We have utilized neural networks in different applications of bioinformatics such as discrimination of beta-barrel membrane proteins, mesophilic and thermophilic proteins, different folding types of globular proteins, different classes of transporter proteins and predicting the secondary structures of beta-barrel membrane proteins. In these methods, we have used the information about amino acid composition, neighboring residue information, inter-residue contacts and amino acid properties as features. We observed that the performance with neural networks is comparable to or better than other widely used machine learning techniques.

MOTIVATION: Large-scale detection and classification of alternative splicing and transcriptional initiation (ASTI) is the first step towards detailed studies of the functional implication and mechanisms of these phenomena. RESULTS: We have developed an algorithm that classifies all observed units of ASTI into an extendable set of distinct types (e.g. cassette type) by converting a collection of alignments between a genomic DNA sequence and cDNA sequences into binary description. This description system can uniquely and compactly encode not only typical patterns but also any rare patterns that are usually collectively assigned to 'others.' More than 150 distinct ASTI types were found when this system was applied to genome-wide detection of ASTI units in human and five other eukaryotes. AVAILABILITY: The data detected by this system are available through ASTRA (http://alterna.cbrc.jp/), a database equipped with a Java-based browser that can interactively reorganize the order of displayed splicing patterns on demand.

MOTIVATION: Discriminating outer membrane proteins from other folding types of globular and membrane proteins is an important task both for identifying outer membrane proteins from genomic sequences and for the successful prediction of their secondary and tertiary structures. RESULTS: We have systematically analyzed the amino acid composition of globular proteins from different structural classes and outer membrane proteins. We found that the residues, Glu, His, Ile, Cys, Gln, Asn and Ser, show a significant difference between globular and outer membrane proteins. Based on this information, we have devised a statistical method for discriminating outer membrane proteins from other globular and membrane proteins. Our approach correctly picked up the outer membrane proteins with an accuracy of 89% for the training set of 337 proteins. On the other hand, our method has correctly excluded the globular proteins at an accuracy of 79% in a non-redundant dataset of 674 proteins. Furthermore, the present method is able to correctly exclude alpha-helical membrane proteins up to an accuracy of 80%. These accuracy levels are comparable to other methods in the literature, and this is a simple method, which could be used for dissecting outer membrane proteins from genomic sequences. The influence of protein size, structural class and specific residues for discrimination is discussed.

MOTIVATION: Discriminating outer membrane proteins from other folding types of globular and membrane proteins is an important task both for dissecting outer membrane proteins (OMPs) from genomic sequences and for the successful prediction of their secondary and tertiary structures. RESULTS: We have developed a method based on support vector machines using amino acid composition and residue pair information. Our approach with amino acid composition has correctly predicted the OMPs with a cross-validated accuracy of 94% in a set of 208 proteins. Further, this method has successfully excluded 633 of 673 globular proteins and 191 of 206 alpha-helical membrane proteins. We obtained an overall accuracy of 92% for correctly picking up the OMPs from a dataset of 1087 proteins belonging to all different types of globular and membrane proteins. Furthermore, residue pair information improved the accuracy from 92 to 94%. This accuracy of discriminating OMPs is higher than that of other methods in the literature, which could be used for dissecting OMPs from genomic sequences. AVAILABILITY: Discrimination results are available at http://tmbeta-svm.cbrc.jp.

Abstract Summary: GENIUS II is an automated database system in which open reading frames (ORFs) in complete genomes are assigned to known protein three-dimensional (3D) structures. The system uses the multiple intermediate sequence search method in which query and target sequences are linked by intermediate sequences gathered by PSI-BLAST search. By applying the system to 129 complete genomes, 43.8% on average of the ORFs in the genomes were assigned to known 3D structures and the results are available for free at GENIUS II web site. Availability: http://genius.cbrc.jp Supplementary information: http://genius.cbrc.jp/summary_linking.html