Survival Design

  1. create timediff variable from date of diagnosis to date of death in days.
  2. Clean the data by changing the log 10 data from continous data to binary data where 0 remains 0 and everything else is changed to 1.
  3. Perform a lifetest on each row. For each row: timediff by flag(0 = alive, 1 = dead), stratify by current row.
    • Grab ChiSq and ProbChiSq for Log-Rank, Wilcoxen, -2Log(LR)
  4. Perform phreg on each row.
    • Grab Estimate, ChiSq and ProbChiSq.
  5. For each row, get the count of columns that are 1.
  6. Select a subset of genes.
  7. For each row, set the chisq values sign to the same sign as the estimate.
  8. For each row, sum the chisq values.
  9. For each row, multiply the data values for that row by the sum value.
  10. For each column, sum the data values for that column.

Need to run survival
  1. Data set to build scores
  2. Data set to modify with scores.
  3. timediff variable (per patient)
  4. path variable (per patient)

Distance objects usage

Load data and score files

  load data set
  load test data set
  load scores

Run user prefilter if provided

if topn generate rankings

Run criteria based prefilter


Loop through criteria sets
  standardize the scores

  filter scores
  get filtered id list from filtered scores
  filter data
  filter test data

  sign the scores

  run distance - train and test
  save distance output

write individual distance output loop

write summary distance output

write eisen data sets

-- JeremyRoberts - 13 Jul 2004
Topic revision: r28 - 16 Sep 2004, JeremyRoberts
 

This site is powered by FoswikiCopyright © 2013-2022 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Vanderbilt Biostatistics Wiki? Send feedback