Department of Medicine, University of Chicago, Chicago, IL 60637, USA.
Department of Pediatrics, University of Chicago, Chicago, IL 60637, USA.
Sci Adv. 2024 Apr 12;10(15):eadj0400. doi: 10.1126/sciadv.adj0400. Epub 2024 Apr 10.
Despite the recognized gut-brain axis link, natural variations in microbial profiles between patients hinder definition of normal abundance ranges, confounding the impact of dysbiosis on infant neurodevelopment. We infer a digital twin of the infant microbiome, forecasting ecosystem trajectories from a few initial observations. Using 16 ribosomal RNA profiles from 88 preterm infants (398 fecal samples and 32,942 abundance estimates for 91 microbial classes), the model (Q-net) predicts abundance dynamics with = 0.69. Contrasting the fit to Q-nets of typical versus suboptimal development, we can reliably estimate individual deficit risk () and identify infants achieving poor future head circumference growth with ≈76% area under the receiver operator characteristic curve, 95% ± 1.8% positive predictive value at 98% specificity at 30 weeks postmenstrual age. We find that early transplantation might mitigate risk for ≈45.2% of the cohort, with potentially negative effects from incorrect supplementation. Q-nets are generative artificial intelligence models for ecosystem dynamics, with broad potential applications.
尽管已经认识到肠道-大脑轴的联系，但患者之间微生物特征的自然变化阻碍了正常丰度范围的定义，使肠道菌群失调对婴儿神经发育的影响变得复杂。我们推断出婴儿微生物组的数字双胞胎，从几个初始观察预测生态系统轨迹。使用 88 名早产儿的 16 个核糖体 RNA 图谱（398 份粪便样本和 91 种微生物类别的 32942 个丰度估计值），该模型（Q 网络）以 = 0.69 的精度预测丰度动态。对比典型和非最佳发育的 Q 网络的拟合程度，我们可以可靠地估计个体缺陷风险（），并以 ≈76%的接收者操作特征曲线下面积、95%±1.8%的阳性预测值在 98%的特异性在孕龄 30 周时识别出未来头围增长不良的婴儿。我们发现早期移植可能会减轻约 45.2%的队列的风险，但补充不当可能会产生负面影响。Q 网络是生态系统动态的生成式人工智能模型，具有广泛的潜在应用。
