AAi HDRs Renhua Song and Jing Ren presented at the academic conference GIW/InCoB 2015, which was held in the beautiful Odaiba, Tokyo, Japan. Renhua presented the paper ‘Inference of gene interaction networks using conserved subsequential patterns from multiple time course gene expression datasets’ (Qian Liu, Renhua Song and Jinyan Li) in the Dynamic Network Inference section. The paper, which will be published in BMC Genomics, developed a framework for reconstructing a reliable gene interaction network from multiple time-course gene expression datasets and demonstrated that the algorithm is substantially useful in deciphering gene interaction networks from multiple time-course gene expression data, especially for less studied organisms where little knowledge is available except gene expression data.
Jing presented the paper ‘Positive-unlabeled learning for the prediction of conformational B-cell epitopes’ (Jing Ren, Qian Liu, John Ellis, and Jinyan Li) in the Epitope section. This paper, which will be published in BMC Bioinformatics, proposes a new positive-unlabeled learning algorithm to deal with the issue of the incomplete ground truth of training data of B-cell epitopes, which has achieved better performance compared with typical structure-based epitope prediction methods. The researchers also constructed a large unbound structure data set, which can be used as a better benchmark for epitope prediction.
Both presentations were very well received and Renhua and Jing have been awarded a travel fellowship. In coming months, more AAi HDRs will be travelling overseas and locally to present their work.