A small subunit ribosomal RNA (16S‐like rRNA) in the hydrocarbon‐rich microalga Botryococcus braunii Kützing (Chlorophyceae) was amplified using RNA polymerase chain reaction, and its sequence was determined. The sequence data of B. braunii were analyzed with those of several other algae in order to determine phylogenetic relationships among these algae. Phylogenetic analysis indicated B. braunii to be a member of the Chlorophyta and possibly related to Characium vacuolatum and Dunaliella parva.

B-cells inducing antigen-specific immune responses in vivo produce large amounts of antigen-specific antibodies by recognizing the subregions (epitope regions) of antigen proteins. These antibodies can inhibit the functioning of antigen proteins. Predicting epitope regions is beneficial for the design and development of vaccines aimed to induce antigen-specific antibody production. However, prediction accuracy requires improvement. The conventional epitope region prediction methods have focused only on the target sequence in the amino acid sequences of an entire antigen protein and have not thoroughly considered its sequence and features as a whole. In the present paper, we propose a deep learning method based on long short-term memory with an attention mechanism to consider the characteristics of a whole antigen protein in addition to the target sequence. The proposed method achieves better accuracy compared with the conventional method in the experimental prediction of epitope regions using the data from the immune epitope database.

B-cells inducing antigen-specific immune responses in vivo produce large amounts of antigen-specific antibodies by recognizing the subregions (epitope regions) of antigen proteins. They can inhibit their functioning by binding antibodies to antigen proteins. Predicting of epitope regions is beneficial for the design and development of vaccines aimed to induce antigen-specific antibody production. However, prediction accuracy requires improvement. The conventional epitope region prediction methods have focused only on the target sequence in the amino acid sequences of an entire antigen protein and have not thoroughly considered its sequence and features as a whole. In the present paper, we propose a deep learning method based on short-term memory with an attention mechanism to consider the characteristics of a whole antigen protein in addition to the target sequence. The proposed method achieves better accuracy compared with the conventional method in the experimental prediction of epitope regions using the data from the immune epitope database.

In this study, we propose a model that extends the continuous space topic model (CSTM), which flexibly controls word probability in a document, using pre-trained word embeddings.To develop the proposed model, we pre-train word embeddings, which capture the semantics of words and plug them into the CSTM. Intrinsic experimental results show that the proposed model exhibits a superior performance over the CSTM in terms of perplexity and convergence speed. Furthermore, extrinsic experimental results show that the proposed model is useful for a document classification task when compared with the baseline model. We qualitatively show that the latent coordinates obtained by training the proposed model are better than those of the baseline model.

No abstract