Antimicrobial resistance is one of our most serious health threats. Antimicrobial peptides (AMPs), effecter molecules of innate immune system, can defend host organisms against microbes and most have shown a lowered likelihood for bacteria to form resistance compared to many conventional drugs. Thus, AMPs are gaining popularity as better substitute to antibiotics. To aid researchers in novel AMPs discovery, we design computational approaches to screen promising candidates. In this work, we design a deep learning model that can learn amino acid embedding patterns, automatically extract sequence features, and fuse heterogeneous information. Results show that the proposed model outperforms state-of-the-art methods on recognition of AMPs. By visualizing data in some layers of the model, we overcome the black-box nature of deep learning, explain the working mechanism of the model, and find some import motifs in sequences. ACEP model can capture similarity between amino acids, calculate attention scores for different parts of a peptide sequence in order to spot important parts that significantly contribute to final predictions, and automatically fuse a variety of heterogeneous information or features. For high-throughput AMPs recognition, open source software and datasets are made freely available at https://github.com/Fuhaoyi/ACEP .

中文翻译：

---

ACEP：通过自动特征融合和氨基酸嵌入改善抗菌肽的识别。

抗菌素耐药性是我们最严重的健康威胁之一。先天性免疫系统的效应分子抗菌肽（AMPs）可以保护宿主生物免受微生物侵袭，与许多传统药物相比，大多数细菌显示出形成耐药性的可能性更低。因此，AMPs作为抗生素的更好替代品而越来越受欢迎。为了帮助研究人员发现新型AMP，我们设计了计算方法来筛选有前途的候选人。在这项工作中，我们设计了一个深度学习模型，该模型可以学习氨基酸嵌入模式，自动提取序列特征并融合异类信息。结果表明，所提出的模型在识别AMP方面优于最新方法。通过可视化模型某些层中的数据，我们克服了深度学习的黑盒性质，解释模型的工作机制，并在序列中找到一些导入图案。ACEP模型可以捕获氨基酸之间的相似性，计算肽序列不同部分的注意力得分，以便发现对最终预测有重大贡献的重要部分，并自动融合各种异类信息或特征。对于高通量AMP识别，可从https://github.com/Fuhaoyi/ACEP免费获得开源软件和数据集。