Antimicrobial peptides (AMPs) are natural peptides possessing antimicrobial activities. These peptides are important components of the innate immune system. They are found in various organisms. AMP screening and identification by experimental techniques are laborious and time-consuming tasks. Alternatively, computational methods based on machine learning have been developed to screen potential AMP candidates prior to experimental verification. Although various AMP prediction programs are available, there is still a need for improvement to reduce false positives (FPs) and to increase the predictive accuracy. In this work, several well-known single and ensemble machine learning approaches have been explored and evaluated based on balanced training datasets and two large testing datasets. We have demonstrated that the developed program with various predictive models has high performance in differentiating between AMPs and non-AMPs. Thus, we describe the development of a program for the prediction and recognition of AMPs using MaxProbVote, which is an ensemble model. Moreover, to increase prediction efficiency, the ensemble model was integrated with a new hybrid feature based on logistic regression. The ensemble model integrated with the hybrid feature can effectively increase the prediction sensitivity of the developed program called Ensemble-AMPPred, resulting in overall improvements in terms of both sensitivity and specificity compared to those of currently available programs.

The present study examined the changes in protein expression in Spirulina platensis upon exposure to high temperature, with the changes in expression analyzed at the subcellular level. In addition, the transcriptional expression level of some differentially expressed proteins, the expression pattern clustering, and the protein-protein interaction network were analyzed. The results obtained from differential expression analysis revealed up-regulation of proteins involved in two-component response systems, DNA damage and repair systems, molecular chaperones, known stress-related proteins, and proteins involved in other biological processes, such as capsule formation and unsaturated fatty acid biosynthesis. The clustering of all differentially expressed proteins in the three cellular compartments showed: (i) the majority of the proteins in all fractions were sustained tolerance proteins, suggesting the roles of these proteins in the tolerance to high temperature stress, (ii) the level of resistance proteins in the photosynthetic membrane was 2-fold higher than the level in two other fractions, correlating with the rapid inactivation of the photosynthetic system in response to high temperature. Subcellular communication among the three cellular compartments via protein-protein interactions was clearly shown by the PPI network analysis. Furthermore, this analysis also showed a connection between temperature stress and nitrogen and ammonia assimilation.

The present study addresses the differential expression of Spirulina platensis proteins detected during cold-induced stress, analyzed at the subcellu

The present study focused on comparative proteome analyses of low- and high-temperature stresses and potential protein-protein interaction networks, constructed by using a bioinformatics approach, in response to both stress conditions. The data revealed two important points: first, the results indicate that low-temperature stress is tightly linked with oxidative stress as well as photosynthesis; however, no specific mechanism is revealed in the case of the high-temperature stress response. Second, temperature stress was revealed to be linked with nitrogen and ammonia assimilation. Moreover, the data also highlighted the cross-talk of signaling pathways. Some of the detected signaling proteins, e.g., Hik14, Hik26 and Hik28, have potential interactions with differentially expressed proteins identified in both temperature stress conditions. Some differentially expressed proteins found in the Spirulina protein-protein interaction network were also examined for their physical interactions by a yeast two hybrid system (Y2H). The Y2H results obtained in this study suggests that the potential PPI network gives quite reliable potential interactions for Spirulina. Therefore, the bioinformatics approach employed in this study helps in the analysis of phenomena where proteome analyses of knockout mutants have not been carried out to directly examine for specificity or cross-talk of signaling components.