FMCA-DTI: a fragment-oriented method based on a multihead cross attention mechanism to improve drug-target interaction prediction.

MOTIVATION: Identifying drug-target interactions (DTI) is crucial in drug discovery. Fragments are less complex and can accurately characterize local features, which is important in DTI prediction. Recently, deep learning (DL)-based methods predict DTI more efficiently. However, two challenges remain in existing DL-based methods: (i) some methods directly encode drugs and proteins into integers, ignoring the substructure representation; (ii) some methods learn the features of the drugs and proteins separately instead of considering their interactions. RESULTS: In this article, we propose a fragment-oriented method based on a multihead cross attention mechanism for predicting DTI, named FMCA-DTI. FMCA-DTI obtains multiple types of fragments of drugs and proteins by branch chain mining and category fragment mining. Importantly, FMCA-DTI utilizes the shared-weight-based multihead cross attention mechanism to learn the complex interaction features between different fragments. Experiments on three benchmark datasets show that FMCA-DTI achieves significantly improved performance by comparing it with four state-of-the-art baselines. AVAILABILITY AND IMPLEMENTATION: The code for this workflow is available at: https://github.com/jacky102022/FMCA-DTI.

Slope stability analysis considering the strength anisotropy of c-φ soil.

In traditional slope stability analyses, soil is usually approximated as isotropic. However, naturally cohesive soil deposits are inherently anisotropic, primarily due to the directional arrangement of soil particles during their deposition process. In this paper, a generalized anisotropic constitutive model for c-φ soil is introduced to evaluate the influence of varying shear strength on slope stability. In this model, the initial strength anisotropy is defined by the variety of friction angles to the direction of the principle stress. This model is utilized by two approaches to estimate the slope stability. Firstly, the upper bound limit analysis solution for slope stability is developed, and the safety factor of the slopes is studied. Secondly, this model is coupled with the finite element method to get insight of the influence of anisotropy on slope stability. One typical slope case of slope is studied by numerical analyses. It is found that the slope stability is largely overestimated when the strength anisotropy is ignored, and the overestimation, in terms of safety factors, can reach up to 32.9%. The complex interrelations between the degree of anisotropy and evolution of the ensuing safety factor are revealed by a series of parametric studies in terms of different degrees of anisotropy.

Sevoflurane attenuates ventilator­induced lung injury by regulating c­PLA2 expression.

The aim of the present study was to investigate the potential role of club cell secretory protein (CCSP), an endogenous modulator, in reducing pulmonary inflammation induced by sevoflurane following one­lung ventilation (OLV). Healthy Japanese white rabbits were randomly assigned to six groups: Sham­operated group (group S); respiratory management of OLV group (group O); OLV + sevoflurane treated group (group OF), club cells exfoliated + sham­operated group (group NA), club cells exfoliated + OLV group (group NAO); and club cells exfoliated + OLV + sevoflurane treated group (group NAOF). At the end of the experimental observation, all animals in the different groups were sacrificed and lung injury was evaluated according to the lung wet/dry weight ratio and histological scoring system. Lung homogenates were harvested to detect the mRNA and protein expression of cytosolic phospholipase A2 (c­PLA2) and CCSP. The content of arachidonic acid was measured using an ELISA. Following OLV treatment, c­PLA2 expression was increased, CCSP expression was decreased and lung injury scores were significantly increased. Sevoflurane inhalation in the OLV­treated group induced an upregulation of CCSP and a downregulation of c­PLA2 expression. In the group NAO, in which the club cells were simultaneously exfoliated, OLV caused more severe lung damage and induced higher expression of c­PLA2 compared with that in group O. However, sevoflurane inhalation reduced the extent of lung injury and the expression of c­PLA2, even when the endogenous modulator of lung inflammation, CCSP, was exfoliated (group NAOF). These results indicated that OLV promoted lung inflammation through the CCSP and c­PLA2 pathway. However, the results from the club cells exfoliated group indicated that the CCSP may not be involved in the protective effect exerted by sevoflurane inhalation.