Predicting Protein-Protein Interactions from Matrix-Based Protein Sequence Using Convolution Neural Network and Feature-Selective Rotation Forest.

Protein is an essential component of the living organism. The prediction of protein-protein interactions (PPIs) has important implications for understanding the behavioral processes of life, preventing diseases, and developing new drugs. Although the development of high-throughput technology makes it possible to identify PPIs in large-scale biological experiments, it restricts the extensive use of experimental methods due to the constraints of time, cost, false positive rate and other conditions. Therefore, there is an urgent need for computational methods as a supplement to experimental methods to predict PPIs rapidly and accurately. In this paper, we propose a novel approach, namely CNN-FSRF, for predicting PPIs based on protein sequence by combining deep learning Convolution Neural Network (CNN) with Feature-Selective Rotation Forest (FSRF). The proposed method firstly converts the protein sequence into the Position-Specific Scoring Matrix (PSSM) containing biological evolution information, then uses CNN to objectively and efficiently extracts the deeply hidden features of the protein, and finally removes the redundant noise information by FSRF and gives the accurate prediction results. When performed on the PPIs datasets Yeast and Helicobacter pylori, CNN-FSRF achieved a prediction accuracy of 97.75% and 88.96%. To further evaluate the prediction performance, we compared CNN-FSRF with SVM and other existing methods. In addition, we also verified the performance of CNN-FSRF on independent datasets. Excellent experimental results indicate that CNN-FSRF can be used as a useful complement to biological experiments to identify protein interactions.

Monochloro non-bridged half-metallocene-type zirconium complexes containing phosphine oxide-(thio)phenolate chelating ligands as efficient ethylene polymerization catalysts.

A series of novel monochloro half-zirconocene complexes containing phosphine oxide-(thio)phenolate chelating ligands of the type, ClCp'Zr[X-2-R(1)-4-R(2)-6-(Ph(2)P=O)C(6)H(2)](2) (Cp' = C(5)H(5), 2a: X = O, R(1) = Ph, R(2) = H; 2b: X = O, R(1) = F, R(2) = H; 2c: X = O, R(1) = (t)Bu, R(2) = H; 2d: X = O, R(1) = R(2) = (t)Bu; 2e: X = O, R(1) = SiMe(3), R(2) = H; 2f: X = S, R(1) = SiMe(3), R(2) = H; Cp' = C(5)Me(5), 2g: X = O, R(1) = SiMe(3), R(2) = H), have been synthesized in high yields. These complexes were identified by (1)H {(13)C} NMR and elemental analyses. Structures for 2b, 2c and 2f were further confirmed by X-ray crystallography. Structural characterization of these complexes reveals crowded environments around the zirconium. Complexes 2b and 2c adopt six-coordinate, distorted octahedral geometry around the zirconium center, in which the equatorial positions are occupied by three oxygen atoms of two chelating phosphine oxide-bridged phenolate ligands and a chlorine atom. The cyclopentadienyl ring and one oxygen atom of the ligand are coordinated on the axial position. Complex 2f also folds a six-coordinate, distorted octahedral geometry around the Zr center, consisting of a Cp-Zr-O (in P=O) axis [177.16°] and a distorted plane of two sulfur atoms and one oxygen atom of two chelating phosphine oxide-bridged thiophenolate ligands as well as a chlorine atom. When activated by modified methylaluminoxane (MMAO), all the complexes exhibited high activities towards ethylene polymerization at high temperature (75 °C), giving high molecular weight polymers with unimodal molecular weight distribution. The formation of 14-electron, cationic metal alkyl species might come from the Zr-O (in phenol ring) bond cleavage based on the DFT calculations study.