Skip to content

Latest commit

 

History

History
46 lines (40 loc) · 6.54 KB

exonarray_instruction.md

File metadata and controls

46 lines (40 loc) · 6.54 KB

Convert CEL file format

The format of CEL files may need to be converted first using apt-cel-convert from Affymetrix Power Tools (APT) which can be obtained from http://www.affymetrix.com/estore/partners_programs/programs/developer/tools/powertools.affx#1_2

apt-cel-convert --format xda --cel-files input_file_list.txt -i

Example of input_file_list.txt

cel_files
input_exon_array.CEL

Run GeneBASE

The training exon array data of BIRD is recommended to be combined with the input exon array data, which can be obtained from http://jilab.biostat.jhsph.edu/software/BIRD/Exon_panel/BIRD_57_exon_data.zip

The required library files can be obtained from http://www.affymetrix.com/support/technical/byproduct.affx?product=huexon-st

To run GeneBASE:

ProbeEffects -par PAR_file.txt

Example of PAR_file.txt (Note that flags and parameter values are separated by tabs)

[log]
logfile Log_file.txt

[exon_annotation]
probeset_annotation	HuEx-1_0-st-v2.na33.1.hg19.probeset.csv
pgf_file	HuEx-1_0-st-v2.r2.pgf
clf_file	HuEx-1_0-st-v2.r2.clf
num_cells	6553600
cell_dim	2560

[exon_data]
folder	/CEL_file_directory/
exon_cel_files	input_exon_array.CEL,GSM510528_X_Hs_AG04449_E_091118_01_DS12319_W.CEL,GSM510530_X_Hs_AG04449_E_091208_05_DS12329_W.CEL,GSM510532_X_Hs_AG04450_E_091208_02_DS12270_W.CEL,GSM510534_X_Hs_AG04450_E_091208_01_DS12255_W.CEL,GSM510522_X_Hs_AG09309_E_091118_02_DS12352_W.CEL,GSM510525_X_Hs_AG09309_E_091211_01_DS12357_W.CEL,GSM510536_X_Hs_AG09319_E_091208_04_DS12291_W.CEL,GSM510538_X_Hs_AG09319_E_091208_03_DS12286_W.CEL,GSM510520_X_Hs_AG10803_E_091208_06_DS12384_W.CEL,GSM510521_X_Hs_AG10803_E_091118_03_DS12374_W.CEL,GSM580029_X_Hs_AoAF_E_100603_31_DS13523_W_3.CEL,GSM580030_X_Hs_AoAF_E_100603_30_DS13513_W_3.CEL,GSM472898_X_Hs_BJ_E_080131_04_DS7708_D.CEL,GSM472924_X_Hs_BJ_E_090716_03_DS11522_W.CEL,GSM472925_X_Hs_BJ_E_090716_04_DS11523_W.CEL,GSM472901_X_Hs_GM12878_E_080325_04_DS8623_W.CEL,GSM472902_X_Hs_GM12878_E_080325_05_DS8626_W.CEL,GSM472931_X_Hs_GM12878_E_090723_04_DS11526_W.CEL,GSM580005_X_Hs_hESCT0_E_100603_09_DS13133_W.CEL,GSM510581_X_Hs_hESCT0_E_091028_02_DS11909_W.CEL,GSM1033350_hg19_wgEncodeUwAffyExonArrayH7esDiffa14dRawDataRep2.CEL,GSM1033351_hg19_wgEncodeUwAffyExonArrayH7esDiffa14dRawDataRep1.CEL,GSM651569_X_Hs_HAc_E_101115_03_RS17239_W.CEL,GSM651570_X_Hs_HAc_E_101115_04_RS17240_W.CEL,GSM510516_X_Hs_HAEpiC_E_091211_05_DS12663_W.CEL,GSM510517_X_Hs_HAEpiC_E_091211_06_DS12673_W.CEL,GSM824862_X_Hs_HAh_E_101230_01_RS17565_W.CEL,GSM824863_X_Hs_HAh_E_101230_02_RS17566_W.CEL,GSM651562_X_Hs_HAsp_E_100901_09_RS16425_W.CEL,GSM651563_X_Hs_HAsp_E_100901_10_RS16426_W.CEL,GSM580045_X_Hs_HBMEC_E_100603_40_DS13817_W_3.CEL,GSM651564_X_Hs_HBMEC_E_100901_11_RS16427_W.CEL,GSM824859_X_Hs_HBVP_E_110517_01_RS18997_W.CEL,GSM824849_X_Hs_HBVSMC_E_110517_02_RS18998_W_3.CEL,GSM824850_X_Hs_HBVSMC_E_110517_03_RS18999_W.CEL,GSM510542_X_Hs_HCF_E_091208_10_DS12501_W.CEL,GSM510545_X_Hs_HCF_E_091208_09_DS12491_W.CEL,GSM580031_X_Hs_HCFaa_E_100603_28_DS13480_W.CEL,GSM580032_X_Hs_HCFaa_E_100603_29_DS13484_W_3.CEL,GSM510566_X_Hs_HCM_E_091214_05_DS12599_W.CEL,GSM510569_X_Hs_HCM_E_091214_04_DS12592_W.CEL,GSM580007_X_Hs_HConF_E_100603_02_DS11642_W.CEL,GSM580008_X_Hs_HConF_E_100603_01_DS11637_W.CEL,GSM510547_X_Hs_HCPEpiC_E_091118_08_DS12447_W.CEL,GSM510551_X_Hs_HCPEpiC_E_091208_07_DS12457_W.CEL,GSM510571_X_Hs_HEEpiC_E_091214_09_DS12768_W.CEL,GSM510574_X_Hs_HEEpiC_E_091214_08_DS12763_W.CEL,GSM824864_X_Hs_HFF_E_101230_03_RS17567_W.CEL,GSM824865_X_Hs_HFF_E_101230_04_RS17568_W.CEL,GSM472940_X_Hs_HGF_E_091007_04_DS11738_W.CEL,GSM472941_X_Hs_HGF_E_091007_05_DS11752_W.CEL,GSM510518_X_Hs_HIPEpiC_E_091211_07_DS12694_W.CEL,GSM510519_X_Hs_HIPEpiC_E_091214_07_DS12699_W.CEL,GSM472909_X_Hs_HMEC_E_080325_06_DS8683_W.CEL,GSM472934_X_Hs_HMEC_E_090904_01_DS8680_W.CEL,GSM580006_X_Hs_HMEC_E_100603_43_DS13921_W_3.CEL,GSM580041_X_Hs_HMF_E_100603_20_DS13363_W_2.CEL,GSM580042_X_Hs_HMF_E_100603_21_DS13368_W_2.CEL,GSM824851_X_Hs_HMVECdAd_E_110517_04_RS19000_W.CEL,GSM824852_X_Hs_HMVECdAd_E_110517_05_RS19001_W.CEL,GSM580021_X_Hs_HMVECdBlAd_E_100603_19_DS13337_W_2.CEL,GSM580022_X_Hs_HMVECdBlAd_E_100603_18_DS13329_W.CEL,GSM580013_X_Hs_HMVECdLyAd_E_100603_16_DS13256_W_3.CEL,GSM580014_X_Hs_HMVECdLyAd_E_100603_17_DS13261_W.CEL,GSM510560_X_Hs_HNPCEpiC_E_091208_08_DS12467_W.CEL,GSM510564_X_Hs_HNPCEpiC_E_091211_02_DS12471_W.CEL,GSM824860_X_Hs_HPAEC_E_110517_06_RS19002_W.CEL,GSM580033_X_Hs_HPAF_E_100603_26_DS13411_W.CEL,GSM580034_X_Hs_HPAF_E_100603_27_DS13416_W.CEL,GSM580025_X_Hs_HPdLF_E_100603_35_DS13573_W_3.CEL,GSM580026_X_Hs_HPdLF_E_100603_34_DS13569_W_3.CEL,GSM580035_X_Hs_HPF_E_100603_25_DS13390_W.CEL,GSM580036_X_Hs_HPF_E_100603_24_DS13380_W.CEL,GSM472920_X_Hs_HRCE_E_090616_05_DS10662_W.CEL,GSM472921_X_Hs_HRCE_E_090616_06_DS10666_W.CEL,GSM472918_X_Hs_HRE_E_090616_03_DS10631_W.CEL,GSM472919_X_Hs_HRE_E_090616_04_DS10641_W.CEL,GSM651572_X_Hs_HRGEC_E_101115_06_RS17242_W.CEL,GSM651573_X_Hs_HRGEC_E_101115_07_RS17243_W.CEL,GSM510514_X_Hs_HRPEpiC_E_091208_11_DS12583_W.CEL,GSM510515_X_Hs_HRPEpiC_E_091211_03_DS12568_W.CEL,GSM651574_X_Hs_HSMM_E_101115_08_RS17244_W.CEL,GSM651575_X_Hs_HSMM_E_101115_09_RS17245_W.CEL,GSM651576_X_Hs_HSMM_E_101115_10_RS17246_W.CEL,GSM824861_X_Hs_HSMM_E_101230_08_RS17572_W.CEL,GSM472935_X_Hs_HUVEC_E_090904_05_DS10060_W.CEL,GSM651577_X_Hs_HUVEC_E_101115_11_RS17247_W.CEL,GSM580037_X_Hs_HVMF_E_100603_42_DS13981_W_3.CEL,GSM580038_X_Hs_HVMF_E_100603_41_DS13977_W_3.CEL,GSM824871_X_Hs_CD14_E_110216_06_RS17943_W_2.CEL,GSM580043_X_Hs_NHA_E_100603_03_DS12800_W.CEL,GSM580044_X_Hs_NHA_E_100603_04_DS12805_W.CEL,GSM824853_X_Hs_NHBE_E_110517_07_RS19003_W.CEL,GSM824854_X_Hs_NHBE_E_110517_08_RS19004_W_3.CEL,GSM580017_X_Hs_NHDFAd_E_100603_06_DS12863_W.CEL,GSM580018_X_Hs_NHDFAd_E_100603_05_DS12855_W.CEL,GSM472937_X_Hs_NHEK_E_090904_06_DS11474_W.CEL,GSM510577_X_Hs_NHLF_E_091214_11_DS12834_W.CEL,GSM510579_X_Hs_NHLF_E_091214_10_DS12829_W.CEL,GSM824857_X_Hs_PrEC_E_110517_11_RS19007_W.CEL,GSM824858_X_Hs_PrEC_E_110517_12_RS19008_W.CEL,GSM651565_X_Hs_RPTEC_E_100901_12_RS16428_W.CEL,GSM651566_X_Hs_RPTEC_E_100901_13_RS16429_W.CEL,GSM472922_X_Hs_SAEC_E_090716_01_DS10514_W.CEL,GSM472923_X_Hs_SAEC_E_090716_02_DS10518_W.CEL,GSM472911_X_Hs_SKMC_E_080131_01_DS7911_D.CEL,GSM472943_X_Hs_SKMC_E_091007_06_DS11939_W.CEL,GSM510509_X_Hs_SKMC_E_091028_05_DS11949_W.CEL,GSM472914_X_Hs_tH1_E_080131_05_DS7840_D.CEL,GSM472915_X_Hs_tH2_E_080131_06_DS7842_D.CEL,GSM651580_X_Hs_WI38_E_101115_14_RS17250_W.CEL,GSM651581_X_Hs_WI38_E_101115_15_RS17251_W.CEL

[output]
output_model_fit	output_file.txt

[model]
array_type	exon
method	mat
summarize_expression	true
summary_method	selection
mat_training_probe_type	background
normalization_method	quantile