| Abbreviations | |
| ---- | |
| v value | |
| exp experiment | |
| c contrast | |
| id identifier | |
| as analytics search, which the query either matches or it doesn't | |
| cs conditions search, which the query either matches or it doesn't | |
| Sets considered |
| echo "Clear previous Ensembl data from the public all subdirs of ${ATLAS_FTP}/bioentity_properties" | |
| for dir in ensembl mirbase reactome go interpro wbps; do | |
| rm -rf ${ATLAS_FTP}/bioentity_properties/${dir}/* | |
| done | |
| echo "Copy all array design mapping files into the public Ensembl data directory (this directory is used only for Solr index build)" | |
| cp ${ATLAS_PROD}/bioentity_properties/ensembl/*.A-*.tsv ${ATLAS_FTP}/bioentity_properties/ensembl/ | |
| pushd ${ATLAS_PROD}/bioentity_properties/ensembl | |
| echo "Copy all Ensembl matrices to the public Ensembl data directory" |
| #!/bin/bash | |
| # Look at the header of the file, splay it into lines, then use grep -n to find out the position it's in | |
| head -n1 $ATLAS_FTP/bioentity_properties/ensembl/mus_musculus.ensgene.tsv | tr '\t' '\n' | grep -n mgi_id | cut -f 1 -d : | |
| #16 | |
| head -n1 $ATLAS_PROD/bioentity_properties/ensembl/mus_musculus.ensgene.tsv | tr '\t' '\n' | grep -n mgi_id | cut -f 1 -d : | |
| #16 |
| [fg_atlas@ebi-005 ~]$ ls $ATLAS_EXPS | grep 'E-.*' | tee /var/tmp/atlas-exps-exps | wc -l | |
| 3165 | |
| [fg_atlas@ebi-005 ~]$ ls $ATLAS_PROD/analysis/*/*/experiments | grep 'E-.*' | tee /var/tmp/atlas-prod-exps | wc -l | |
| 3244 | |
| [fg_atlas@ebi-005 ~]$ sort /var/tmp/atlas-prod-exps -o /var/tmp/atlas-prod-exps | |
| [fg_atlas@ebi-005 ~]$ sort /var/tmp/atlas-exps-exps -o /var/tmp/atlas-exps-exps | |
| # experiments in atlas exps but not in atlas prod | |
| [fg_atlas@ebi-005 ~]$ comm -13 /var/tmp/atlas-prod-exps /var/tmp/atlas-exps-exps | |
| E-GEOD-53580 | |
| E-GEOD-73312 |
| [fg_atlas@ebi-005 E-ATMX-20]$ for exp in $(comm -13 <( ls $ATLAS_EXPS | grep 'E-.*' | sort ) <( ls $ATLAS_FTP/experiments | grep 'E-.*' | sort )) ; do find $ATLAS_FTP/experiments/$exp -name '*-analytics.tsv' ; done | xargs ls -ld | |
| -rw-r--r-- 1 fg_atlas microarray 5561657 Mar 2 2014 /ebi/ftp/pub/databases/microarray/data/atlas/experiments/E-GEOD-10041/E-GEOD-10041_A-AFFY-44-analytics.tsv | |
| -rw-r--r-- 1 fg_atlas microarray 1062342 Feb 19 2014 /ebi/ftp/pub/databases/microarray/data/atlas/experiments/E-GEOD-12332/E-GEOD-12332_A-AFFY-17-analytics.tsv | |
| -rw-r--r-- 1 fg_atlas microarray 7589235 Apr 22 2014 /ebi/ftp/pub/databases/microarray/data/atlas/experiments/E-GEOD-12667/E-GEOD-12667_A-AFFY-44-analytics.tsv | |
| -rw-r--r-- 1 fg_atlas microarray 3393121 Mar 2 2014 /ebi/ftp/pub/databases/microarray/data/atlas/experiments/E-GEOD-12767/E-GEOD-12767_A-AFFY-44-analytics.tsv | |
| -rw-r--r-- 1 fg_atlas microarray 1330410 Mar 14 2016 /ebi/ftp/pub/databases/microarray/data/atlas/experiments/E-GEOD-14895/E-GEOD-14895_A-AFFY-33-ana |
| [fg_atlas@ebi-005 archive]$ mkdir /var/tmp/array-designs | |
| [fg_atlas@ebi-005 archive]$ cp ensembl_87_34/homo_sapiens*A-*.tsv /var/tmp/array-designs | |
| [fg_atlas@ebi-005 archive]$ cd /var/tmp/array-designs | |
| [fg_atlas@ebi-005 array-designs]$ for file in `ls ` ; do cat <(echo -e "ensgene\tdesign_element") <(grep -E "\w+\W\w+" $file) > $file.tmp ; mv $file.tmp $file ; done | |
| [fg_atlas@ebi-005 array-designs]$ wc -l * | |
| 8684 homo_sapiens.A-AFFY-10.tsv | |
| 6938 homo_sapiens.A-AFFY-11.tsv | |
| 5155 homo_sapiens.A-AFFY-12.tsv | |
| 6835 homo_sapiens.A-AFFY-13.tsv | |
| 25196 homo_sapiens.A-AFFY-141.tsv |
| --- Analytics index build started Tue Jan 31 10:01:04 GMT 2017 --- | |
| Experiments to index: [E-MTAB-2770, E-MTAB-2706, E-MTAB-4840, E-GEOD-48433, E-GEOD-26284, E-MTAB-4342, E-GEOD-18858, E-MTAB-2512, E-MTAB-3579, E-MTAB-4404, E-MTAB-5214, E-MTAB-2919, E-MTAB-76, E-GEOD-53960, E-GEOD-36272, E-MTAB-4045, E-MTAB-1354, E-GEOD-16837, E-GEOD-49284, E-MTAB-4395, E-MTAB-4484, E-MTAB-4222, E-MTAB-3838, E-MTAB-2836, E-MTAB-1729, E-MTAB-3358, E-MTAB-3827, E-GEOD-60424, E-GEOD-53197, E-GEOD-18344, E-MTAB-5140, E-TABM-234, E-MTAB-4270, E-MTAB-1027, E-GEOD-66354, E-GEOD-16879, E-ERAD-401, E-GEOD-18791, E-TABM-142, E-MTAB-4444, E-MTAB-3871, E-GEOD-3307, E-MTAB-2801, E-MTAB-2812, E-GEOD-41678, E-MTAB-2137, E-GEOD-30495, E-GEOD-62673, E-GEOD-15129, E-GEOD-33643, E-GEOD-38351, E-GEOD-63252, E-GEOD-25250, E-MTAB-513, E-GEOD-16992, E-GEOD-63362, E-GEOD-45757, E-JJRD-1, E-GEOD-37940, E-GEOD-38023, E-TABM-1216, E-TABM-1205, E-MTAB-4260, E-TABM-82, E-GEOD-58603, E-MTAB-4289, E-GEOD-49050, E-GEOD-40844, E-MTAB-4308, E-GEOD-13637, E-GE |
| Gene ID Gene Name g1_g2.p-value g1_g2.log2foldchange g1_g3.p-value g1_g3.log2foldchange g1_g4.p-value g1_g4.log2foldchange g5_g6.p-value g5_g6.log2foldchange g5_g7.p-value g5_g7.log2foldchange g5_g8.p-value g5_g8.log2foldchange | |
| ENSG00000000003 TSPAN6 0.00455588947600315 -0.2 1.47389153905488e-05 0.3 5.25735911012297e-74 1.1 0.137744420192993 -0.2 0.0192978221738748 -0.2 1.69287277016467e-07 0.6 | |
| ENSG00000000005 TNMD NA 0 NA 0.2 NA 0.3 NA 0 NA -0.1 NA 0 | |
| ENSG00000124635 HIST1H2BJ 2.062881127556e-210 -1.2 0 -1.5 0 -2.6 2.46220174669173e-223 -1.5 0 -1.5 0 -2.7 |
| cd ~/dev/atlas-annotations | |
| # modify the annsrcs to be (much) smaller | |
| # test environment | |
| source util/create_test_env.sh /var/tmp/will-it-go | |
| # use the whole file from prod | |
| scp ebi-cli:/nfs/production3/ma/home/atlas3-production/bioentity_properties/go/go.alternativeID2CanonicalID.tsv /var/tmp/will-it-go/bioentity_properties/go/go.alternativeID2CanonicalID.tsv | |
| # get some properties populated in test environment | |
| export JAVA_OPTS=-Xmx3000M |