One of the main challenges in computational biology is the revelation and interpretation of the rich genomic information underlying cancer biology and to facilitating molecular classification and prediction of cancers and responses to therapies. Genomic sequencing and gene expression technologies have been widely recognized as vital approaches to modern drug design and disease classification. With the recent advances in DNA microarray technologies, it has become possible to measure the expression level of thousands of genes simultaneously. However, the large number of genes together with the complexity of gene expression patterns and sequences make interpreting the million of biological measurements a challenging task. Machine learning will play an important role in meeting this challenge. In this special issue, we encourage papers on novel machine learning algorithms for (including, but not limited to)

• Gene expression analysis

• Protein/RNA structure prediction

• Sequence analysis and motif discovery

• Gene discovery

• Drug design