A digital twin of the infant microbiome to predict neurodevelopmental deficits

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 16S 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 R² = 0.69. Contrasting the fit to Q-nets of typical versus suboptimal development, we can reliably estimate individual deficit risk (Mδ) 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.

All data needed to evaluate the conclusions in the paper are present in the paper and/or the Supplementary Materials. Q-net models are available at the permanent links https://doi.org/10.5281/zenodo.7453696 and https://doi.org/10.5281/zenodo.7942501. Complete software is available as a python installable application at https://pypi.org/project/qbiome/ (also deposited to a permanent repository, accessible as https://doi.org/10.5281/zenodo.7459014), which includes installation notes, and examples to run the inference and computation of Mδ risk for individual patients. Q-net models inferred for the key results in this study are available at the permanent links https://doi.org/10.5281/zenodo.7453696 and https://doi.org/10.5281/zenodo.7942501.