Fine-grained selective similarity integration for drug-target interaction prediction.

The discovery of drug-target interactions (DTIs) is a pivotal process in pharmaceutical development. Computational approaches are a promising and efficient alternative to tedious and costly wet-lab experiments for predicting novel DTIs from numerous candidates. Recently, with the availability of abundant heterogeneous biological information from diverse data sources, computational methods have been able to leverage multiple drug and target similarities to boost the performance of DTI prediction. Similarity integration is an effective and flexible strategy to extract crucial information across complementary similarity views, providing a compressed input for any similarity-based DTI prediction model. However, existing similarity integration methods filter and fuse similarities from a global perspective, neglecting the utility of similarity views for each drug and target. In this study, we propose a Fine-Grained Selective similarity integration approach, called FGS, which employs a local interaction consistency-based weight matrix to capture and exploit the importance of similarities at a finer granularity in both similarity selection and combination steps. We evaluate FGS on five DTI prediction datasets under various prediction settings. Experimental results show that our method not only outperforms similarity integration competitors with comparable computational costs, but also achieves better prediction performance than state-of-the-art DTI prediction approaches by collaborating with conventional base models. Furthermore, case studies on the analysis of similarity weights and on the verification of novel predictions confirm the practical ability of FGS.

SparNet: A Convolutional Neural Network for EEG Space-Frequency Feature Learning and Depression Discrimination.

Depression affects many people around the world today and is considered a global problem. Electroencephalogram (EEG) measurement is an appropriate way to understand the underlying mechanisms of major depressive disorder (MDD) to distinguish depression from normal control. With the development of deep learning methods, many researchers have adopted deep learning models to improve the classification accuracy of depression recognition. However, there are few studies on designing convolution filters for spatial and frequency domain feature learning in different brain regions. In this study, SparNet, a convolutional neural network composed of five parallel convolutional filters and the SENet, is proposed to learn EEG space-frequency domain characteristics and distinguish between depressive and normal control. The model is trained and tested by the cross-validation method of subject division. The results show that SparNet achieves a sensitivity of 95.07%, a specificity of 93.66%, and an accuracy of 94.37% in classification. Therefore, our results can conclude that the proposed SparNet model is effective in detecting depression using EEG signals. It also indicates that the combination of spatial information and frequency domain information is an effective way to identify patients with depression.

Genome-wide identification and comprehensive analyses of NAC transcription factor gene family and expression analysis under Fusarium kyushuense and drought stress conditions in Passiflora edulis.

The NAC gene family is one of the largest plant transcription factors (TFs) families and plays important roles in plant growth, development, metabolism, and biotic and abiotic stresses. However, NAC gene family has not been reported in passion fruit (Passiflora edulis). In this study, a total of 105 NAC genes were identified in the passion fruit genome and were unevenly distributed across all nine-passion fruit chromomere, with a maximum of 48 PeNAC genes on chromosome one. The physicochemical features of all 105 PeNAC genes varied including 120 to 3,052 amino acids, 3 to 8 conserved motifs, and 1 to 3 introns. The PeNAC genes were named (PeNAC001-PeNAC105) according to their chromosomal locations and phylogenetically grouped into 15 clades (NAC-a to NAC-o). Most PeNAC proteins were predicted to be localized in the nucleus. The cis-element analysis indicated the possible roles of PeNAC genes in plant growth, development, light, hormones, and stress responsiveness. Moreover, the PeNAC gene duplications including tandem (11 gene pairs) and segmental (12 gene pairs) were identified and subjected to purifying selection. All PeNAC proteins exhibited similar 3D structures, and a protein-protein interaction network analysis with known Arabidopsis proteins was predicted. Furthermore, 17 putative ped-miRNAs were identified to target 25 PeNAC genes. Potential TFs including ERF, BBR-BPC, Dof, and bZIP were identified in promoter region of all 105 PeNAC genes and visualized in a TF regulatory network. GO and KEGG annotation analysis exposed that PeNAC genes were related to different biological, molecular, and cellular terms. The qRT-PCR expression analysis discovered that most of the PeNAC genes including PeNAC001, PeNAC003, PeNAC008, PeNAC028, PeNAC033, PeNAC058, PeNAC063, and PeNAC077 were significantly upregulated under Fusarium kyushuense and drought stress conditions compared to controls. In conclusion, these findings lay the foundation for further functional studies of PeNAC genes to facilitate the genetic improvement of plants to stress resistance.

Genome-Wide Identification and Expression Profiling of KCS Gene Family in Passion Fruit (Passiflora edulis) Under Fusarium kyushuense and Drought Stress Conditions.

Plant and fruit surfaces are covered with cuticle wax and provide a protective barrier against biotic and abiotic stresses. Cuticle wax consists of very-long-chain fatty acids (VLCFAs) and their derivatives. ß-Ketoacyl-CoA synthase (KCS) is a key enzyme in the synthesis of VLCFAs and provides a precursor for the synthesis of cuticle wax, but the KCS gene family was yet to be reported in the passion fruit (Passiflora edulis). In this study, thirty-two KCS genes were identified in the passion fruit genome and phylogenetically grouped as KCS1-like, FAE1-like, FDH-like, and CER6-like. Furthermore, thirty-one PeKCS genes were positioned on seven chromosomes, while one PeKCS was localized to the unassembled genomic scaffold. The cis-element analysis provides insight into the possible role of PeKCS genes in phytohormones and stress responses. Syntenic analysis revealed that gene duplication played a crucial role in the expansion of the PeKCS gene family and underwent a strong purifying selection. All PeKCS proteins shared similar 3D structures, and a protein-protein interaction network was predicted with known Arabidopsis proteins. There were twenty putative ped-miRNAs which were also predicted that belong to nine families targeting thirteen PeKCS genes. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) annotation results were highly associated with fatty acid synthase and elongase activity, lipid metabolism, stress responses, and plant-pathogen interaction. The highly enriched transcription factors (TFs) including ERF, MYB, Dof, C2H2, TCP, LBD, NAC, and bHLH were predicted in PeKCS genes. qRT-PCR expression analysis revealed that most PeKCS genes were highly upregulated in leaves including PeKCS2, PeKCS4, PeKCS8, PeKCS13, and PeKCS9 but not in stem and roots tissues under drought stress conditions compared with controls. Notably, most PeKCS genes were upregulated at 9th dpi under Fusarium kyushuense biotic stress condition compared to controls. This study provides a basis for further understanding the functions of KCS genes, improving wax and VLCFA biosynthesis, and improvement of passion fruit resistance.