A function to impute missing expression data, using nearest neighbor averaging.
pamr.knnimpute(data ,k = 10, rowmax = 0.5, colmax = 0.8, maxp = 1500)
The PAM input data. A list with components: x
, an expression
matrix with
genes in the rows, samples in the columns, and y
, a vector of
the class labels for each sample. Same form as used by pamr.train,
and same as that produced by pamr.from.excel
Number of neighbors to be used in the imputation (default=10)
The maximum percent missing data allowed in any row
(default 50%). For any rows with more than rowmax
% missing
are imputed using the overall mean per sample.
The maximum percent missing data allowed in any column
(default 80%). If any column has more than colmax
% missing data,
the program halts and reports an error.
The largest block of genes imputed using the knn
algorithm inside pamr.knnimpute
(default
1500); larger blocks are divided by two-means clustering
(recursively) prior to imputation. If maxp=p
, only knn
imputation is done.
The input data list, with x replaced by the imputed version of x
pamr.knnimpute
uses k-nearest neighbors in the space of genes to impute missing
expression values.
For each gene with missing values, we find the k nearest neighbors using a Euclidean metric, confined to the columns for which that gene is NOT missing. Each candidate neighbor might be missing some of the coordinates used to calculate the distance. In this case we average the distance from the non-missing coordinates. Having found the k nearest neighbors for a gene, we impute the missing elements by averaging those (non-missing) elements of its neighbors. This can fail if ALL the neighbors are missing in a particular element. In this case we use the overall column mean for that block of genes.
Since nearest neighbor imputation costs
\(O(p\log(p))\) operations per gene, where p is the
number of rows, the computational time can be excessive for large p and
a large number of missing rows. Our strategy is to break blocks with
more than maxp
genes into two smaller blocks using two-mean
clustering. This is done recursively till all blocks have less than
maxp
genes. For each block, knn imputation is done separately.
We have set the default value of maxp
to 1500. Depending on the
speed of the machine, and number of samples, this number might be
increased. Making it too small is counter-productive, because the
number of two-mean clustering algorithms will increase.
Hastie, T., Tibshirani, R., Sherlock, G., Eisen, M., Brown, P. and Botstein, D., Imputing Missing Data for Gene Expression Arrays, Stanford University Statistics Department Technical report (1999), http://www-stat.stanford.edu/~hastie/Papers/missing.pdf
Olga Troyanskaya, Michael Cantor, Gavin Sherlock, Pat Brown, Trevor Hastie, Robert Tibshirani, David Botstein and Russ B. Altman, Missing value estimation methods for DNA microarrays BIOINFORMATICS Vol. 17 no. 6, 2001 Pages 520-525