Abstract：
Klebsiella pneumoniae is a type of Gram-negative bacterium which can cause a range of infections in human. In recent years, an increasing number of strains of K. pneumoniae resistant to multiple antibiotics have emerged, posing a significant threat to public health. The protein function of this bacterium is not well known, thus a systematic investigation of K. pneumoniae proteome is in urgent need. In this study, the protein functions of this bacteria were re-annotated, and their function groups were analyzed. Moreover, three machine learning models were built to identify novel virulence factors. Results showed that the functions of 16 uncharacterized proteins were first annotated by sequence alignment. In addition, K. pneumoniae proteins share a high proportion of homology with Haemophilus influenzae and a low homology proportion with Chlamydia pneumoniae. By sequence analysis, 10 proteins were identified as potential drug targets for this bacterium. Our model achieved a high accuracy of 0.901 in the benchmark dataset. By applying our models to K. pneumoniae, we identified 39 virulence factors in this pathogen. Our findings could provide novel clues for the treatment of K. pneumoniae infection.
摘要：
肺炎克雷伯菌是一种革兰氏阴性细菌，可引起人类多种感染。近年来,越来越多的肺炎克雷伯菌对多种抗生素具有耐药性，对公众健康构成重大威胁。这种细菌的蛋白质功能尚不清楚，因此，迫切需要对肺炎克雷伯菌蛋白质组进行系统的研究。在这项研究中,这种细菌的蛋白质功能被重新注释，并对其功能组进行了分析。此外，建立了三个机器学习模型来识别新的毒力因子。结果表明，16个未表征的蛋白质的功能首先通过序列比对注释。此外,肺炎克雷伯菌蛋白与流感嗜血杆菌具有高比例的同源性,与肺炎衣原体具有低比例的同源性。通过序列分析,10种蛋白质被鉴定为该细菌的潜在药物靶标。我们的模型在基准数据集中实现了0.901的高精度。通过将我们的模型应用于肺炎克雷伯菌，我们在该病原体中鉴定出39个毒力因子。我们的发现可以为肺炎克雷伯菌感染的治疗提供新的线索。
