Dietary ecology of the Australian freshwater turtle (Elseya sp.: Chelonia : Chelidae) in the Burnett River, Queensland

The Burnett River snapping turtle (Elseya sp.) from the Burnett, Mary and Fitzroy river systems is an undescribed Australian freshwater turtle, of which very little ecological information is known. This paper describes the dietary ecology of the species in the Burnett River catchment. Stomach and faecal samples were collected from turtles and an index of relative importance was used to rank food items found in stomach samples. This index indicated that algae and aquatic ribbon weed (Vallisneria) were the dominant food items consumed. No difference in diet was found between males and females. Although the sample size was small, diet appeared to vary slightly seasonally, with Elseya sp. selectively feeding on the flower buds of the Chinese elm tree (Celtis chinensis) and the seeds of the blackbean tree (Castanospermum australe) when these food items were seasonally available. Faecal samples suggest that the most ingested foods ( algae and aquatic ribbon weed) were also the most digestible. Although predominantly herbivorous, Elseya sp. was seen to eat carrion once in the wild.

Extreme learning machine for predicting HLA-peptide binding

Machine learning techniques have been recognized as powerful tools for learning from data. One of the most popular learning techniques, the Back-Propagation (BP) Artificial Neural Networks, can be used as a computer model to predict peptides binding to the Human Leukocyte Antigens (HLA). The major advantage of computational screening is that it reduces the number of wet-lab experiments that need to be performed, significantly reducing the cost and time. A recently developed method, Extreme Learning Machine (ELM), which has superior properties over BP has been investigated to accomplish such tasks. In our work, we found that the ELM is as good as, if not better than, the BP in term of time complexity, accuracy deviations across experiments, and most importantly - prevention from over-fitting for prediction of peptide binding to HLA.