R version 4.5.0 RC (2025-04-04 r88113 ucrt) -- "How About a Twenty-Six"
Copyright (C) 2025 The R Foundation for Statistical Computing
Platform: x86_64-w64-mingw32/x64

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(plasma)
> # Repeat basic stuff from first test
> fls <- try(loadESCAdata())
> if (inherits(fls, "try-error")) {
+   stop("Unable to load data from remote server.")
+ }
> ls()
[1] "fls"
> MO <- with(plasmaEnv, prepareMultiOmics(assemble, Outcome))
> train <- rep(c(TRUE, FALSE), times = c(112, 185-112))
> MO2 <- MO[, train]
> ## Fit a survival model on a single data set on the MultiOmics object
> fitted <- fitSingleModel(MO2, "ClinicalBin", "Days", "vital_status", "dead")
____************************************************____
____There are some NAs in X but not in Y____
____Component____ 1 ____
____Component____ 2 ____
____Component____ 3 ____
____Predicting X with NA in X and not in Y____
****________________________________________________****

> summary(fitted)
Risk Model:
Call:
coxph(formula = formula(paste("Surv(", timevar, ",", eventvar, 
    "== \"", eventvalue, "\") ~ Risk", sep = "")), data = Xout)

  n= 112, number of events= 49 

       coef exp(coef) se(coef)     z Pr(>|z|)    
Risk 1.0000    2.7183   0.1319 7.582  3.4e-14 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

     exp(coef) exp(-coef) lower .95 upper .95
Risk     2.718     0.3679     2.099      3.52

Concordance= 0.814  (se = 0.034 )
Likelihood ratio test= 63.67  on 1 df,   p=1e-15
Wald test            = 57.49  on 1 df,   p=3e-14
Score (logrank) test = 52.22  on 1 df,   p=5e-13

SplitModel:
Call:
coxph(formula = formula(paste("Surv(", timevar, ",", eventvar, 
    "==\"", eventvalue, "\") ~ Split", sep = "")), data = Xout)

  n= 112, number of events= 49 

         coef exp(coef) se(coef)   z Pr(>|z|)    
Split  2.3571   10.5606   0.4286 5.5  3.8e-08 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

      exp(coef) exp(-coef) lower .95 upper .95
Split     10.56    0.09469     4.559     24.46

Concordance= 0.725  (se = 0.029 )
Likelihood ratio test= 44.08  on 1 df,   p=3e-11
Wald test            = 30.25  on 1 df,   p=4e-08
Score (logrank) test = 42.95  on 1 df,   p=6e-11

PLS Model:
  n= 112, number of events= 49 

        coef exp(coef) se(coef)     z Pr(>|z|)    
tt.1 0.75268   2.12269  0.11444 6.577 4.79e-11 ***
tt.2 0.61475   1.84920  0.11538 5.328 9.92e-08 ***
tt.3 0.22720   1.25508  0.08479 2.679  0.00737 ** 
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

     exp(coef) exp(-coef) lower .95 upper .95
tt.1     2.123     0.4711     1.696     2.656
tt.2     1.849     0.5408     1.475     2.318
tt.3     1.255     0.7968     1.063     1.482

Concordance= 0.814  (se = 0.034 )
Likelihood ratio test= 63.67  on 3 df,   p=1e-13
Wald test            = 57.49  on 3 df,   p=2e-12
Score (logrank) test = 52.58  on 3 df,   p=2e-11

> p <- predict(fitted)
> summary(p)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
-4.6400 -0.9655  0.1312  0.0000  0.8547  4.5559 
> plot(fitted, xlab = "Time (Days)", legloc = "topright", main = "Training Data")
> ## Make sure we can predict on new data
> testobj <- MO[, !train]
> summary(testobj)
Datasets:
     ClinicalBin ClinicalCont MAF Meth450 miRSeq mRNASeq RPPA
[1,]          53            6 566    1454    926    2520  192
[2,]          73           73  73      73     73      73   73
Outcomes:
   patient_id vital_status days_to_death    days_to_last_followup
 a4a1   : 1   alive:45     Min.   :  47.0   Min.   :   4.0       
 a4a2   : 1   dead :28     1st Qu.: 208.0   1st Qu.: 365.0       
 a4a3   : 1                Median : 317.0   Median : 388.0       
 a4a4   : 1                Mean   : 402.8   Mean   : 497.2       
 a4a5   : 1                3rd Qu.: 554.0   3rd Qu.: 549.0       
 a4a6   : 1                Max.   :1405.0   Max.   :1641.0       
 (Other):67                NA's   :45       NA's   :28           
      Days     
 Min.   :   4  
 1st Qu.: 247  
 Median : 383  
 Mean   : 461  
 3rd Qu.: 553  
 Max.   :1641  
               
> ## How do we get rid of the "Missing value" information?
> pre <- predict(fitted, newdata = testobj)
> prer <- predict(fitted, newdata = testobj, type = "risk")
> pres <- predict(fitted, newdata = testobj, type = "split")
> pairs(cbind(pre, prer, pres))
> 
> ## Things that should fail:
> p <- try( predict(fitted, "risk") )
Error in newdata@data : 
  no applicable method for `@` applied to an object of class "character"
> p <- try( predict(fitted, type = "riak") )
Error in match.arg(type) : 
  'arg' should be one of "components", "risk", "split", "survfit"
> 
> proc.time()
   user  system elapsed 
   7.00    1.46    9.82