The Development of Chinese Herbal Formulae for Non-severe COVID-19 Based on Artificial Intelligence Technology and Investigation of Its Action Mechanisms / 中医杂志

ABSTRACT

ObjectiveTo develop traditional Chinese medicine （TCM） formulae for the treatment of nonsevere coronavirus disease 2019 （COVID-19） and to explore its anti-inflammatory mechanism. MethodsThe dysregulated signaling pathways were determined in macrophages from bronchoalveolar lavage fluid of COVID-19 patients and in lung epithelial cells infected with SARS-CoV-2 in vitro based on transcriptome analysis. A total of 102 TCM formulae for the clinical treatment of nonsevere COVID-19 were collected through literature. The pathway-reversing rates of these formulae in macrophages and lung epithelial cells were evaluated based on signature signaling pathways， and the basic formula was determined in conjunction with TCM theory. The commonly used Chinese materia medica for nonsevere COVID-19 were summarized from the 102 TCM formulae as abovementioned. And together with the screening results from the Pharmacopoeia of the People's Republic of China， a “Chinese materia medica pool” was esta-blished for the development of TCM formulae for COVID-19. The regulatory effects of each herb on signaling pathways were obtained based on targeted transcriptome analysis. Oriented at reversing dysregulated signaling pathways of COVID-19， the calculation was carried out， and the artificial intelligent methods for compositing formulae， that are exhaustive method and parallel computing， were used to obtain candidate compound formulas. Finally， with reference to professional experience， an innovative formula for the treatment of nonsevere COVID-19 was developed. The ethanol extract of the formula was evaluated for its anti-inflammatory effects by detecting the mRNA expression of interleukin 1b （Il1b）， C-X-C motif chemokine ligand 2 （Cxcl2）， C-X-C motif chemokine ligand 10 （Cxcl10）， C-C motif chemokine ligand 2 （Ccl2）， nitric oxide synthase 2 （Nos2）， and prostaglandin-endoperoxide synthase 2 （Ptgs2） using reverse transcription-quantitative polymerase chain reaction （RT-qPCR） in RAW264.7 cells treated with lipopolysaccharide （LPS）. ResultsIn macrophages and lung epithelial cells， 34 dysregulated signaling pathways associated with COVID-19 were identified respectively. The effects of the 102 formulae for clinical treatment of nonsevere COVID-19 were evaluated based on the dysregulated signaling pathways and targeted transcriptome， and the result showed that Yinqiao Powder and Pingwei Powder （银翘散合平胃散， YQPWP） ranked first， reversing 91.18% of the dysregulated signaling pathways in macrophages and 100% of the dysregulated signaling pathways in lung epithelial cells. Additionally， YQPWP had the function of scattering wind and clearing heat， resolving toxins and removing dampness in accordance with the pathogenesis of wind-heat with dampness in COVID-19. It was selected as the basic formula， and was further modified and optimized to develop an innovative fomula Qiaobang Zhupi Yin （翘蒡术皮饮， QBZPY） based on expert experience and artificial intelligence in composing formulae. QBZPY can reverse all the dysregulated signaling pathways associated with COVID-19 in macrophages and lung epithelial cells， with the reversing rates of 100%. The chief medicinal of QBZPY， including Lianqiao （Fructus Forsythiae）， Xixiancao （Herba Siegesbeckiae） and Niubangzi （Fructus Arctii）， can down-regulate multiple signaling pathways related with virus infection， immune response， and epithelial damage. RT-qPCR results indicated that compared with the model group， the QBZPY group down-regulated the mRNA expression of Il1b， tumor necrosis factor （Tnf）， Cxcl2， Cxcl10， Ccl2， Nos2 and Ptgs2 induced by LPS in RAW264.7 cells （P＜0.05 or P＜0.01）. ConclusionBased on targeted transcriptome analysis， expert experience in TCM and artificial intelligence， QBZPY has been developed for the treatment of nonsevere COVID-19. The ethanol extract of QBZPY has been found to inhibit mRNA expression of several pro-inflammatory genes in a cellular inflammation model.