CL:0000655
## 1846     E-MEXP-51       MIIoocyte3           CL:0000655
## 1847     E-MEXP-51          16cell1       UBERON:0000085
## 1848     E-MEXP-51          16cell2       UBERON:0000085
## 1849     E-MEXP-51     Early2-cell1       UBERON:0000922
## 1850     E-MEXP-51     Early2-cell2       UBERON:0000922
## 1851     E-MEXP-51      Late2-cell1       UBERON:0000922
## 1852     E-MEXP-51      Late2-cell2       UBERON:0000922
## 1853     E-MEXP-51       Mid2-cell1       UBERON:0000922
## 1854     E-MEXP-51       Mid2-cell2       UBERON:0000922
## 1855     E-MEXP-51       Mid2-cell3       UBERON:0000922
## 1856     E-MEXP-51           4Cell1       UBERON:0000922
## 1857     E-MEXP-51           4cell2       UBERON:0000922
## 1858     E-MEXP-51           4cell3       UBERON:0000922
## 1859     E-MEXP-51           8cell1       UBERON:0000922
## 1860     E-MEXP-51           8cell2       UBERON:0000922
## 1861     E-MEXP-51           8cell3       UBERON:0000922
## 1862     E-MEXP-51 EarlyBlastocyst1       UBERON:0000922
## 1863     E-MEXP-51 EarlyBlastocyst2       UBERON:0000922
## 1864     E-MEXP-51 EarlyBlastocyst3       UBERON:0000922
## 1865     E-MEXP-51 EarlyBlastocyst4       UBERON:0000922
## 1866     E-MEXP-51   MidBlastocyst1       UBERON:0000922
## 1867     E-MEXP-51   MidBlastocyst2       UBERON:0000922
## 1868     E-MEXP-51  LateBlastocyst1       UBERON:0000922
## 1869     E-MEXP-51  LateBlastocyst2       UBERON:0000922
## 1870     E-MEXP-51  LateBlastocyst3       UBERON:0000922
##      Anatomical.entity.name       Stage.ID                Stage.name
## 1836                 zygote UBERON:0000106              zygote stage
## 1837                 zygote UBERON:0000106              zygote stage
## 1838                 zygote UBERON:0000106              zygote stage
## 1839                 zygote UBERON:0000106              zygote stage
## 1840         primary oocyte UBERON:0000113 post-juvenile adult stage
## 1841         primary oocyte UBERON:0000113 post-juvenile adult stage
## 1842         primary oocyte UBERON:0000113 post-juvenile adult stage
## 1843         primary oocyte UBERON:0000113 post-juvenile adult stage
## 1844       secondary oocyte UBERON:0000113 post-juvenile adult stage
## 1845       secondary oocyte UBERON:0000113 post-juvenile adult stage
## 1846       secondary oocyte UBERON:0000113 post-juvenile adult stage
## 1847                 morula MmusDv:0000006  Theiler stage 03 (mouse)
## 1848                 morula MmusDv:0000006  Theiler stage 03 (mouse)
## 1849                 embryo MmusDv:0000005  Theiler stage 02 (mouse)
## 1850                 embryo MmusDv:0000005  Theiler stage 02 (mouse)
## 1851                 embryo MmusDv:0000005  Theiler stage 02 (mouse)
## 1852                 embryo MmusDv:0000005  Theiler stage 02 (mouse)
## 1853                 embryo MmusDv:0000005  Theiler stage 02 (mouse)
## 1854                 embryo MmusDv:0000005  Theiler stage 02 (mouse)
## 1855                 embryo MmusDv:0000005  Theiler stage 02 (mouse)
## 1856                 embryo MmusDv:0000006  Theiler stage 03 (mouse)
## 1857                 embryo MmusDv:0000006  Theiler stage 03 (mouse)
## 1858                 embryo MmusDv:0000006  Theiler stage 03 (mouse)
## 1859                 embryo MmusDv:0000006  Theiler stage 03 (mouse)
## 1860                 embryo MmusDv:0000006  Theiler stage 03 (mouse)
## 1861                 embryo MmusDv:0000006  Theiler stage 03 (mouse)
## 1862                 embryo MmusDv:0000008  Theiler stage 04 (mouse)
## 1863                 embryo MmusDv:0000008  Theiler stage 04 (mouse)
## 1864                 embryo MmusDv:0000008  Theiler stage 04 (mouse)
## 1865                 embryo MmusDv:0000008  Theiler stage 04 (mouse)
## 1866                 embryo MmusDv:0000009  Theiler stage 05 (mouse)
## 1867                 embryo MmusDv:0000009  Theiler stage 05 (mouse)
## 1868                 embryo MmusDv:0000010  Theiler stage 06 (mouse)
## 1869                 embryo MmusDv:0000010  Theiler stage 06 (mouse)
## 1870                 embryo MmusDv:0000010  Theiler stage 06 (mouse)
##      IQRray.score MAS5.percent.present Normalization.type       Scan.date
## 1836     47883.54                32.01              gcRMA 02/27/ 16:31:23
## 1837     48592.69                33.04              gcRMA 02/27/ 16:19:35
## 1838     46959.46                29.06              gcRMA 02/20/ 17:56:57
## 1839     48053.21                30.73              gcRMA 02/20/ 18:08:12
## 1840     50769.96                33.42              gcRMA 12/21/ 14:48:27
## 1841     51133.57                34.18              gcRMA 12/21/ 15:00:32
## 1842     53766.59                38.92              gcRMA 12/23/ 15:51:49
## 1843     51714.74                38.11              gcRMA 12/30/ 13:57:52
## 1844     47625.00                30.18              gcRMA 02/20/ 19:22:46
## 1845     46662.15                29.14              gcRMA 02/20/ 19:45:42
## 1846     48439.18                31.95              gcRMA 03/06/ 14:36:39
## 1847     54791.02                41.80              gcRMA 04/26/ 20:26:07
## 1848     55477.89                42.30              gcRMA 04/26/ 19:57:23
## 1849     47968.59                34.32              gcRMA 02/27/ 14:52:08
## 1850     47188.40                33.64              gcRMA 03/06/ 16:20:26
## 1851     52613.70                41.14              gcRMA 12/30/ 14:13:53
## 1852     51534.73                40.46              gcRMA 12/30/ 14:26:59
## 1853     50929.56                39.04              gcRMA 03/14/ 16:51:24
## 1854     48914.31                36.87              gcRMA 03/14/ 16:11:45
## 1855     50681.62                39.25              gcRMA 04/27/ 17:11:34
## 1856     54046.04                41.60              gcRMA 04/25/ 14:33:00
## 1857     56463.66                43.79              gcRMA 04/26/ 20:36:26
## 1858     55470.60                42.93              gcRMA 04/26/ 20:10:43
## 1859     49949.18                37.08              gcRMA 03/06/ 14:22:14
## 1860     51584.40                39.13              gcRMA 03/06/ 16:07:51
## 1861     50419.38                35.91              gcRMA 02/27/ 15:04:39
## 1862     53141.50                40.88              gcRMA 04/26/ 19:33:43
## 1863     56462.55                44.11              gcRMA 04/26/ 19:44:03
## 1864     53715.91                42.78              gcRMA 04/27/ 17:46:32
## 1865     54169.92                41.01              gcRMA 04/25/ 15:03:49
## 1866     53501.41                41.45              gcRMA 04/25/ 15:41:24
## 1867     51745.67                40.51              gcRMA 04/27/ 16:59:27
## 1868     54152.55                43.47              gcRMA 04/27/ 17:24:54
## 1869     53305.39                42.83              gcRMA 04/25/ 14:52:10
## 1870     55872.16                45.41              gcRMA 04/27/ 17:34:59
##      Chip.type.ID  CDF.name                           Chip.type.name
## 1836     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1837     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1838     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1839     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1840     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1841     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1842     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1843     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1844     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1845     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1846     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1847     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1848     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1849     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1850     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1851     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1852     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1853     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1854     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1855     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1856     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1857     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1858     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1859     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1860     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1861     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1862     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1863     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1864     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1865     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1866     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1867     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1868     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1869     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
## 1870     A-AFFY-6 MG_U74Av2 Affymetrix GeneChip Murine Genome U74Av2
##      IQRray.score.threshold.for.the.chip.type
## 1836                                 44245.73
## 1837                                 44245.73
## 1838                                 44245.73
## 1839                                 44245.73
## 1840                                 44245.73
## 1841                                 44245.73
## 1842                                 44245.73
## 1843                                 44245.73
## 1844                                 44245.73
## 1845                                 44245.73
## 1846                                 44245.73
## 1847                                 44245.73
## 1848                                 44245.73
## 1849                                 44245.73
## 1850                                 44245.73
## 1851                                 44245.73
## 1852                                 44245.73
## 1853                                 44245.73
## 1854                                 44245.73
## 1855                                 44245.73
## 1856                                 44245.73
## 1857                                 44245.73
## 1858                                 44245.73
## 1859                                 44245.73
## 1860                                 44245.73
## 1861                                 44245.73
## 1862                                 44245.73
## 1863                                 44245.73
## 1864                                 44245.73
## 1865                                 44245.73
## 1866                                 44245.73
## 1867                                 44245.73
## 1868                                 44245.73
## 1869                                 44245.73
## 1870                                 44245.73
##      MAS5.percent.present.threshold.for.the.chip.type  Data.source
## 1836                                            26.68 ArrayExpress
## 1837                                            26.68 ArrayExpress
## 1838                                            26.68 ArrayExpress
## 1839                                            26.68 ArrayExpress
## 1840                                            26.68 ArrayExpress
## 1841                                            26.68 ArrayExpress
## 1842                                            26.68 ArrayExpress
## 1843                                            26.68 ArrayExpress
## 1844                                            26.68 ArrayExpress
## 1845                                            26.68 ArrayExpress
## 1846                                            26.68 ArrayExpress
## 1847                                            26.68 ArrayExpress
## 1848                                            26.68 ArrayExpress
## 1849                                            26.68 ArrayExpress
## 1850                                            26.68 ArrayExpress
## 1851                                            26.68 ArrayExpress
## 1852                                            26.68 ArrayExpress
## 1853                                            26.68 ArrayExpress
## 1854                                            26.68 ArrayExpress
## 1855                                            26.68 ArrayExpress
## 1856                                            26.68 ArrayExpress
## 1857                                            26.68 ArrayExpress
## 1858                                            26.68 ArrayExpress
## 1859                                            26.68 ArrayExpress
## 1860                                            26.68 ArrayExpress
## 1861                                            26.68 ArrayExpress
## 1862                                            26.68 ArrayExpress
## 1863                                            26.68 ArrayExpress
## 1864                                            26.68 ArrayExpress
## 1865                                            26.68 ArrayExpress
## 1866                                            26.68 ArrayExpress
## 1867                                            26.68 ArrayExpress
## 1868                                            26.68 ArrayExpress
## 1869                                            26.68 ArrayExpress
## 1870                                            26.68 ArrayExpress
##      Data.source.URL
## 1836            <NA>
## 1837            <NA>
## 1838            <NA>
## 1839            <NA>
## 1840            <NA>
## 1841            <NA>
## 1842            <NA>
## 1843            <NA>
## 1844            <NA>
## 1845            <NA>
## 1846            <NA>
## 1847            <NA>
## 1848            <NA>
## 1849            <NA>
## 1850            <NA>
## 1851            <NA>
## 1852            <NA>
## 1853            <NA>
## 1854            <NA>
## 1855            <NA>
## 1856            <NA>
## 1857            <NA>
## 1858            <NA>
## 1859            <NA>
## 1860            <NA>
## 1861            <NA>
## 1862            <NA>
## 1863            <NA>
## 1864            <NA>
## 1865            <NA>
## 1866            <NA>
## 1867            <NA>
## 1868            <NA>
## 1869            <NA>
## 1870            <NA>
##                                                                                                                                            Bgee.normalized.data.URL
## 1836 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1837 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1838 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1839 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1840 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1841 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1842 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1843 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1844 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1845 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1846 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1847 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1848 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1849 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1850 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1851 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1852 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1853 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1854 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1855 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1856 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1857 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1858 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1859 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1860 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1861 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1862 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1863 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1864 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1865 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1866 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1867 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1868 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1869 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
## 1870 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/affymetrix/Mus_musculus/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip
##                                Bgee.normalized.data.file
## 1836 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1837 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1838 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1839 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1840 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1841 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1842 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1843 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1844 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1845 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1846 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1847 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1848 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1849 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1850 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1851 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1852 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1853 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1854 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1855 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1856 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1857 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1858 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1859 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1860 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1861 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1862 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1863 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1864 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1865 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1866 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1867 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1868 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1869 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
## 1870 Mus_musculus_probesets_E-MEXP-51_A-AFFY-6_gcRMA.tsv
##                                                                                             Bgee.raw.file.URL
## 1836          ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Zygote1.CEL.gz
## 1837          ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Zygote2.CEL.gz
## 1838          ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Zygote3.CEL.gz
## 1839          ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Zygote4.CEL.gz
## 1840        ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/GVoocyte1.CEL.gz
## 1841        ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/GVoocyte2.CEL.gz
## 1842        ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/GVoocyte3.CEL.gz
## 1843        ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/GVoocyte4.CEL.gz
## 1844       ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/MIIoocyte1.CEL.gz
## 1845       ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/MIIoocyte2.CEL.gz
## 1846       ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/MIIoocyte3.CEL.gz
## 1847          ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/16cell1.CEL.gz
## 1848          ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/16cell2.CEL.gz
## 1849     ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Early2-cell1.CEL.gz
## 1850     ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Early2-cell2.CEL.gz
## 1851      ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Late2-cell1.CEL.gz
## 1852      ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Late2-cell2.CEL.gz
## 1853       ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Mid2-cell1.CEL.gz
## 1854       ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Mid2-cell2.CEL.gz
## 1855       ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/Mid2-cell3.CEL.gz
## 1856           ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/4Cell1.CEL.gz
## 1857           ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/4cell2.CEL.gz
## 1858           ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/4cell3.CEL.gz
## 1859           ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/8cell1.CEL.gz
## 1860           ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/8cell2.CEL.gz
## 1861           ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/8cell3.CEL.gz
## 1862 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/EarlyBlastocyst1.CEL.gz
## 1863 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/EarlyBlastocyst2.CEL.gz
## 1864 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/EarlyBlastocyst3.CEL.gz
## 1865 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/EarlyBlastocyst4.CEL.gz
## 1866   ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/MidBlastocyst1.CEL.gz
## 1867   ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/MidBlastocyst2.CEL.gz
## 1868  ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/LateBlastocyst1.CEL.gz
## 1869  ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/LateBlastocyst2.CEL.gz
## 1870  ftp://lausanne.isb-sib.ch/pub/databases/Bgee/affymetrix_data/cel_files/E-MEXP-51/LateBlastocyst3.CEL.gz
data_E_MEXP_51 <- getData(bgee_affymetrix, experimentId="E-MEXP-51")
## 
## Downloading expression data for the experiment E-MEXP-51 ...
## 
## Saved expression data file in /Users/jroux/Dropbox/RpackagePaper/Mus_musculus_Bgee_13_2 folder. Now unzipping /Users/jroux/Dropbox/RpackagePaper/Mus_musculus_Bgee_13_2/Mus_musculus_Affymetrix_probesets_E-MEXP-51.zip file...
## 
## Saving all data in .rds file...
head(data_E_MEXP_51)
##   Experiment.ID Chip.ID Probeset.ID            Gene.ID
## 1     E-MEXP-51 16cell1   100001_at ENSMUSG00000002033
## 2     E-MEXP-51 16cell1   100002_at ENSMUSG00000006522
## 3     E-MEXP-51 16cell1   100003_at ENSMUSG00000030592
## 4     E-MEXP-51 16cell1   100004_at ENSMUSG00000037461
## 5     E-MEXP-51 16cell1   100005_at ENSMUSG00000017386
## 6     E-MEXP-51 16cell1   100006_at ENSMUSG00000031673
##   Anatomical.entity.ID Anatomical.entity.name       Stage.ID
## 1       UBERON:0000085                 morula MmusDv:0000006
## 2       UBERON:0000085                 morula MmusDv:0000006
## 3       UBERON:0000085                 morula MmusDv:0000006
## 4       UBERON:0000085                 morula MmusDv:0000006
## 5       UBERON:0000085                 morula MmusDv:0000006
## 6       UBERON:0000085                 morula MmusDv:0000006
##                 Stage.name Log.of.normalized.signal.intensity
## 1 Theiler stage 03 (mouse)                               2.06
## 2 Theiler stage 03 (mouse)                               2.06
## 3 Theiler stage 03 (mouse)                               2.25
## 4 Theiler stage 03 (mouse)                               6.48
## 5 Theiler stage 03 (mouse)                               4.85
## 6 Theiler stage 03 (mouse)                               2.06
##   Detection.flag Detection.quality              State.in.Bgee
## 1         absent      high quality Used in no-expression call
## 2         absent      high quality Used in no-expression call
## 3         absent      high quality Used in no-expression call
## 4        present      high quality    Used in expression call
## 5         absent      high quality Used in no-expression call
## 6         absent      high quality Used in no-expression call
data_E_MEXP_51_formatted <- formatData(bgee_affymetrix, 
                                       data_E_MEXP_51, 
                                       callType="all", 
                                       stats="intensities")
## 
## Extracting expression data matrix...
## 
## Extracting features information...
## 
## Extracting samples information...
data_E_MEXP_51_formatted
## ExpressionSet (storageMode: lockedEnvironment)
## assayData: 9017 features, 35 samples 
##   element names: exprs 
## protocolData: none
## phenoData
##   sampleNames: 16cell1 16cell2 ... Zygote4 (35 total)
##   varLabels: Chip.ID Anatomical.entity.ID ... Stage.name (5 total)
##   varMetadata: labelDescription
## featureData
##   featureNames: 100001_at 100002_at ...
##     AFFX-TransRecMur/X57349_M_at (9017 total)
##   fvarLabels: Probeset.ID Gene.ID
##   fvarMetadata: labelDescription
## experimentData: use 'experimentData(object)'
## Annotation:
# matrix of expression intensities
head(exprs(data_E_MEXP_51_formatted))
##           16cell1 16cell2 4Cell1 4cell2 4cell3 8cell1 8cell2 8cell3
## 100001_at    2.06    2.06   2.06   2.06   2.06   2.06   2.06   2.21
## 100002_at    2.06    2.06   2.06   2.06   2.06   2.06   2.06   2.06
## 100003_at    2.25    2.06   2.87   4.09   2.08   2.06   2.28   2.06
## 100004_at    6.48    6.94   5.69   5.68   5.77   7.41   7.41   6.16
## 100005_at    4.85    4.85   4.85   4.85   4.85   4.47   4.84   4.84
## 100006_at    2.06    2.06   2.06   2.06   2.06   2.06   2.06   2.06
##           Early2-cell1 Early2-cell2 EarlyBlastocyst1 EarlyBlastocyst2
## 100001_at         2.06         2.06             2.06             2.06
## 100002_at         2.06         2.06             2.06             2.06
## 100003_at         2.06         2.06             2.06             2.06
## 100004_at         5.63         5.68             6.75             6.43
## 100005_at         4.85         4.85             4.85             4.85
## 100006_at         2.06         2.06             2.06             2.06
##           EarlyBlastocyst3 EarlyBlastocyst4 GVoocyte1 GVoocyte2 GVoocyte3
## 100001_at             2.06             2.06      2.06      2.06      2.06
## 100002_at             2.06             2.06      2.06      2.06      2.06
## 100003_at             2.45             2.06      2.06      2.06      2.06
## 100004_at             6.35             5.68      5.68      4.23      3.64
## 100005_at             4.85             4.85      4.85      4.85      5.22
## 100006_at             2.06             2.06      2.06      2.06      2.06
##           GVoocyte4 Late2-cell1 Late2-cell2 LateBlastocyst1
## 100001_at      2.06        2.06        2.06            2.06
## 100002_at      2.06        2.06        2.06            2.06
## 100003_at      2.06        2.06        2.06            2.06
## 100004_at      4.25        5.68        5.68            6.65
## 100005_at      4.85        5.29        5.16            4.85
## 100006_at      2.06        2.06        2.06            2.06
##           LateBlastocyst2 LateBlastocyst3 Mid2-cell1 Mid2-cell2 Mid2-cell3
## 100001_at            2.06            2.06       2.06       2.06       2.06
## 100002_at            2.06            2.06       2.06       2.06       2.06
## 100003_at            2.09            2.78       2.06       2.06       2.06
## 100004_at            5.68            6.52       5.68       5.42       5.68
## 100005_at            4.85            4.85       7.36       4.85       6.47
## 100006_at            2.06            2.06       2.06       2.06       2.06
##           MidBlastocyst1 MidBlastocyst2 MIIoocyte1 MIIoocyte2 MIIoocyte3
## 100001_at           2.06           2.06       2.06       2.06       2.06
## 100002_at           2.06           2.06       2.06       2.06       2.06
## 100003_at           2.06           2.06       2.06       2.06       2.06
## 100004_at           6.21           5.68       5.68       5.68       5.68
## 100005_at           4.83           4.85       4.85       4.85       4.85
## 100006_at           2.06           2.06       2.06       2.06       2.06
##           Zygote1 Zygote2 Zygote3 Zygote4
## 100001_at    2.06    2.06    2.06    2.06
## 100002_at    2.06    2.06    2.06    2.06
## 100003_at    2.06    2.06    2.06    2.06
## 100004_at    5.63    5.68    5.68    5.02
## 100005_at    4.85    4.85    4.85    6.70
## 100006_at    2.06    2.06    2.06    2.06
# annotation of samples
pData(data_E_MEXP_51_formatted)
##                           Chip.ID Anatomical.entity.ID
## 16cell1                   16cell1       UBERON:0000085
## 16cell2                   16cell2       UBERON:0000085
## 4Cell1                     4Cell1       UBERON:0000922
## 4cell2                     4cell2       UBERON:0000922
## 4cell3                     4cell3       UBERON:0000922
## 8cell1                     8cell1       UBERON:0000922
## 8cell2                     8cell2       UBERON:0000922
## 8cell3                     8cell3       UBERON:0000922
## Early2-cell1         Early2-cell1       UBERON:0000922
## Early2-cell2         Early2-cell2       UBERON:0000922
## EarlyBlastocyst1 EarlyBlastocyst1       UBERON:0000922
## EarlyBlastocyst2 EarlyBlastocyst2       UBERON:0000922
## EarlyBlastocyst3 EarlyBlastocyst3       UBERON:0000922
## EarlyBlastocyst4 EarlyBlastocyst4       UBERON:0000922
## GVoocyte1               GVoocyte1           CL:0000654
## GVoocyte2               GVoocyte2           CL:0000654
## GVoocyte3               GVoocyte3           CL:0000654
## GVoocyte4               GVoocyte4           CL:0000654
## Late2-cell1           Late2-cell1       UBERON:0000922
## Late2-cell2           Late2-cell2       UBERON:0000922
## LateBlastocyst1   LateBlastocyst1       UBERON:0000922
## LateBlastocyst2   LateBlastocyst2       UBERON:0000922
## LateBlastocyst3   LateBlastocyst3       UBERON:0000922
## Mid2-cell1             Mid2-cell1       UBERON:0000922
## Mid2-cell2             Mid2-cell2       UBERON:0000922
## Mid2-cell3             Mid2-cell3       UBERON:0000922
## MidBlastocyst1     MidBlastocyst1       UBERON:0000922
## MidBlastocyst2     MidBlastocyst2       UBERON:0000922
## MIIoocyte1             MIIoocyte1           CL:0000655
## MIIoocyte2             MIIoocyte2           CL:0000655
## MIIoocyte3             MIIoocyte3           CL:0000655
## Zygote1                   Zygote1           CL:0000365
## Zygote2                   Zygote2           CL:0000365
## Zygote3                   Zygote3           CL:0000365
## Zygote4                   Zygote4           CL:0000365
##                  Anatomical.entity.name       Stage.ID
## 16cell1                          morula MmusDv:0000006
## 16cell2                          morula MmusDv:0000006
## 4Cell1                           embryo MmusDv:0000006
## 4cell2                           embryo MmusDv:0000006
## 4cell3                           embryo MmusDv:0000006
## 8cell1                           embryo MmusDv:0000006
## 8cell2                           embryo MmusDv:0000006
## 8cell3                           embryo MmusDv:0000006
## Early2-cell1                     embryo MmusDv:0000005
## Early2-cell2                     embryo MmusDv:0000005
## EarlyBlastocyst1                 embryo MmusDv:0000008
## EarlyBlastocyst2                 embryo MmusDv:0000008
## EarlyBlastocyst3                 embryo MmusDv:0000008
## EarlyBlastocyst4                 embryo MmusDv:0000008
## GVoocyte1                primary oocyte UBERON:0000113
## GVoocyte2                primary oocyte UBERON:0000113
## GVoocyte3                primary oocyte UBERON:0000113
## GVoocyte4                primary oocyte UBERON:0000113
## Late2-cell1                      embryo MmusDv:0000005
## Late2-cell2                      embryo MmusDv:0000005
## LateBlastocyst1                  embryo MmusDv:0000010
## LateBlastocyst2                  embryo MmusDv:0000010
## LateBlastocyst3                  embryo MmusDv:0000010
## Mid2-cell1                       embryo MmusDv:0000005
## Mid2-cell2                       embryo MmusDv:0000005
## Mid2-cell3                       embryo MmusDv:0000005
## MidBlastocyst1                   embryo MmusDv:0000009
## MidBlastocyst2                   embryo MmusDv:0000009
## MIIoocyte1             secondary oocyte UBERON:0000113
## MIIoocyte2             secondary oocyte UBERON:0000113
## MIIoocyte3             secondary oocyte UBERON:0000113
## Zygote1                          zygote UBERON:0000106
## Zygote2                          zygote UBERON:0000106
## Zygote3                          zygote UBERON:0000106
## Zygote4                          zygote UBERON:0000106
##                                 Stage.name
## 16cell1           Theiler stage 03 (mouse)
## 16cell2           Theiler stage 03 (mouse)
## 4Cell1            Theiler stage 03 (mouse)
## 4cell2            Theiler stage 03 (mouse)
## 4cell3            Theiler stage 03 (mouse)
## 8cell1            Theiler stage 03 (mouse)
## 8cell2            Theiler stage 03 (mouse)
## 8cell3            Theiler stage 03 (mouse)
## Early2-cell1      Theiler stage 02 (mouse)
## Early2-cell2      Theiler stage 02 (mouse)
## EarlyBlastocyst1  Theiler stage 04 (mouse)
## EarlyBlastocyst2  Theiler stage 04 (mouse)
## EarlyBlastocyst3  Theiler stage 04 (mouse)
## EarlyBlastocyst4  Theiler stage 04 (mouse)
## GVoocyte1        post-juvenile adult stage
## GVoocyte2        post-juvenile adult stage
## GVoocyte3        post-juvenile adult stage
## GVoocyte4        post-juvenile adult stage
## Late2-cell1       Theiler stage 02 (mouse)
## Late2-cell2       Theiler stage 02 (mouse)
## LateBlastocyst1   Theiler stage 06 (mouse)
## LateBlastocyst2   Theiler stage 06 (mouse)
## LateBlastocyst3   Theiler stage 06 (mouse)
## Mid2-cell1        Theiler stage 02 (mouse)
## Mid2-cell2        Theiler stage 02 (mouse)
## Mid2-cell3        Theiler stage 02 (mouse)
## MidBlastocyst1    Theiler stage 05 (mouse)
## MidBlastocyst2    Theiler stage 05 (mouse)
## MIIoocyte1       post-juvenile adult stage
## MIIoocyte2       post-juvenile adult stage
## MIIoocyte3       post-juvenile adult stage
## Zygote1                       zygote stage
## Zygote2                       zygote stage
## Zygote3                       zygote stage
## Zygote4                       zygote stage
# annotation of probesets
head(fData(data_E_MEXP_51_formatted))
##           Probeset.ID            Gene.ID
## 100001_at   100001_at ENSMUSG00000002033
## 100002_at   100002_at ENSMUSG00000006522
## 100003_at   100003_at ENSMUSG00000030592
## 100004_at   100004_at ENSMUSG00000037461
## 100005_at   100005_at ENSMUSG00000017386
## 100006_at   100006_at ENSMUSG00000031673
# specify species and data type
bgee_rnaseq <- Bgee$new(species="Macaca_mulatta", dataType="rna_seq", release="13.2")
## 
## Querying Bgee to get release information...
## 
## NOTE: the file describing Bgee species information for release 13_2 was found in the download directory /Users/jroux/Dropbox/RpackagePaper. Data will not be redownloaded.
## 
## API key built: 696a8ee5f27f212d71349c131d413fb0de7947e688c95fcdd001689789c7333dbdf6fad8d4d48c239a3e0f4e60a3e74cd5b98398d6a3f93286288211920ddbdc
# retrieve annotation of RNA-seq samples and experiments
annotation_bgee_macaque_rna_seq <- getAnnotation(bgee_rnaseq)
## 
## Downloading annotation files...
## 
## Saved annotation files in /Users/jroux/Dropbox/RpackagePaper/Macaca_mulatta_Bgee_13_2 folder.
sample_annotation <- annotation_bgee_macaque_rna_seq$sample.annotation
experiment_annotation <- annotation_bgee_macaque_rna_seq$experiment.annotation

# list experiments including both brain and liver samples
selected_experiments <- 
  intersect(unique(sample_annotation$Experiment.ID[sample_annotation$Anatomical.entity.ID 
                                                   == "UBERON:0000955"]), 
            unique(sample_annotation$Experiment.ID[sample_annotation$Anatomical.entity.ID 
                                                   == "UBERON:0002107"]))
experiment_annotation[experiment_annotation$Experiment.ID %in% selected_experiments,]
##   Experiment.ID Library.count Condition.count Organ.count Stage.count
## 1      GSE41637            27               9           9           1
## 2      GSE30352            13               8           7           3
##   Data.source                                            Data.source.URL
## 1         GEO http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41637
## 2         GEO http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE30352
##                                                                                                                                                 Bgee.normalized.data.URL
## 1 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/rna_seq/Macaca_mulatta/Macaca_mulatta_RNA-Seq_read_counts_RPKM_GSE41637.tsv.zip
## 2 ftp://lausanne.isb-sib.ch/pub/databases/Bgee/bgee_v13_1/download/processed_expr_values/rna_seq/Macaca_mulatta/Macaca_mulatta_RNA-Seq_read_counts_RPKM_GSE30352.tsv.zip
##                                                             Experiment.name
## 1 Evolutionary dynamics of gene and isoform regulation in mammalian tissues
## 2               The evolution of gene expression levels in mammalian organs
##                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Experiment.description
## 1                                                                                                                                                                                                                                                                                                                                                      Most mammalian genes produce multiple distinct mRNAs through alternative splicing, but the extent of splicing conservation is not clear. To assess tissue-specific transcriptome variation across mammals, we sequenced cDNA from 9 tissues from 4 mammals and one bird in biological triplicate, at unprecedented depth. We find that while tissue-specific gene expression programs are largely conserved, alternative splicing is well conserved in only a subset of tissues and is frequently lineage-specific. Thousands of novel, lineage-specific and conserved alternative exons were identified; widely conserved alternative exons had signatures of binding by MBNL, PTB, RBFOX, STAR and TIA family splicing factors, implicating them as ancestral mammalian splicing regulators. Our data also indicates that alternative splicing is often used to alter protein phosphorylatability, delimiting the scope of kinase signaling.
## 2 Changes in gene expression are thought to underlie many of the phenotypic differences between species. However, large-scale analyses of gene expression evolution were until recently prevented by technological limitations. Here we report the sequencing of polyadenylated RNA from six organs across ten species that represent all major mammalian lineages (placentals, marsupials and monotremes) and birds (the evolutionary outgroup), with the goal of understanding the dynamics of mammalian transcriptome evolution. We show that the rate of gene expression evolution varies among organs, lineages and chromosomes, owing to differences in selective pressures: transcriptome change was slow in nervous tissues and rapid in testes, slower in rodents than in apes and monotremes, and rapid for the X chromosome right after its formation. Although gene expression evolution in mammals was strongly shaped by purifying selection, we identify numerous potentially selectively driven expression switches, which occurred at different rates across lineages and tissues and which probably contributed to the specific organ biology of various mammals. Our transcriptome data provide a valuable resource for functional and evolutionary analyses of mammalian genomes.
# check whether experiments include biological replicates
sample_annotation[sample_annotation$Experiment.ID %in% selected_experiments & 
    (sample_annotation$Anatomical.entity.ID == "UBERON:0000955" 
     | sample_annotation$Anatomical.entity.ID == "UBERON:0002107"), 1:6]
##    Experiment.ID Library.ID Library.secondary.ID Anatomical.entity.ID
## 10      GSE41637 GSM1020693            SRX196317       UBERON:0000955
## 11      GSE41637 GSM1020702            SRX196326       UBERON:0000955
## 12      GSE41637 GSM1020711            SRX196335       UBERON:0000955
## 25      GSE41637 GSM1020697            SRX196321       UBERON:0002107
## 26      GSE41637 GSM1020706            SRX196330       UBERON:0002107
## 27      GSE41637 GSM1020715            SRX196339       UBERON:0002107
## 35      GSE30352  GSM752631            SRX081922       UBERON:0000955
## 36      GSE30352  GSM752632            SRX081923       UBERON:0000955
## 39      GSE30352  GSM752640            SRX081931       UBERON:0002107
## 40      GSE30352  GSM752641            SRX081932       UBERON:0002107
##    Anatomical.entity.name       Stage.ID
## 10                  brain UBERON:0018241
## 11                  brain UBERON:0018241
## 12                  brain UBERON:0018241
## 25                  liver UBERON:0018241
## 26                  liver UBERON:0018241
## 27                  liver UBERON:0018241
## 35                  brain MmulDv:0000028
## 36                  brain MmulDv:0000028
## 39                  liver MmulDv:0000028
## 40                  liver MmulDv:0000028
data_GSE41637 <- getData(bgee_rnaseq, experimentId="GSE41637")
## 
## Downloading expression data for the experiment GSE41637 ...
## 
## Saved expression data file in /Users/jroux/Dropbox/RpackagePaper/Macaca_mulatta_Bgee_13_2 folder. Now unzipping /Users/jroux/Dropbox/RpackagePaper/Macaca_mulatta_Bgee_13_2/Macaca_mulatta_RNA-Seq_read_counts_RPKM_GSE41637.tsv.zip file...
## 
Read 42.9% of 816642 rows
Read 816642 rows and 13 (of 13) columns from 0.126 GB file in 00:00:03
## 
## Saving all data in .rds file...
data_GSE41637_formatted <- formatData(bgee_rnaseq, 
                                      data_GSE41637, 
                                      callType="all", 
                                      stats="counts")
## 
## Extracting expression data matrix...
## 
## Extracting features information...
## 
## Extracting samples information...
data_GSE41637_formatted
## ExpressionSet (storageMode: lockedEnvironment)
## assayData: 30246 features, 27 samples 
##   element names: exprs 
## protocolData: none
## phenoData
##   sampleNames: GSM1020693 GSM1020694 ... GSM1020719 (27 total)
##   varLabels: Library.ID Anatomical.entity.ID ... Stage.name (5
##     total)
##   varMetadata: labelDescription
## featureData
##   featureNames: ENSMMUG00000000001 ENSMMUG00000000002 ...
##     ENSMMUG00000037447 (30246 total)
##   fvarLabels: Gene.ID
##   fvarMetadata: labelDescription
## experimentData: use 'experimentData(object)'
## Annotation:
# for simplicity, keep only one sample per condition
data_E_MEXP_51_formatted <- 
  data_E_MEXP_51_formatted[, !duplicated(pData(data_E_MEXP_51_formatted)[2:5])]

# order developmental stages
data_E_MEXP_51_formatted <- data_E_MEXP_51_formatted[, c(5,8,9,3,2,1,4,7,6)]

# filter out rows with no variance
data_E_MEXP_51_formatted <- 
  data_E_MEXP_51_formatted[apply(exprs(data_E_MEXP_51_formatted), 1, sd) != 0, ]
library(Mfuzz)
## Loading required package: e1071
# standardize matric of expression data
z.mat <- standardise(data_E_MEXP_51_formatted)
# cluster data into 16 clusters
clusters <- mfuzz(z.mat, centers=16, m=1.25)
# visualizing clusters
mfuzz.plot2(z.mat, 
            cl=clusters, 
            mfrow=c(4,4), 
            colo="fancy", 
            time.labels=row.names(pData(z.mat)), 
            las=2, xlab="", ylab="Standardized expression level",
            x11 = FALSE)

# differential expression analysis with edgeR
library(edgeR)
## Loading required package: limma
## 
## Attaching package: 'limma'
## The following object is masked from 'package:BiocGenerics':
## 
##     plotMA
# subset the dataset to brain and liver
brain_liver <- 
  data_GSE41637_formatted[, pData(data_GSE41637_formatted)$Anatomical.entity.name 
                            %in% c("brain", "liver")]  

# filter out very lowly expressed genes
brain_liver_filtered <- brain_liver[rowSums(cpm(brain_liver) > 1) > 3, ]

# create edgeR DGElist object
dge <- DGEList(counts= brain_liver_filtered, 
               group=pData(brain_liver_filtered)$Anatomical.entity.name)
dge <- calcNormFactors(dge)
dge <- estimateCommonDisp(dge)
dge <- estimateTagwiseDisp(dge)
de <- exactTest(dge, pair=c("brain","liver"))
de.genes <- topTags(de, n=nrow(de))$table
# MA plot with DE genes highlighted
plotSmear(dge, de.tags=rownames(de.genes)[de.genes$FDR < 0.01], cex=0.3)

bgee_topanat <- Bgee$new(species="Danio_rerio", release="13.2")
## 
## NOTE: You did not specify any data type. The argument dataType will be set to c("rna_seq","affymetrix","est","in_situ") for the next steps.
## 
## Querying Bgee to get release information...
## 
## NOTE: the file describing Bgee species information for release 13_2 was found in the download directory /Users/jroux/Dropbox/RpackagePaper. Data will not be redownloaded.
## 
## API key built: 696a8ee5f27f212d71349c131d413fb0de7947e688c95fcdd001689789c7333dbdf6fad8d4d48c239a3e0f4e60a3e74cd5b98398d6a3f93286288211920ddbdc
myTopAnatData <- loadTopAnatData(bgee_topanat)
## 
## Building URLs to retrieve organ relationships from Bgee.........
##    URL successfully built (http://r13_2.bgee.org/?page=dao&action=org.bgee.model.dao.api.ontologycommon.RelationDAO.getAnatEntityRelations&display_type=tsv&species_list=7955&attr_list=SOURCE_ID&attr_list=TARGET_ID&api_key=696a8ee5f27f212d71349c131d413fb0de7947e688c95fcdd001689789c7333dbdf6fad8d4d48c239a3e0f4e60a3e74cd5b98398d6a3f93286288211920ddbdc&source=BgeeDB_R_package&source_version=2.0.0)
##    Submitting URL to Bgee webservice (can be long)
##    Got results from Bgee webservice. Files are written in "/Users/jroux/Dropbox/RpackagePaper/Danio_rerio_Bgee_13_2"
## 
## Building URLs to retrieve organ names from Bgee.................
##    URL successfully built (http://r13_2.bgee.org/?page=dao&action=org.bgee.model.dao.api.anatdev.AnatEntityDAO.getAnatEntities&display_type=tsv&species_list=7955&attr_list=ID&attr_list=NAME&api_key=696a8ee5f27f212d71349c131d413fb0de7947e688c95fcdd001689789c7333dbdf6fad8d4d48c239a3e0f4e60a3e74cd5b98398d6a3f93286288211920ddbdc&source=BgeeDB_R_package&source_version=2.0.0)
##    Submitting URL to Bgee webservice (can be long)
##    Got results from Bgee webservice. Files are written in "/Users/jroux/Dropbox/RpackagePaper/Danio_rerio_Bgee_13_2"
## 
## Building URLs to retrieve mapping of gene to organs from Bgee...
##    URL successfully built (http://r13_2.bgee.org/?page=dao&action=org.bgee.model.dao.api.expressiondata.ExpressionCallDAO.getExpressionCalls&display_type=tsv&species_list=7955&attr_list=GENE_ID&attr_list=ANAT_ENTITY_ID&api_key=696a8ee5f27f212d71349c131d413fb0de7947e688c95fcdd001689789c7333dbdf6fad8d4d48c239a3e0f4e60a3e74cd5b98398d6a3f93286288211920ddbdc&source=BgeeDB_R_package&source_version=2.0.0)
##    Submitting URL to Bgee webservice (can be long)
##    Got results from Bgee webservice. Files are written in "/Users/jroux/Dropbox/RpackagePaper/Danio_rerio_Bgee_13_2"
## 
## Parsing the results.............................................
## 
## Adding BGEE:0 as unique root of all terms of the ontology.......
## 
## Done.
str(myTopAnatData)
## List of 4
##  $ gene2anatomy       :List of 18715
##   ..$ ENSDARG00000000001: chr [1:3] "UBERON:0000468" "UBERON:0001997" "ZFA:0001093"
##   ..$ ENSDARG00000000002: chr [1:11] "UBERON:0000019" "UBERON:0000468" "UBERON:0000965" "UBERON:0002329" ...
##   ..$ ENSDARG00000000018: chr [1:28] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000000019: chr [1:23] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000000068: chr [1:53] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000000069: chr [1:23] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000000102: chr [1:7] "UBERON:0000151" "UBERON:0000468" "UBERON:0001774" "UBERON:0002329" ...
##   ..$ ENSDARG00000000103: chr [1:20] "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000000142: chr [1:4] "UBERON:0000080" "UBERON:0000468" "UBERON:0000992" "UBERON:0001555"
##   ..$ ENSDARG00000000151: chr [1:13] "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000000161: chr "UBERON:0000955"
##   ..$ ENSDARG00000000175: chr [1:36] "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000000183: chr [1:10] "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000000189: chr [1:6] "UBERON:0000965" "UBERON:0001891" "UBERON:0001893" "UBERON:0001894" ...
##   ..$ ENSDARG00000000212: chr [1:20] "UBERON:0000004" "UBERON:0000019" "UBERON:0000080" "UBERON:0000468" ...
##   ..$ ENSDARG00000000229: chr [1:4] "UBERON:0000307" "UBERON:0000468" "UBERON:0000992" "UBERON:0007010"
##   ..$ ENSDARG00000000241: chr [1:22] "UBERON:0000080" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000000324: chr "UBERON:0000473"
##   ..$ ENSDARG00000000369: chr [1:2] "UBERON:0000080" "UBERON:0000468"
##   ..$ ENSDARG00000000370: chr "UBERON:0000468"
##   ..$ ENSDARG00000000380: chr [1:9] "UBERON:0000019" "UBERON:0000468" "UBERON:0000922" "UBERON:0000955" ...
##   ..$ ENSDARG00000000384: chr [1:25] "UBERON:0000019" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000000394: chr [1:17] "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000000423: chr [1:3] "UBERON:0000468" "UBERON:0000473" "UBERON:0000992"
##   ..$ ENSDARG00000000442: chr [1:20] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000000460: chr "UBERON:0000948"
##   ..$ ENSDARG00000000472: chr [1:24] "UBERON:0000468" "UBERON:0000955" "UBERON:0001675" "UBERON:0001700" ...
##   ..$ ENSDARG00000000476: chr [1:16] "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" "UBERON:0000473" ...
##   ..$ ENSDARG00000000489: chr [1:18] "UBERON:0000307" "UBERON:0000468" "UBERON:0000473" "UBERON:0000922" ...
##   ..$ ENSDARG00000000503: chr [1:14] "UBERON:0000019" "UBERON:0000468" "UBERON:0000473" "UBERON:0000922" ...
##   ..$ ENSDARG00000000516: chr [1:3] "UBERON:0000468" "UBERON:0000473" "UBERON:0004734"
##   ..$ ENSDARG00000000529: chr [1:22] "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" "UBERON:0000473" ...
##   ..$ ENSDARG00000000540: chr [1:20] "UBERON:0000019" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000000551: chr [1:22] "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" "UBERON:0000955" ...
##   ..$ ENSDARG00000000563: chr [1:31] "UBERON:0000019" "UBERON:0000080" "UBERON:0000151" "UBERON:0000468" ...
##   ..$ ENSDARG00000000567: chr [1:2] "UBERON:0000019" "UBERON:0000468"
##   ..$ ENSDARG00000000568: chr [1:20] "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000000588: chr [1:2] "UBERON:0000468" "UBERON:0001997"
##   ..$ ENSDARG00000000606: chr [1:2] "UBERON:0000019" "UBERON:0000468"
##   ..$ ENSDARG00000000631: chr [1:21] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000000638: chr [1:3] "UBERON:0000019" "UBERON:0000468" "UBERON:0000966"
##   ..$ ENSDARG00000000651: chr [1:14] "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000000656: chr [1:12] "UBERON:0000019" "UBERON:0000080" "UBERON:0000468" "UBERON:0000473" ...
##   ..$ ENSDARG00000000666: chr [1:6] "UBERON:0000019" "UBERON:0000080" "UBERON:0000468" "UBERON:0000473" ...
##   ..$ ENSDARG00000000690: chr [1:24] "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000000729: chr [1:19] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000000730: chr [1:4] "UBERON:0000468" "UBERON:0002107" "UBERON:0008897" "ZFA:0001093"
##   ..$ ENSDARG00000000747: chr [1:3] "UBERON:0000019" "UBERON:0000468" "UBERON:0001555"
##   ..$ ENSDARG00000000760: chr [1:20] "UBERON:0000019" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000000767: chr [1:30] "UBERON:0000019" "UBERON:0000033" "UBERON:0000080" "UBERON:0000178" ...
##   ..$ ENSDARG00000000779: chr [1:24] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000000796: chr [1:31] "UBERON:0000004" "UBERON:0000019" "UBERON:0000080" "UBERON:0000151" ...
##   ..$ ENSDARG00000000804: chr [1:3] "UBERON:0000468" "UBERON:0001997" "ZFA:0001093"
##   ..$ ENSDARG00000000830: chr [1:5] "UBERON:0000080" "UBERON:0000468" "UBERON:0000992" "UBERON:0002107" ...
##   ..$ ENSDARG00000000837: chr [1:3] "UBERON:0000178" "UBERON:0000468" "UBERON:0001997"
##   ..$ ENSDARG00000000853: chr [1:22] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000000857: chr [1:34] "UBERON:0000004" "UBERON:0000080" "UBERON:0000151" "UBERON:0000307" ...
##   ..$ ENSDARG00000000861: chr [1:13] "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" "UBERON:0000473" ...
##   ..$ ENSDARG00000000887: chr [1:29] "UBERON:0000019" "UBERON:0000080" "UBERON:0000151" "UBERON:0000307" ...
##   ..$ ENSDARG00000000906: chr [1:6] "UBERON:0000080" "UBERON:0000468" "UBERON:0001555" "UBERON:0001997" ...
##   ..$ ENSDARG00000000935: chr [1:18] "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000000943: chr [1:3] "UBERON:0000080" "UBERON:0000468" "ZFA:0001093"
##   ..$ ENSDARG00000000966: chr [1:26] "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000000972: chr [1:23] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000001014: chr [1:4] "UBERON:0000019" "UBERON:0000080" "UBERON:0000468" "UBERON:0008897"
##   ..$ ENSDARG00000001015: chr [1:3] "UBERON:0000019" "UBERON:0000468" "UBERON:0000955"
##   ..$ ENSDARG00000001057: chr [1:33] "UBERON:0000019" "UBERON:0000307" "UBERON:0000468" "UBERON:0000473" ...
##   ..$ ENSDARG00000001127: chr [1:5] "CL:0005000" "UBERON:0000468" "UBERON:0000955" "UBERON:0001898" ...
##   ..$ ENSDARG00000001129: chr [1:20] "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" "UBERON:0000473" ...
##   ..$ ENSDARG00000001162: chr [1:17] "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000001169: chr [1:14] "UBERON:0000019" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000001210: chr [1:7] "UBERON:0000019" "UBERON:0000080" "UBERON:0000468" "UBERON:0000473" ...
##   ..$ ENSDARG00000001220: chr [1:23] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000001234: chr [1:3] "UBERON:0000468" "UBERON:0000955" "UBERON:0000966"
##   ..$ ENSDARG00000001241: chr [1:27] "UBERON:0000019" "UBERON:0000080" "UBERON:0000151" "UBERON:0000307" ...
##   ..$ ENSDARG00000001244: chr [1:22] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000001249: chr [1:4] "UBERON:0000080" "UBERON:0000468" "UBERON:0000473" "UBERON:0000992"
##   ..$ ENSDARG00000001285: chr [1:2] "UBERON:0000468" "UBERON:0001997"
##   ..$ ENSDARG00000001303: chr [1:16] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000001313: chr [1:25] "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" "UBERON:0000473" ...
##   ..$ ENSDARG00000001354: chr "UBERON:0000468"
##   ..$ ENSDARG00000001414: chr [1:7] "UBERON:0000468" "UBERON:0000473" "UBERON:0000922" "UBERON:0001997" ...
##   ..$ ENSDARG00000001431: chr [1:28] "UBERON:0000019" "UBERON:0000080" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000001437: chr [1:8] "UBERON:0000033" "UBERON:0000468" "UBERON:0000966" "UBERON:0001017" ...
##   ..$ ENSDARG00000001442: chr [1:13] "UBERON:0000019" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000001447: chr [1:3] "UBERON:0000307" "UBERON:0000468" "UBERON:0007010"
##   ..$ ENSDARG00000001452: chr [1:13] "UBERON:0000080" "UBERON:0000468" "UBERON:0000473" "UBERON:0000926" ...
##   ..$ ENSDARG00000001463: chr [1:4] "UBERON:0000019" "UBERON:0000468" "UBERON:0000966" "UBERON:0001997"
##   ..$ ENSDARG00000001498: chr [1:4] "UBERON:0000080" "UBERON:0000468" "UBERON:0000992" "UBERON:0001846"
##   ..$ ENSDARG00000001549: chr [1:13] "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000001557: chr [1:25] "UBERON:0000019" "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" ...
##   ..$ ENSDARG00000001558: chr [1:22] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000001559: chr "ZFA:0001093"
##   ..$ ENSDARG00000001572: chr "UBERON:0000080"
##   ..$ ENSDARG00000001578: chr [1:28] "UBERON:0000019" "UBERON:0000080" "UBERON:0000307" "UBERON:0000468" ...
##   ..$ ENSDARG00000001621: chr "UBERON:0000468"
##   ..$ ENSDARG00000001634: chr [1:13] "UBERON:0000019" "UBERON:0000080" "UBERON:0000151" "UBERON:0000468" ...
##   ..$ ENSDARG00000001637: chr [1:16] "UBERON:0000307" "UBERON:0000468" "UBERON:0000922" "UBERON:0000948" ...
##   ..$ ENSDARG00000001656: chr [1:13] "UBERON:0000019" "UBERON:0000468" "UBERON:0000473" "UBERON:0000948" ...
##   .. [list output truncated]
##   ..- attr(*, "dim")= int 18715
##   ..- attr(*, "dimnames")=List of 1
##   .. ..$ : chr [1:18715] "ENSDARG00000000001" "ENSDARG00000000002" "ENSDARG00000000018" "ENSDARG00000000019" ...
##  $ organ.relationships:List of 12587
##   ..$ AEO:0000013   : chr "UBERON:0000479"
##   ..$ AEO:0000127   : chr "UBERON:0005423"
##   ..$ AEO:0000129   : chr "UBERON:0005423"
##   ..$ AEO:0000131   : chr "UBERON:0005423"
##   ..$ AEO:0000153   : chr "AEO:0000187"
##   ..$ AEO:0000162   : chr "UBERON:0006984"
##   ..$ AEO:0000173   : chr [1:2] "UBERON:0002416" "UBERON:0000020"
##   ..$ AEO:0000180   : chr "UBERON:0002418"
##   ..$ AEO:0000185   : chr [1:2] "UBERON:0004288" "UBERON:0007475"
##   ..$ AEO:0000187   : chr "UBERON:0000481"
##   ..$ AEO:0000188   : chr [1:2] "UBERON:0000463" "UBERON:0000476"
##   ..$ AEO:0000189   : chr "AEO:0000187"
##   ..$ AEO:0000196   : chr "UBERON:0002548"
##   ..$ AEO:0000210   : chr "UBERON:0000480"
##   ..$ AEO:0000211   : chr [1:2] "UBERON:0000477" "UBERON:0005423"
##   ..$ AEO:0000215   : chr "UBERON:0010064"
##   ..$ AEO:0000217   : chr "UBERON:0005423"
##   ..$ AEO:0001003   : chr "UBERON:0000476"
##   ..$ AEO:0001006   : chr "UBERON:0000463"
##   ..$ AEO:0001007   : chr [1:2] "UBERON:0000483" "UBERON:0005423"
##   ..$ AEO:0001009   : chr "UBERON:0004022"
##   ..$ AEO:0001010   : chr "UBERON:0004022"
##   ..$ AEO:0001013   : chr [1:2] "UBERON:0010314" "UBERON:0002020"
##   ..$ AEO:0001014   : chr "UBERON:0005423"
##   ..$ AEO:0001019   : chr "UBERON:0005423"
##   ..$ AEO:0001020   : chr "UBERON:0000479"
##   ..$ AEO:0001021   : chr "UBERON:0000479"
##   ..$ CARO:0000049  : chr "UBERON:0010895"
##   ..$ CARO:0000050  : chr "UBERON:0010895"
##   ..$ CARO:0000064  : chr "CL:0000003"
##   ..$ CL:0000000    : chr "GO:0005575"
##   ..$ CL:0000001    : chr "CL:0000010"
##   ..$ CL:0000003    : chr [1:3] "GO:0005623" "CL:0000000" "UBERON:0000061"
##   ..$ CL:0000005    : chr [1:2] "UBERON:0010313" "CL:0000057"
##   ..$ CL:0000006    : chr [1:2] "CL:0000197" "CL:0000101"
##   ..$ CL:0000007    : chr "CL:0002321"
##   ..$ CL:0000008    : chr "CL:0000333"
##   ..$ CL:0000010    : chr "CL:0000578"
##   ..$ CL:0000011    : chr [1:2] "UBERON:0003083" "CL:0000333"
##   ..$ CL:0000014    : chr [1:2] "CL:0000039" "CL:0000034"
##   ..$ CL:0000015    : chr "CL:0000586"
##   ..$ CL:0000016    : chr [1:2] "CL:0000014" "CL:0000015"
##   ..$ CL:0000017    : chr [1:2] "UBERON:0000473" "CL:0000015"
##   ..$ CL:0000018    : chr [1:2] "CL:0000015" "CL:0000413"
##   ..$ CL:0000019    : chr [1:3] "CL:0000064" "CL:0000219" "CL:0000408"
##   ..$ CL:0000020    : chr [1:2] "UBERON:0000473" "CL:0000015"
##   ..$ CL:0000021    : chr "CL:0000586"
##   ..$ CL:0000022    : chr [1:2] "CL:0000014" "CL:0000021"
##   ..$ CL:0000023    : chr [1:2] "UBERON:0001305" "CL:0000021"
##   ..$ CL:0000024    : chr "CL:0000021"
##   ..$ CL:0000025    : chr "CL:0000675"
##   ..$ CL:0000026    : chr [1:2] "CL:0000039" "CL:0000412"
##   ..$ CL:0000027    : chr [1:2] "UBERON:0010313" "CL:0000192"
##   ..$ CL:0000028    : chr "CL:2000029"
##   ..$ CL:0000029    : chr [1:2] "UBERON:0010313" "CL:0000540"
##   ..$ CL:0000030    : chr [1:2] "CL:0000055" "UBERON:0004121"
##   ..$ CL:0000031    : chr [1:2] "CL:0000047" "CL:0000055"
##   ..$ CL:0000032    : chr [1:2] "CL:0002321" "UBERON:0004121"
##   ..$ CL:0000033    : chr "CL:0000151"
##   ..$ CL:0000034    : chr "CL:0000003"
##   ..$ CL:0000035    : chr "CL:0000723"
##   ..$ CL:0000036    : chr "CL:0000035"
##   ..$ CL:0000037    : chr [1:3] "UBERON:0002390" "CL:0000048" "CL:0008001"
##   ..$ CL:0000038    : chr [1:2] "CL:0000764" "CL:0000839"
##   ..$ CL:0000039    : chr "CL:0000548"
##   ..$ CL:0000040    : chr [1:3] "CL:0000763" "CL:0002194" "UBERON:0004120"
##   ..$ CL:0000041    : chr [1:2] "CL:0000771" "CL:0002242"
##   ..$ CL:0000042    : chr [1:2] "CL:0000835" "CL:0000834"
##   ..$ CL:0000043    : chr [1:3] "CL:0000767" "CL:0002274" "CL:0002242"
##   ..$ CL:0000047    : chr [1:3] "CL:0000048" "CL:0002319" "UBERON:0001017"
##   ..$ CL:0000048    : chr "CL:0000723"
##   ..$ CL:0000049    : chr [1:2] "UBERON:0004120" "CL:0002032"
##   ..$ CL:0000050    : chr [1:3] "CL:0000839" "CL:0000763" "CL:0002032"
##   ..$ CL:0000051    : chr [1:2] "UBERON:0004120" "CL:0002032"
##   ..$ CL:0000052    : chr "CL:0000723"
##   ..$ CL:0000054    : chr "CL:0000151"
##   ..$ CL:0000055    : chr "CL:0000003"
##   ..$ CL:0000056    : chr "CL:0000680"
##   ..$ CL:0000057    : chr [1:2] "UBERON:0004120" "CL:0002320"
##   ..$ CL:0000058    : chr [1:2] "CL:0000667" "CL:0000055"
##   ..$ CL:0000059    : chr [1:3] "CL:0000151" "CL:0000146" "UBERON:0005176"
##   ..$ CL:0000060    : chr [1:4] "UBERON:0001754" "CL:0000055" "CL:0002159" "UBERON:0005176"
##   ..$ CL:0000061    : chr [1:4] "UBERON:0000078" "CL:0000062" "CL:0000151" "UBERON:0005176"
##   ..$ CL:0000062    : chr [1:4] "UBERON:0010313" "CL:0000055" "CL:0002320" "UBERON:0004120"
##   ..$ CL:0000064    : chr "CL:0000003"
##   ..$ CL:0000065    : chr [1:3] "UBERON:0001016" "CL:0000067" "CL:0000710"
##   ..$ CL:0000066    : chr [1:2] "UBERON:0000483" "CL:0000548"
##   ..$ CL:0000067    : chr [1:2] "CL:0000075" "CL:0000064"
##   ..$ CL:0000068    : chr [1:3] "CL:0000066" "CL:0002371" "UBERON:0000058"
##   ..$ CL:0000069    : chr "CL:0000068"
##   ..$ CL:0000071    : chr [1:3] "CL:0000076" "CL:0002139" "UBERON:0004638"
##   ..$ CL:0000072    : chr [1:2] "CL:0000068" "UBERON:0004120"
##   ..$ CL:0000073    : chr [1:2] "CL:0000066" "CL:0002371"
##   ..$ CL:0000075    : chr [1:2] "CL:0000066" "CL:0002371"
##   ..$ CL:0000076    : chr "CL:0000066"
##   ..$ CL:0000077    : chr [1:3] "CL:0000213" "CL:0000076" "UBERON:0004120"
##   ..$ CL:0000078    : chr [1:2] "CL:0000076" "CL:0002371"
##   ..$ CL:0000079    : chr [1:2] "CL:0000066" "CL:0002371"
##   ..$ CL:0000080    : chr [1:2] "CL:0000003" "UBERON:0000179"
##   .. [list output truncated]
##  $ organ.names        :'data.frame': 12588 obs. of  2 variables:
##   ..$ ID  : chr [1:12588] "AEO:0001009" "AEO:0001010" "AEO:0001013" "CL:0000005" ...
##   ..$ NAME: chr [1:12588] "proliferating neuroepithelium" "differentiating neuroepithelium" "neuronal column" "fibroblast neural crest derived" ...
##  $ bgee.object        :Reference class 'Bgee' [package "BgeeDB"] with 13 fields
##   ..$ species          : chr "Danio_rerio"
##   ..$ speciesName      : chr "Danio_rerio"
##   ..$ speciesId        : num 7955
##   ..$ dataType         : chr [1:4] "rna_seq" "affymetrix" "est" "in_situ"
##   ..$ pathToData       : chr "/Users/jroux/Dropbox/RpackagePaper/Danio_rerio_Bgee_13_2"
##   ..$ release          : chr "13_2"
##   ..$ annotationUrl    : chr(0) 
##   ..$ experimentUrl    : chr(0) 
##   ..$ allExperimentsUrl: chr(0) 
##   ..$ topAnatUrl       : chr "http://r13_2.bgee.org/"
##   ..$ sendStats        : logi TRUE
##   ..$ quantitativeData : logi FALSE
##   ..$ apiKey           : chr "696a8ee5f27f212d71349c131d413fb0de7947e688c95fcdd001689789c7333dbdf6fad8d4d48c239a3e0f4e60a3e74cd5b98398d6a3f93286288211920ddbd"| __truncated__
##   ..and 18 methods, of which 4 are  possibly relevant:
##   ..  format_data, get_annotation, get_data, initialize
library(biomaRt)

# zebrafish data in Ensembl 85 (stable link)
ensembl <- useMart("ENSEMBL_MART_ENSEMBL", 
                   dataset="drerio_gene_ensembl", 
                   host="jul2016.archive.ensembl.org")

# get the mapping of Ensembl genes to phenotypes
genesToPhenotypes <- getBM(filters=c("phenotype_source"), 
                           value=c("ZFIN"),
                           attributes=c("ensembl_gene_id","phenotype_description"),
                           mart=ensembl)

# select phenotypes related to pectoral fin
myPhenotypes = grep("pectoral fin", unique(genesToPhenotypes$phenotype_description), value=T)

# select the genes annotated to select phenotypes
myGenes <- unique(genesToPhenotypes$ensembl_gene_id[genesToPhenotypes$phenotype_description 
                                                    %in% myPhenotypes])

# prepare the gene list vector 
geneList <- factor(as.integer(unique(genesToPhenotypes$ensembl_gene_id) %in% myGenes))
names(geneList) <- unique(genesToPhenotypes$ensembl_gene_id)
summary(geneList)
##    0    1 
## 2986  150
# prepare the topAnat object based on topGO
myTopAnatObject <- topAnat(myTopAnatData, geneList)
## 
## Checking topAnatData object.........
## 
## Checking gene list..................
## 
## WARNING: Some genes in your gene list have no expression data in Bgee, and will not be included in the analysis. 2578 genes in background will be kept.
## 
## Building 'most specific' Terms......  ( 942 Terms found. )
## 
## Build DAG topology..................  ( 1707 terms and 3442 relations. )
## 
## Annotating nodes (Can be long)......  ( 2578 genes annotated to the nodes. )
myTopAnatObject
## 
## ------------------------- topGOdata object -------------------------
## 
##  Description:
##    -   
## 
##  Ontology:
##    -   
## 
##  3136 available genes (all genes from the array):
##    - symbol:  ENSDARG00000063924 ENSDARG00000028663 ENSDARG00000088634 ENSDARG00000063197 ENSDARG00000058996  ...
##    - 150  significant genes. 
## 
##  2578 feasible genes (genes that can be used in the analysis):
##    - symbol:  ENSDARG00000063924 ENSDARG00000028663 ENSDARG00000063197 ENSDARG00000058996 ENSDARG00000051783  ...
##    - 128  significant genes. 
## 
##  GO graph (nodes with at least  10  genes):
##    - a graph with directed edges
##    - number of nodes = 891 
##    - number of edges = 1798 
## 
## ------------------------- topGOdata object -------------------------
results <- runTest(myTopAnatObject, algorithm='weight', statistic='fisher')
## 
##           -- Weight Algorithm -- 
## 
##       The algorithm is scoring 819 nontrivial nodes
##       parameters: 
##           test statistic: fisher : ratio
## 
##   Level 28:  1 nodes to be scored.
## 
##   Level 27:  1 nodes to be scored.
## 
##   Level 26:  2 nodes to be scored.
## 
##   Level 25:  3 nodes to be scored.
## 
##   Level 24:  3 nodes to be scored.
## 
##   Level 23:  2 nodes to be scored.
## 
##   Level 22:  10 nodes to be scored.
## 
##   Level 21:  20 nodes to be scored.
## 
##   Level 20:  19 nodes to be scored.
## 
##   Level 19:  35 nodes to be scored.
## 
##   Level 18:  34 nodes to be scored.
## 
##   Level 17:  53 nodes to be scored.
## 
##   Level 16:  76 nodes to be scored.
## 
##   Level 15:  87 nodes to be scored.
## 
##   Level 14:  71 nodes to be scored.
## 
##   Level 13:  80 nodes to be scored.
## 
##   Level 12:  92 nodes to be scored.
## 
##   Level 11:  74 nodes to be scored.
## 
##   Level 10:  56 nodes to be scored.
## 
##   Level 9:   34 nodes to be scored.
## 
##   Level 8:   19 nodes to be scored.
## 
##   Level 7:   11 nodes to be scored.
## 
##   Level 6:   9 nodes to be scored.
## 
##   Level 5:   15 nodes to be scored.
## 
##   Level 4:   3 nodes to be scored.
## 
##   Level 3:   6 nodes to be scored.
## 
##   Level 2:   2 nodes to be scored.
## 
##   Level 1:   1 nodes to be scored.
results
## 
## Description:  
## Ontology:  
## 'weight' algorithm with the 'fisher : ratio' test
## 891 GO terms scored: 53 terms with p < 0.01
## Annotation data:
##     Annotated genes: 2578 
##     Significant genes: 128 
##     Min. no. of genes annotated to a GO: 10 
##     Nontrivial nodes: 819
# retrieve anatomical structures enriched at a 1% FDR threshold, sorted by decreasing fold enrichment
tableOver <- makeTable(myTopAnatData, myTopAnatObject, results, cutoff=0.01)
## 
## Building the results table for the 22 significant terms at FDR threshold of 0.01...
## Ordering results by pValue column in increasing order...
## Done
head(tableOver)
##                       organId                           organName
## UBERON:0004357 UBERON:0004357                 paired limb/fin bud
## UBERON:0000151 UBERON:0000151                        pectoral fin
## UBERON:2000040 UBERON:2000040                     median fin fold
## UBERON:0003051 UBERON:0003051                         ear vesicle
## UBERON:0005729 UBERON:0005729            pectoral appendage field
## UBERON:0007390 UBERON:0007390 pectoral appendage cartilage tissue
##                annotated significant expected foldEnrichment       pValue
## UBERON:0004357       144          41     7.15       5.734266 1.622480e-22
## UBERON:0000151       420          70    20.85       3.357314 1.037552e-18
## UBERON:2000040        51          18     2.53       7.114625 7.171001e-12
## UBERON:0003051       304          41    15.09       2.717031 3.135769e-10
## UBERON:0005729        16          10     0.79      12.658228 4.004917e-10
## UBERON:0007390        17           9     0.84      10.714286 2.411891e-08
##                         FDR
## UBERON:0004357 1.445630e-19
## UBERON:0000151 4.622296e-16
## UBERON:2000040 2.129787e-09
## UBERON:0003051 6.984926e-08
## UBERON:0005729 7.136762e-08
## UBERON:0007390 3.581659e-06
sessionInfo()
## R version 3.3.1 (2016-06-21)
## Platform: x86_64-apple-darwin13.4.0 (64-bit)
## Running under: OS X 10.12.1 (Sierra)
## 
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## attached base packages:
##  [1] tcltk     stats4    parallel  stats     graphics  grDevices utils    
##  [8] datasets  methods   base     
## 
## other attached packages:
##  [1] biomaRt_2.30.0       edgeR_3.16.1         limma_3.30.0        
##  [4] Mfuzz_2.34.0         DynDoc_1.52.0        widgetTools_1.52.0  
##  [7] e1071_1.6-7          BgeeDB_2.0.0         tidyr_0.6.0         
## [10] topGO_2.26.0         SparseM_1.72         GO.db_3.4.0         
## [13] AnnotationDbi_1.36.0 IRanges_2.8.0        S4Vectors_0.12.0    
## [16] Biobase_2.34.0       graph_1.52.0         BiocGenerics_0.20.0 
## [19] BiocInstaller_1.24.0
## 
## loaded via a namespace (and not attached):
##  [1] Rcpp_0.12.7        formatR_1.4        tkWidgets_1.52.0  
##  [4] bitops_1.0-6       class_7.3-14       tools_3.3.1       
##  [7] digest_0.6.10      RSQLite_1.0.0      evaluate_0.10     
## [10] tibble_1.2         lattice_0.20-34    DBI_0.5-1         
## [13] yaml_2.1.13        stringr_1.1.0      dplyr_0.5.0       
## [16] knitr_1.14         locfit_1.5-9.1     grid_3.3.1        
## [19] data.table_1.9.6   R6_2.2.0           XML_3.98-1.4      
## [22] rmarkdown_1.1      magrittr_1.5       htmltools_0.3.5   
## [25] matrixStats_0.51.0 assertthat_0.1     stringi_1.1.2     
## [28] RCurl_1.95-4.8     chron_2.3-47