Antimicrobial peptides (AMPs) are small molecule peptides that are widely found in living organisms with broad-spectrum antibacterial activity and immunomodulatory effect. Due to slower emergence of resistance, excellent clinical potential and wide range of application, AMP is a strong alternative to conventional antibiotics. AMP recognition is a significant direction in the field of AMP research. The high cost, low efficiency and long period shortcomings of the wet experiment methods prevent it from meeting the need for the large-scale AMP recognition. Therefore, computer-aided identification methods are important supplements to AMP recognition approaches, and one of the key issues is how to improve the accuracy. Protein sequences could be approximated as a language composed of amino acids. Consequently, rich features may be extracted using natural language processing (NLP) techniques. In this paper, we combine the pre-trained model BERT and the fine-tuned structure Text-CNN in the field of NLP to model protein languages, develop an open-source available antimicrobial peptide recognition tool and conduct a comparison with other five published tools. The experimental results show that the optimization of the two-phase training approach brings an overall improvement in accuracy, sensitivity, specificity, and Matthew correlation coefficient, offering a novel approach for further research on AMP recognition.
Anti-Bacterial Agents/chemistry* ; Amino Acid Sequence ; Antimicrobial Cationic Peptides/chemistry* ; Antimicrobial Peptides ; Natural Language Processing

Objective: To explore the effect of miR-3188 on the proliferation, apoptosis, invasion and migration of gastric cancer cells and the underlying molecular mechanism. Methods: The expression level of miR-3188 was examined in normal human gastric mucosal cells(GES-1) and human gastric cancer cell lines(HGC-27,MGC-803,BGC-823,MKN-45) by qRT-PCR. It was determined by bioinformatic analysis and dual luciferase reporter assay whether NRAGE was the target gene of miR-3188.miR-3188 mimic, miR-3188 inhibitor and negative control miR-NC were transfected into gastric cancer cell line HGC-27 respectively, and the expression of NRAGE on protein and mRNA levels was detected by Western blot and qRT-PCR. miR-3188 mimic, NRAGE overexpression plasmid(pc-NRAGE) and its negative control(miR-NC,pc-control) were separately or co-transfected into gastric cancer cell line HGC-27. CCK-8, flow cytometry and Transwell experiment were used to detect cell proliferation, apoptosis, invasion and migration in each group. The expressions of epithelial-mesenchymal transition(EMT), proliferation, apoptosis, invasion and migration related proteins [CyclinD 1,matrix metalloproteinase 9(MMP 9),Bcl-2,N-cadherin, Vimentin, E-cadherin] in each group were detected by Western blot. Results: The expression of miR-3188 in human gastric cancer cell lines was lower than that of human normal gastric mucosal cells. Bioinformatics analysis and dual luciferase reporter assay confirmed that miR-3188 could target and bind to NRAGE 3′UTR.Western blot and qRT-PCR confirmed that miR-3188 negatively regulated the expression of NRAGE on the protein level in HGC-27 cells, but not on the mRNA level. Compared with the miR-NC group, Transfected miR-3188 mimic reduced the proliferation, invasion and migration ability of HGC-27 cells, and increased the apoptosis rate, and the co-transfection of pc-NRAGE could reverse the above effects. Compared with the miR-NC group, when miR-3188 was overexpressed in HGC-27 cell, the expression of cyclinD 1, MMP 9, Bcl-2, N-cadherin, and Vimentin was down regulated, while E-cadherin expression was up-regulated, and the above effects could be reversed by co-transfection with pc-NRAGE. Conclusion The miR-3188/NRAGE axis may play important roles in the progression of gastric cancer, and miR-3188 may be a potential therapeutic target for gastric cancer.