“Creating novel computational models and high-throughput experimental systems to understand the role of the microbiota in human diseases, and applying these findings to develop new diagnostic tests and therapeutic interventions to improve patient care.“
email: ggerber#bwh.harvard.edu, physical address: Hale Building 8002M, 60 Fenwood Road, Boston, MA 02115
Sept 2020: MTM 2: The rules of microbiota colonization of the mammalian gut
The Gerber lab in collaboration with the Wang lab at Columbia have received a $2.9M grant from the National Science Foundation to develop and apply novel computational and experimental methods to elucidate fundamental rules governing the formation and maintenance of complex microbial ecosystems in the mammalian gut.
July 2020: Spotlight Oral at ICML 2020 Workshop on Human Interpretability in Machine Learning
“Scalable learning of interpretable rules for the dynamic microbiome domain” from Venkata Suhas Maringanti et al.
We present a new fully-differentiable model that learns human-interpretable rules operating on microbiome time-series data to classify host status. Our approach uses a novel 5-layer Neural Inductive Logic Programming (ILP)-type model with domain-specific microbiome and temporal attention mechanisms that outputs human-interpretable classification rules.
July 2020: Genome Medicine paper
“High-resolution temporal profiling of the human gut microbiome reveals consistent and cascading alterations in response to dietary glycans” from Richard Creswell et al.
In collaborative work with Kaleido Biosciences, Inc., we investigated the effects of dietary glycans on the microbiota of human participants. Stool samples, collected at dense temporal resolution (~ 4 times per week over 10 weeks) and analyzed using shotgun metagenomic sequencing, enabled detailed characterization of participants’ microbiomes. For analyzing the microbiome time-series data, we developed MC-TIMME2 (Microbial Counts Trajectories Infinite Mixture Model Engine 2.0), a purpose-built computational tool based on nonparametric Bayesian methods that infer temporal patterns induced by perturbations and groups of microbes sharing these patterns.