Prediction of cystine connectivity using SVM

One of the major contributors to protein structures is the formation of disulphide bonds between selected pairs of cysteines at oxidized state. Prediction of such disulphide bridges from sequence is challenging given that the possible combination of cysteine pairs as the number of cysteines increases in a protein. Here, we describe a SVM (support vector machine) model for the prediction of cystine connectivity in a protein sequence with and without a priori knowledge on their bonding state. We make use of a new encoding scheme based on physico-chemical properties and statistical features (probability of occurrence of each amino acid residue in different secondary structure states along with PSI-blast profiles). We evaluate our method in SPX (an extended dataset of SP39 (swiss-prot 39) and SP41 (swiss-prot 41) with known disulphide information from PDB) dataset and compare our results with the recursive neural network model described for the same dataset.     

An elephantine challenge: human–elephant conflict distribution in the largest Asian elephant population,southern India

Wildlife conservation is a complex issue especially when it involves large carnivores or mega-herbivores that are conflict-prone. Karnataka state in southern India is known to harbor high density of wild elephants. This conservation success story also has opportunity costs for communities living in close proximity to elephants. Despite the fact that human–elephant conflict is a serious conservation and social issue, there is little quantitative understanding of conflict especially over large areas. Here we conduct the first analysis of human–elephant conflict distribution, severity and explanatory factors over the entire state of Karnataka. We use data from the state forest department records on villages that experience conflict, compensation payments made by the government, elephant densities, forest cover and perimeter, and presence of physical barriers to mitigate elephant conflict. In total, 60,939 incidences of crop loss were reported and US$ 2.99 m paid in compensation during April 2008–March 2011. A total of 91 people were killed by elephants and 101 elephants died in retaliatory killings during the study period. A total of 9.4 % of the state’s geographic area covering 25 of the 42 forest administrative divisions were affected. There was no significant difference in conflict incidences or compensation given between protected areas and non-protected areas. There was no correlation between conflict incidences/unit area and elephant density, forest cover, forest perimeter of protected areas and presence of physical barriers. The results depict the importance of efficient management of physical barriers, conserving key habitat linkages, and acts as baseline data for future work.