B-factor is a measure of ray attenuation or scattering caused by atomic thermal motion during X-ray diffraction of protein crystal structure. B-factor reflects the vibration of atoms; hence, it is the most common experimental descriptor of protein flexibility and has been extensively applied in the studies of protein dynamics, screening of bioactive small molecules, and protein engineering. The prediction of B-factor profiles has considerable significance for analyzing the dynamic properties of unknown proteins. Deep learning technology has developed rapidly in recent years and has been widely implemented in many research fields, especially structural biology. In this paper, a deep neural network model based on bidirectional long short-term memory (biLSTM) network is proposed to predict the B-factor profile of a protein by combining its sequence-based features and structure-based features. Based on a large dataset of high-resolution proteins, our method predicts the B-factor profiles with an average Pearson correlation coefficient (PCC) of 0.71, and 85% of the B-factor profiles have a PCC greater than 0.6, which indicates a strong correlation between predicted and experimental values. In addition, our method remarkably outperforms the existing methods on four test datasets with different protein sizes.

UNLABELLED: SCAssign (side-chain assignment) is a Sparky extension written in Python to assist the NMR resonance assignment of aliphatic side-chains of uniformly (13)C,(15)N-labeled large proteins. It is based on a general strategy recently developed in our laboratory that makes use of 4D (13)C,(15)N-edited NOESY, 3D MQ-(H)CC(m)H(m)-TOCSY, and prior backbone assignments. The program runs on all operating systems for which Sparky is available, and is easy to install, setup and use. Not only can it accelerate the assignment process, it also allows assignments of weak NOEs in 4D NOESY, which used to be very difficult with manual approach. AVAILABILITY: The program, in the form of source code, is provided as free download at http://yangdw.science.nus.edu.sg/SCAssign. The website also contains installation guide, user manual and demonstrations recorded in Flash.

UNLABELLED: A graphics package has been developed for performing statistics on interatomic distances and torsion angles in protein secondary structures (STARS) from a protein crystal structure database. It allows one to obtain both the graphical view and the text format of distributions of the distances and angles for atoms located in 10 types of protein secondary structures. STARS will facilitate assignment of ambiguous NOESY peaks, structure determination by nuclear magnetic resonance, structure validation and comparison of protein folds. AVAILABILITY: All data, documents and execute files are freely downloadable at http://stars.zhengyuhome.com. The software works appropriately on Windows system, without any compilation or installation. CONTACT: [email protected].