Activiteit

Predicting protein-protein interaction sites (PPI sites) can provide important clues for understanding biological activity. Using machine learning to predict PPI sites can mitigate the cost of running expensive and time-consuming biological experiments. Here we propose PPISP-XGBoost, a novel PPI sites prediction method based on eXtreme gradient boosting (XGBoost). First, the characteristic information of protein is extracted through the pseudo-position specific scoring matrix (PsePSSM), pseudo-amino acid composition (PseAAC), hydropathy index and solvent accessible surface area (ASA) under the sliding window. Next, these raw features are preprocessed to obtain more optimal representations in order to achieve better prediction. In particular, the synthetic minority oversampling technique (SMOTE) is used to circumvent class imbalance, and the kernel principal component analysis (KPCA) is applied to remove redundant characteristics. Finally, these optimal features are fed to the XGBoost classifier to identify PPI sites. Using PPISP-XGBoost, the prediction accuracy on the training dataset Dset186 reaches 85.4%, and the accuracy on the independent validation datasets Dtestset72, PDBtestset164, Dset_448 and Dset_355 reaches 85.3%, 83.9%, 85.8% and 85.4%, respectively, which all show an increase in accuracy against existing PPI sites prediction methods. These results demonstrate that the PPISP-XGBoost method can further enhance the prediction of PPI sites.The term ‘MicroRNA’ (miRNA) refers to a class of small endogenous non-coding RNAs (ncRNAs) regenerated from hairpin transcripts. Recent studies reveal miRNAs’ regulatory involvement in essential biological processes through translational repression or mRNA degradation. Recently, there is a growing body of literature focusing on the importance of miRNAs and their functions. In this respect, several databases have been developed to manage the dispersed data produced. Therefore, it is necessary to know the parameters and characteristics of each database to benefit their data. Besides, selecting the correct database is of great importance to scientists who do not have enough experience in this field. A comprehensive classification along with an explanation of the information contained in each database leads to facilitating access to these resources. In this regard, we have classified relevant databases into several categories, including miRNA sequencing and annotation, validated/predicted miRNA targets, disease-related miRNA, SNP in miRNA sequence or target site, miRNA-related pathways, or gene ontology, and mRNA-miRNA interactions. Hence, this review introduces available miRNA databases and presents a convenient overview to inform researchers of different backgrounds to find suitable miRNA-related bioinformatics web tools and relevant information rapidly.Strabismus is an eye disease that affects about 0.12%-9.86% of the population, which can cause irreversible sensory damage to vision and psychological problems. The most severe cases require surgical intervention, despite other less invasive techniques being available for a more conservative approach. As for surgeries, the treatment goal is to align the eyes to recover binocular vision, which demands knowledge, training, and experience. One of the leading causes of failure is human error during the measurement of deviation. Thus, this work proposes a new method based on the Decision Tree Regressor algorithms to assist in the surgical planning for horizontal strabismus to predict recoil and resection measures in the lateral and medial rectus muscles. In the presented method, two application approaches were taken, being in the form of multiple single target models, one procedure at a time, and the form of one multiple target model or all surgical procedures together. The method’s efficiency is indicated by the average difference between the value indicated by the method and the physician’s value. In our most accurate model, an average error of 0.66 mm was obtained for all surgical procedures, both for resection and recoil in the indication of the horizontal strabismus surgical planning. The results present the feasibility of using Decision Tree Regressor algorithms to perform the planning of strabismus surgeries, making it possible to predict correction values for surgical procedures based on medical data analysis and exceeding state-of-art.The spatial distribution and temporal trends of trace metals (i.e. Cd, Cu, Hg, Pb and Zn) and a metalloid (i.e. As) along the Spanish Mediterranean coast from 1993 to 2013 are presented with a new estimation of their background levels monitored using wild mussels. Over a 20 years period, yearly mussel monitoring was undertaken with a rigorous field sampling protocol using 3 pooled samples strategy (3 x n = 80, with 8 mussels in the 3.0 to 3.9 size categories at each site), obtained in the pre-spawning period (May-June) to minimize biological factors and seasonal variability, which is a fundamental element of the international programme. Spatial distribution was characterized every 5 years and temporal trends were determined in 11 locations. The main aims of the present long term study are to evaluate the environmental status of different coastal locations regarding trace metal levels and follow the evolution of these levels over time after the implementation of regulatory measures. Regarding spatial distributoast as a threshold criterion 1.62 mg/kg d.w. for Cd, 8.75 mg/kg d.w. for Cu, 0.202 mg/kg d.w. for Hg and 2.83 mg/kg d.w. for Pb. Exceptions should exist for As and Zn, for which there should be different levels in each demarcation, due to the geological, hydrological and oceanographic peculiarities of the Spanish coast. For the Levantine-Balearic demarcation, the proposed background concentrations are 117 mg/kg d.w. for As and 200 mg/kg d.w. for Zn., whereas in the Strait of Gibraltar-Alboran Sea demarcation, they are 27.5 mg/kg d.w. for As, and 471 mg/kg d.w. for Zn. this website This work demonstrates the vital importance of defining the background levels of metal(loid)s at a regional or subregional level because, for areas not affected by anthropogenic causes which have high values as the result of natural processes, this would avoid the risk of constantly surpassing the levels proposed in directives.