Institution: | aSookmyung Women's University, Department of Biological Sciences, Research Center for Women's Diseases (RCWD), Hyochangwongil 52, Yongsan-gu, Seoul 140-742, Republic of Korea bUniversity of Medicine & Dentistry of New Jersey (UMDNJ), Department of Pharmacology, Robert Wood Johnson Medical School and the Informatics Institute of UMDNJ, 675 Hoes Lane, Piscataway, NJ 08854, USA cKorea University, College of Medicine, Graduate School of Medicine, Anam-dong 126-1, Sungbuk-ku, Seoul 136-705, Republic of Korea |
Abstract: | The calculation of contact-dependent secondary structure propensity (CSSP) has been reported to sensitively detect non-native β-strand propensities in the core sequences of amyloidogenic proteins. Here we describe a noble energy-based CSSP method implemented on dual artificial neural networks that rapidly and accurately estimate the potential for the non-native secondary structure formation in local regions of protein sequences. In this method, we attempted to quantify long-range interaction patterns in diverse secondary structures by potential energy calculations and decomposition on a pairwise per-residue basis. The calculated energy parameters and seven-residue sequence information were used as inputs for artificial neural networks (ANNs) to predict sequence potential for secondary structure conversion. The trained single ANN using the >(i, i ± 4) interaction energy parameter exhibited 74% accuracy in predicting the secondary structure of test sequences in their native energy state, while the dual ANN-based predictor using (i, i ± 4) and >(i, i ± 4) interaction energies showed 83% prediction accuracy. The present method provides a simple and accurate tool for predicting sequence potential for secondary structure conversions without using 3D structural information. |