RESPONSE TO OXIDATIVE STRESS ENABLES FISTULIFERA SOLARIS TO EFFICIENTLY PRODUCE BIOFUEL
Published In: 2ND INTERNATIONAL CONFERENCE ON ADVANCES IN BIO-INFORMATICS, BIO-TECHNOLOGY AND ENVIRONMENTAL ENGINEERING
Author(s): MASAYOSHI TANAKA , PUI SHAN WONG , SACHIYO ABURATANI , TAKEAKI TANIGUCHI , TOMOKO YOSHINO , TSUYOSHI TANAKA , YOSHIAKI MAEDA , YOSHIHIKO SUNAGA
Abstract: Biofuel can be produced sustainably by oleaginous microalgae when they are grown in nitrogen limited conditions. Fistulifera solaris JPCC DA0580 demonstrates higher lipid accumulation as a percentage of cell weight than other diatoms in nitrogen limited conditions. These features make it a solid candidate for biofuel production so we compared the gene expression of F. solaris with its close relative and a model diatom, Phaeodactylum tricornutum. The gene expression of the two diatoms cultured in low nitrogen conditions were used to calculate the difference in fold change expression. We selected genes exhibiting significantly different fold change differences and divided them into groups based on the direction of the fold change. These groups were characterised by the gene ontologies of known genes within their respective groups and the degree of fold change differences between the two diatoms in each group. The gene ontologies and fold change differences helped to highlight the differe
- Publication Date: 17-Nov-2014
- DOI: 10.15224/978-1-63248-053-8-06
- Views: 0
- Downloads: 0
INFERRING GENES INVOLVED IN METABOLIC PATHWAYS BY USING SUPPORT VECTOR MACHINES
Published In: 2ND INTERNATIONAL CONFERENCE ON ADVANCES IN BIO-INFORMATICS, BIO-TECHNOLOGY AND ENVIRONMENTAL ENGINEERING
Author(s): SACHIYO ABURATANI , SHOHEI MARUYAMA , YASUO MATSUYAMA
Abstract: The development of a method to annotate unknown gene functions is an important task in bioinformatics. The identification of the relevant genes to metabolic pathways is also helpful for understanding the genes. However, the relationships between metabolic pathways and genes are complicated. Thus, it is difficult to identify the relevant genes by linear models. In this study, we propose a new method based on the SVM approach, for inferring the genes involved in metabolic pathways from the gene expression profiles. To improve the classification performances of SVMs, we developed a method for finding the important interactions for classification, from a huge number of experiment combinations. The interactions selected by our method were added as new features to the training data set of the SVMs. Furthermore, feature selection by the Gini importance was applied, to avoid overlearning of the SVMs. To demonstrate the validity of our method, we trained SVMs with Saccharomyces cerevisiae gene
- Publication Date: 17-Nov-2014
- DOI: 10.15224/978-1-63248-053-8-07
- Views: 0
- Downloads: 0