[1] "libdir: /xchip/tcga/gdac_prod/applications/process_mgmt/firehose_task_registry/tcga-gdac/ClinicalAnalysisAllGenes_new/broadinstitute.org/cancer.genome.analysis/00333/69/"
[1] "op: MUTATION_RATE"
[1] "dfn: /xchip/cga/gdac-prod/tcga-gdac/jobResults/MutSigRun/HNSC-TP/15638854/HNSC-TP.patients.counts_and_rates.txt"
[1] "cfn: /xchip/cga/gdac-prod/tcga-gdac/jobResults/Append_Data/HNSC-TP/15078978/HNSC-TP.merged_data.txt"
[1] "gv: ALL"
[1] "gfn: "
[1] "sfn: "
[1] "fv: ALL"
[1] "ofn: "
[1] "dx: "
[1] "cfn"
[1] "/xchip/cga/gdac-prod/tcga-gdac/jobResults/Append_Data/HNSC-TP/15078978/HNSC-TP.merged_data.txt"
[1] "ok3"

nSamples in clinical file=522, in expression file=510, common to both=506
Number of genes in original expression dataset=2
[1] "ALL"
[1] "data2feature, selection=ALL"
 [1] "YEARS_TO_BIRTH"                        
 [2] "VITAL_STATUS"                          
 [3] "DAYS_TO_DEATH"                         
 [4] "DAYS_TO_LAST_FOLLOWUP"                 
 [5] "PRIMARY_SITE_OF_DISEASE"               
 [6] "NEOPLASM_DISEASESTAGE"                 
 [7] "PATHOLOGY_T_STAGE"                     
 [8] "PATHOLOGY_N_STAGE"                     
 [9] "PATHOLOGY_M_STAGE"                     
[10] "DCC_UPLOAD_DATE"                       
[11] "GENDER"                                
[12] "DATE_OF_INITIAL_PATHOLOGIC_DIAGNOSIS"  
[13] "DAYS_TO_LAST_KNOWN_ALIVE"              
[14] "RADIATION_THERAPY"                     
[15] "HISTOLOGICAL_TYPE"                     
[16] "RADIATIONS_RADIATION_REGIMENINDICATION"
[17] "NUMBER_PACK_YEARS_SMOKED"              
[18] "YEAR_OF_TOBACCO_SMOKING_ONSET"         
[19] "NUMBER_OF_LYMPH_NODES"                 
[20] "RACE"                                  
[21] "ETHNICITY"                             
[22] "BATCH_NUMBER"                          

Input Data has 22 rows and 506 columns.

[1] "Batch" "22"   
[1] "Last Follow UP"
Variable 1:'YEARS_TO_BIRTH':	nDistinctValues=60,	numeric=TRUE,	binary=FALSE,	exclude=FALSE.
Variable 2:'VITAL_STATUS':	nDistinctValues=2,	numeric=TRUE,	binary=TRUE,	exclude=FALSE.
Variable 3:'DAYS_TO_DEATH':	nDistinctValues=186,	numeric=TRUE,	binary=FALSE,	exclude=TRUE.
[1] "exclude grep('DAYS_?TO', vnms) to deal with survival parameters seperately"
Variable 4:'DAYS_TO_LAST_FOLLOWUP':	nDistinctValues=322,	numeric=TRUE,	binary=FALSE,	exclude=TRUE.
[1] "exclude grep('FOLLOWUP', vnms) to deal with survival parameters seperately"
Variable 5:'PRIMARY_SITE_OF_DISEASE':	nDistinctValues=1,	numeric=FALSE,	binary=FALSE,	exclude=TRUE.
[1] "PRIMARY_SITE_OF_DISEASE is excluded in the analysis because there is no more than two cases of (unique non-NA values)"
Variable 6:'NEOPLASM_DISEASESTAGE':	nDistinctValues=5,	numeric=FALSE,	binary=FALSE,	exclude=FALSE.
Variable 7:'PATHOLOGY_T_STAGE':	nDistinctValues=8,	numeric=FALSE,	binary=FALSE,	exclude=FALSE.
Variable 8:'PATHOLOGY_N_STAGE':	nDistinctValues=8,	numeric=FALSE,	binary=FALSE,	exclude=FALSE.
Variable 9:'PATHOLOGY_M_STAGE':	nDistinctValues=2,	numeric=FALSE,	binary=FALSE,	exclude=FALSE.
Variable 10:'DCC_UPLOAD_DATE':	nDistinctValues=5,	numeric=FALSE,	binary=FALSE,	exclude=TRUE.
[1] "exclude grep('DATE', vnms) to deal with survival parameters seperately"
Variable 11:'GENDER':	nDistinctValues=2,	numeric=FALSE,	binary=FALSE,	exclude=FALSE.
Variable 12:'DATE_OF_INITIAL_PATHOLOGIC_DIAGNOSIS':	nDistinctValues=22,	numeric=TRUE,	binary=FALSE,	exclude=TRUE.
[1] "exclude grep('DATE', vnms) to deal with survival parameters seperately"
Variable 13:'DAYS_TO_LAST_KNOWN_ALIVE':	nDistinctValues=44,	numeric=TRUE,	binary=FALSE,	exclude=TRUE.
[1] "exclude grep('DAYS_?TO', vnms) to deal with survival parameters seperately"
Variable 14:'RADIATION_THERAPY':	nDistinctValues=1,	numeric=FALSE,	binary=FALSE,	exclude=TRUE.
[1] "RADIATION_THERAPY is excluded in the analysis because there is no more than two cases of (unique non-NA values)"
Variable 15:'HISTOLOGICAL_TYPE':	nDistinctValues=3,	numeric=FALSE,	binary=FALSE,	exclude=FALSE.
Variable 16:'RADIATIONS_RADIATION_REGIMENINDICATION':	nDistinctValues=2,	numeric=FALSE,	binary=FALSE,	exclude=FALSE.
Variable 17:'NUMBER_PACK_YEARS_SMOKED':	nDistinctValues=86,	numeric=TRUE,	binary=FALSE,	exclude=FALSE.
Variable 18:'YEAR_OF_TOBACCO_SMOKING_ONSET':	nDistinctValues=58,	numeric=TRUE,	binary=FALSE,	exclude=FALSE.
Variable 19:'NUMBER_OF_LYMPH_NODES':	nDistinctValues=23,	numeric=TRUE,	binary=FALSE,	exclude=FALSE.
Variable 20:'RACE':	nDistinctValues=4,	numeric=FALSE,	binary=FALSE,	exclude=FALSE.
Variable 21:'ETHNICITY':	nDistinctValues=2,	numeric=FALSE,	binary=FALSE,	exclude=FALSE.
Variable 22:'BATCH_NUMBER':	nDistinctValues=25,	numeric=FALSE,	binary=FALSE,	exclude=TRUE.
[1] NA
[1] "## **** detect survival parameters (defined in index such as ind_OS, ind_MFS, ind_RFS, ind_RFS, ind_BCR and ind_d2ssd) *** ##"
[1] "detected survival parameters using [ind_OS, overall_survival]"
[1] "survival parameters accumulated so far"
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "detected survival parameters using [ind_OS, curated_overall_survival]"
[1] "survival parameters accumulated so far"
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "detected survival parameters using [ind_TCGAOS]"
[1] "survival parameters accumulated so far"
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "detected survivial parameters using [ind_MFS]"
[1] "survival parameters accumulated so far"
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "detected survival parameters using [ind_RFS]"
[1] "survival parameters accumulated so far"
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "detected survival parameters using [ind_BCR]"
[1] "survival parameters accumulated so far"
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "detected survival parameters using [ind_Progression]"
[1] "survival parameters accumulated so far"
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "detected survival parameters using [index_additional_survival_time]"
[1] "survival parameters accumulated so far"
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "detected survival parameters using condition: [is.null(surv.mat)&&(selection=='SURV')]"
[1] "survival parameters accumulated so far"
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "************ conversion from categorical data to rank data ********** "
[1] "PATHOLOGY_T_STAGE is converted to numeric rank data using modified categoies"
[1] "PATHOLOGY_N_STAGE is converted to numeric rank data using modified categoies"
[1] "PATHOLOGY_M_STAGE is converted to rank data using modified categoies"
[1] "****** SUMMARY ***** "
Output Data has 506 columns, 1 survival variables, and 12 non-survival variables.
[1] "* survival variables: "
[1] "DAYS_TO_DEATH_OR_LAST_FUP" "VITAL_STATUS"             
[1] "* non-survival variables: "
 [1] "YEARS_TO_BIRTH"                        
 [2] "NEOPLASM_DISEASESTAGE"                 
 [3] "PATHOLOGY_T_STAGE"                     
 [4] "PATHOLOGY_N_STAGE"                     
 [5] "GENDER"                                
 [6] "HISTOLOGICAL_TYPE"                     
 [7] "RADIATIONS_RADIATION_REGIMENINDICATION"
 [8] "NUMBER_PACK_YEARS_SMOKED"              
 [9] "YEAR_OF_TOBACCO_SMOKING_ONSET"         
[10] "NUMBER_OF_LYMPH_NODES"                 
[11] "RACE"                                  
[12] "ETHNICITY"                             
[1] "changed to 13 non-survival variables adding another age variable for linear regression analysis on mutaion rate."
[1] "DAYS_TO_DEATH_OR_LAST_FUP"
[1] "DAYS_TO_DEATH_OR_LAST_FUP"
[1] "D"                         "DAYS_TO_DEATH_OR_LAST_FUP"
[3] "Month"                    
[1] "check if there is any case_to_report in survival time data or not"
[1] "alarming case(s) exist!"
[1] "[  1  ] case_to_report(s) is(are) excluded in survival analysis"
AGE, nv=60, binary=FALSE, numeric=TRUE
AGE_mutation.rate, nv=60, binary=FALSE, numeric=TRUE
$MUTATIONRATE_NONSYNONYMOUS

Call:
lm(formula = as.numeric(i) ~ vv)

Residuals:
       Min         1Q     Median         3Q        Max 
-4.503e-06 -2.479e-06 -1.444e-06  1.270e-07  8.949e-05 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)  
(Intercept) 1.478e-06  1.449e-06   1.020    0.308  
vv          5.201e-08  2.330e-08   2.232    0.026 *
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 

Residual standard error: 6.299e-06 on 504 degrees of freedom
Multiple R-squared: 0.009789,	Adjusted R-squared: 0.007824 
F-statistic: 4.983 on 1 and 504 DF,  p-value: 0.02604 


$MUTATIONRATE_SILENT

Call:
lm(formula = as.numeric(i) ~ vv)

Residuals:
       Min         1Q     Median         3Q        Max 
-1.514e-06 -8.598e-07 -5.370e-07  9.450e-08  3.058e-05 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)  
(Intercept) 5.837e-07  5.586e-07   1.045   0.2966  
vv          1.562e-08  8.985e-09   1.739   0.0827 .
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 

Residual standard error: 2.429e-06 on 504 degrees of freedom
Multiple R-squared: 0.005963,	Adjusted R-squared: 0.00399 
F-statistic: 3.023 on 1 and 504 DF,  p-value: 0.08269 


NEOPLASM_DISEASESTAGE, nv=5, binary=FALSE, numeric=FALSE
PATHOLOGY_T_STAGE, nv=5, binary=FALSE, numeric=TRUE
[1] "PATHOLOGY_T_STAGE"
[1] "num to class table"
vv1
 T0  T1  T2  T3  T4 
  1  47 131  98 168 
PATHOLOGY_N_STAGE, nv=4, binary=FALSE, numeric=TRUE
[1] "PATHOLOGY_N_STAGE"
[1] "num to class table"
vv1
 N0  N1  N2  N3 
174  65 161   7 
GENDER, nv=2, binary=FALSE, numeric=FALSE
HISTOLOGICAL_TYPE, nv=3, binary=FALSE, numeric=FALSE
RADIATIONS_RADIATION_REGIMENINDICATION, nv=2, binary=FALSE, numeric=FALSE
NUMBER_PACK_YEARS_SMOKED, nv=86, binary=FALSE, numeric=TRUE
YEAR_OF_TOBACCO_SMOKING_ONSET, nv=58, binary=FALSE, numeric=TRUE
NUMBER_OF_LYMPH_NODES, nv=23, binary=FALSE, numeric=TRUE
RACE, nv=4, binary=FALSE, numeric=FALSE
ETHNICITY, nv=2, binary=FALSE, numeric=FALSE
[1] "saved param, results, example.expr in analysis.result.Rdata "
