West, J. J. | Search bioRxiv

bioRxiv2020

An integrated model system to gain mechanistic insights into biofilm formation and antimicrobial resistance development in Pseudomonas aeruginosa MPAO1

Pseudomonas aeruginosa MPAO1 is the parental strain of the widely utilized transposon mutant collection for this important clinical pathogen. Here, we validate a model system to identify genes involved in biofilm growth and antibiotic resistance. Our model employs a genomics-driven workflow to assemble the complete MPAO1 genome, identify unique and conserved genes by comparative genomics with the PAO1 reference strain and missed genes by proteogenomics. Among over 200 unique MPAO1 genes, we identified six general essential genes that were overlooked when mapping public Tn-seq datasets against PAO1, including an antitoxin. Genomic data were integrated with phenotypic data from an experimental workflow using a user-friendly, soft lithography-based microfluidic flow chamber for biofilm growth. Experiments conducted across three laboratories delivered reproducible data on P. aeruginosa biofilms and validated both known and novel genes involved in biofilm growth and antibiotic resistance identified in screens of the mutant collection. Differential protein expression data from planktonic cells versus biofilm confirmed upregulation of candidates known to affect biofilm formation, of structural and secreted proteins of type six secretion systems, and provided proteogenomic evidence for some missed MPAO1 genes. This integrated, broadly applicable model promises to improve the mechanistic understanding of biofilm formation, antimicrobial tolerance and resistance evolution.

systems biology↗

bioRxiv2019

Mapping biology from mouse to man using transfer learning

Biomedical research often involves conducting experiments on model organisms in the anticipation that the biology learnt from these experiments will transfer to the human. Yet, it is commonly the case that biology does not transfer effectively, often for unknown reasons. Despite its importance to translational research this transfer process is not currently rigorously quantified. Here, we show that transfer learning - the branch of machine learning that concerns passing information from one domain to another - can be used to efficiently map biology from mouse to man, using the bone marrow (BM) as a representative example of a complex tissue. We first trained an artificial neural network (ANN) to accurately recognize various different cell types in mouse BM using data obtained from single-cell RNA-sequencing (scRNA-Seq) experiments. We found that this ANN, trained exclusively on mouse data, was able to identify individual human cells obtained from comparable scRNA-Seq experiments of human BM with 83% overall accuracy. However, while some human cell types were easily identified, others were not, indicating important differences in biology. To obtain a more accurate map of the human BM we then retrained the mouse ANN using scRNA-Seq data from a limited sample of human BM cells. Typically, less than 10 human cells of a given type were needed to accurately learn its representation in the updated model. In some cases, human cell identities could be inferred directly from the mouse ANN without retraining, via a process of biologically-guided zero-shot learning. These results show how machine learning can be used to reconstruct complex biology from limited data and have broad implications for biomedical research.

systems biology↗