@techreport{oai:ipsj.ixsq.nii.ac.jp:00083422,
 author = {Morihiro, Hayashida and Mayumi, Kamada and Jiangning, Song and Tatsuya, Akutsu and Morihiro, Hayashida and Mayumi, Kamada and Jiangning, Song and Tatsuya, Akutsu},
 issue = {4},
 month = {Aug},
 note = {It is important to understand interactions between proteins and RNAs for uncovering networks and functions of molecules in cellular systems. Many researchers have studied for analyzing and investigating interactions between protein residues and RNA bases. For interactions between protein residues, it is supported that residues at interacting sites have co-evolved with the corresponding residues in the partner protein to keep the interactions between the proteins. In our previous work, on the basis of this idea, we calculated mutual information (MI) between residues from multiple sequence alignments of homologous proteins for identifying interacting pairs of residues in interacting proteins, and combined it with the discriminative random field (DRF), which is useful to extract some characteristic regions from an image in the field of image processing, and is a special type of conditional random fields (CRFs). In a similar way, in this technical report, we make use of mutual information for predicting interactions between protein residues and RNA bases. Furthermore, we introduce labels of amino acids and bases as features of a simple two-dimensional CRF instead of DRF. To evaluate our method, we perform computational experiments for several interactions between Pfam domains and Rfam entries. The results suggest that the CRF model with MI and labels is more useful than the CRF model with only MI., It is important to understand interactions between proteins and RNAs for uncovering networks and functions of molecules in cellular systems. Many researchers have studied for analyzing and investigating interactions between protein residues and RNA bases. For interactions between protein residues, it is supported that residues at interacting sites have co-evolved with the corresponding residues in the partner protein to keep the interactions between the proteins. In our previous work, on the basis of this idea, we calculated mutual information (MI) between residues from multiple sequence alignments of homologous proteins for identifying interacting pairs of residues in interacting proteins, and combined it with the discriminative random field (DRF), which is useful to extract some characteristic regions from an image in the field of image processing, and is a special type of conditional random fields (CRFs). In a similar way, in this technical report, we make use of mutual information for predicting interactions between protein residues and RNA bases. Furthermore, we introduce labels of amino acids and bases as features of a simple two-dimensional CRF instead of DRF. To evaluate our method, we perform computational experiments for several interactions between Pfam domains and Rfam entries. The results suggest that the CRF model with MI and labels is more useful than the CRF model with only MI.},
 title = {Predicting Protein-RNA Residue-base Contacts Using Two-dimensional Conditional Random Field},
 year = {2012}
}