From: An integrative imputation method based on multi-omics datasets
A: Initialize with replacing all missing values in all matrices G i , i = 1, 2, 3 by self-imputation methods to obtain complete matrices {G (0) i }. |
B: for each iteration h,  |
 (1). |
  a. Self-impute G 1 based on G (h − 1)1 ; Cross-impute G 1 by G (h − 1)2 , G h − 13 using multi-omics imputation method to obtain G (h)1 . |
  b. Self-impute G 2 based on G (h − 1)2 ; Cross-impute G 2 by G (h)1 , using multi-omics imputation method to obtain G (h)2 . |
  c. Self-impute G 3 based on G (h − 1)3 ; Cross-impute G 3 by G (h)1 , G (h)2 using multi-omics imputation method to obtain G (h)3 . |
 (2). Determine the sum of square of difference on the missing locations j between {G (h − 1) i } and {G (h) i }: |
   \( {\delta}^h={\displaystyle \sum_j{\displaystyle \sum_i{\left({G}_i^{j,\left(h-1\right)}-{G}_i^{j,(h)}\right)}^2}} \) |
C. If δ h ≤ τ, the iteration is stopped and output {G (h) i }; otherwise go to Step 2 to continue the iteration until the convergence criteria τ is reached. |