Abstract

The low rate of discovery and rapid spread of resistant pathogens have made antibiotic discovery a worldwide priority. In cell-based screening, the mechanism of action (MOA) is identified after antimicrobial activity. This increases rediscovery, impairs low potency candidate detection, and does not guide lead optimization. In this study, high-throughput Fourier-transform infrared (FTIR) spectroscopy was used to discriminate the MOA of 14 antibiotics at pathway, class, and individual antibiotic level. For that, the optimal combinations and parametrizations of spectral preprocessing were selected with cross-validated partial least squares discriminant analysis, to which various machine learning algorithms were applied. This coherently resulted in very good accuracies, independently of the algorithms, and at all levels of MOA. Particularly, an ensemble of subspace discriminants predicted the known pathway (98.6%), antibiotic classes (100%), and individual antibiotics (97.8%) with exceptional accuracy, and similar results were obtained for simulated novel MOA. Even at very low concentrations (1 μg/mL) and growth inhibition (15%), over 70% pathway and class accuracy was achieved, suggesting FTIR spectroscopy can probe the grey chemical matter. Prediction of inhibitory effect was also examined, for which a squared exponential Gaussian process regression yielded a root mean square error of 0.33 and a R² of 0.92, indicating that metabolic alterations leading to growth inhibition are intrinsically reflected on FTIR spectra beyond cell density.

Key points

• Antibiotic MOA and potency estimated with high-throughput FTIR spectroscopy

• Sub-inhibitory MOA identification suggests ability to explore grey chemical matter

• Data analysis optimization improved MOA identification at antibiotic level by 38%

中文翻译：

---

通过高通量傅里叶变换红外（FTIR）光谱和机器学习同时阐明抗生素的作用机理和功效

摘要

耐药病原体的发现率低和迅速传播已使抗生素发现成为世界范围的优先考虑。在基于细胞的筛选中，在抗菌活性后确定了作用机理（MOA）。这增加了重新发现，削弱了低效能候选物的检测，并且不指导潜在顾客优化。在这项研究中，高通量傅立叶变换红外（FTIR）光谱用于区分14种抗生素在途径，类别和个体抗生素水平上的MOA。为此，通过交叉验证的偏最小二乘判别分析选择了光谱预处理的最佳组合和参数，并对其应用了各种机器学习算法。独立于算法以及在MOA的所有级别上，这连贯地带来了非常好的准确性。尤其，一组亚空间判别器以极高的准确性预测了已知途径（98.6％），抗生素类别（100％）和单个抗生素（97.8％），并且对模拟新型MOA获得了相似的结果。即使在极低的浓度（1μg/ mL）和生长抑制（15％）下，也可以达到70％以上的途径和分类准确度，这表明FTIR光谱可以探测灰色化学物质。还检查了抑制作用的预测，为此，平方指数高斯过程回归得出的均方根误差为0.33，达到了70％以上的途径和分类准确度，这表明FTIR光谱可以探测灰色化学物质。还检查了抑制作用的预测，为此，平方指数高斯过程回归得出的均方根误差为0.33，达到了70％以上的途径和分类准确度，这表明FTIR光谱可以探测灰色化学物质。还检查了抑制作用的预测，为此，平方指数高斯过程回归得出的均方根误差为0.33，R ²为0.92，表明导致生长抑制的代谢改变固有地反映在细胞密度以外的FTIR光谱上。

关键点

•通过高通量FTIR光谱估计抗生素的MOA和效力

•亚抑制性MOA鉴定表明具有探索灰色化学物质的能力

•数据分析优化使抗生素水平的MOA鉴定提高了38％