Performance evaluation of L1-norm-based microarray missing value imputation

l₁-norm minimization was utilized in the imputation of microarray missing values, which is an important procedure in bioinformatics experiments. Two l₁ approaches, based on the framework of local least squares (LLS) and iterative bicluster-based least squares (bicluster-iLLS) respectively, were employed. Imputed datasets of the l₁ approaches were compared with those of traditional l₂ methods. The imputation error rates showed that the assumption of sparsity is not supported by the microarray datasets. Singular value decompositions in biclusters and in the neighborhoods of target gens were computed to show the structure of a microarray dataset. The coefficients of l₁ minimization solutions were also analyzed to reveal possible reasons for the performance of l₁ approaches.