Dimensionality of amino acid space and solvent accessibility prediction with neural networks

Sequence-dependence and prediction of nucleotide solvent accessibility in double stranded DNA

Solvent accessibility of amino acid residues in proteins has been widely studied and many methods for its prediction from sequence and evolutionary information are available. Some of the advantages of studying amino acid solvent accessibility also apply to DNA. However, currently there are no methods to estimate the solvent accessibility of nucleotides, as most works on DNA structures have focused on elastic deformations and other structural attributes. In this work, an attempt has been made to analyze the distribution of different nucleotides in various accessibility ranges. Effect of neighboring nucleotides on the predictability of exposure has been evaluated by developing a linear perceptron model that takes sequence information as the input. Five different types of solvent accessibility (overall nucleotide, side chain, main chain, polar and non-polar) have been predicted. From the analysis, it is observed that Thymine stands out in terms of its higher exposed surface area, particularly its side chain and non-polar atoms. It is also concluded that the solvent accessibility of a nucleotide strongly depends on its sequence neighbors and can be predicted with fair success using this information.

Sequence and structural features of carbohydrate binding in proteins and assessment of predictability using a neural network

Background

Protein-Carbohydrate interactions are crucial in many biological processes with implications to drug targeting and gene expression. Nature of protein-carbohydrate interactions may be studied at individual residue level by analyzing local sequence and structure environments in binding regions in comparison to non-binding regions, which provide an inherent control for such analyses. With an ultimate aim of predicting binding sites from sequence and structure, overall statistics of binding regions needs to be compiled. Sequence-based predictions of binding sites have been successfully applied to DNA-binding proteins in our earlier works. We aim to apply similar analysis to carbohydrate binding proteins. However, due to a relatively much smaller region of proteins taking part in such interactions, the methodology and results are significantly different. A comparison of protein-carbohydrate complexes has also been made with other protein-ligand complexes.

Results

We have compiled statistics of amino acid compositions in binding versus non-binding regions- general as well as in each different secondary structure conformation. Binding propensities of each of the 20 residue types and their structure features such as solvent accessibility, packing density and secondary structure have been calculated to assess their predisposition to carbohydrate interactions. Finally, evolutionary profiles of amino acid sequences have been used to predict binding sites using a neural network. Another set of neural networks was trained using information from single sequences and the prediction performance from the evolutionary profiles and single sequences were compared. Best of the neural network based prediction could achieve an 87% sensitivity of prediction at 23% specificity for all carbohydrate-binding sites, using evolutionary information. Single sequences gave 68% sensitivity and 55% specificity for the same data set. Sensitivity and specificity for a limited galactose binding data set were obtained as 63% and 79% respectively for evolutionary information and 62% and 68% sensitivity and specificity for single sequences. Propensity and other sequence and structural features of carbohydrate binding sites have also been compared with our similar extensive studies on DNA-binding proteins and also with protein-ligand complexes.

Conclusion

Carbohydrates typically show a preference to bind aromatic residues and most prominently tryptophan. Higher exposed surface area of binding sites indicates a role of hydrophobic interactions. Neural networks give a moderate success of prediction, which is expected to improve when structures of more protein-carbohydrate complexes become available in future.