Machine Learning of Designed Translational Control Allows Predictive Pathway Optimization in Escherichia coli

Abstract

The field of synthetic biology aims to make the design of biological systems predictable, shrinking the huge design space to practical numbers for testing. When designing microbial cell factories, most optimization efforts have focused on enzyme and strain selection/ engineering, pathway regulation, and process development. In silico tools for the predictive design of bacterial ribosome binding sites (RBSs) and RBS libraries now allow translational tuning of biochemical pathways; however, methods for predicting optimal RBS combinations in multigene pathways are desirable. Here we present the implementation of machine learning algorithms to model the RBS sequence−phenotype relationship from representative subsets of large combinatorial RBS libraries allowing the accurate prediction of optimal high-producers. Applied to a recombinant monoterpenoid production pathway in Escherichia coli, our approach was able to boost production titers by over 60% when screening under 3% of a library. To facilitate library screening, a multiwell plate fermentation procedure was developed, allowing increased screening throughput with sufficient resolution to discriminate between high and low producers. High producers from one library did not translate during scale-up, but the reduced screening requirements allowed rapid rescreening at the larger scale. This methodology is potentially compatible with any biochemical pathway and provides a powerful tool toward predictive design of bacterial production chassis.

Large-scale DNA-based phenotypic recording and deep learning enable highly accurate sequence-function mapping

“…As a part of the 5′-untranslated region (5′-UTR) of bacterial mRNAs, RBSs dictate the rate-limiting initiation of translation 38 . Because few mutations in this region can lead to orders-of-magnitude differences in protein expression, RBSs have become proven targets for optimization of cellular protein levels, in particular in multi-protein systems such as metabolic pathways 39 , 40 . This trend has been largely fueled by models that predict the relative strength of RBSs 41 – 44 and tools for smart RBS library design 45 , 46 .…”

Large-scale DNA-based phenotypic recording and deep learning enable highly accurate sequence-function mapping

“…As a part of the 5’-untranslated region (5’-UTR) of bacterial mRNAs, RBSs dictate the rate-limiting initiation of translation 36 . Because few mutations in this region can lead to orders-of-magnitude differences in protein expression, RBSs have become proven targets for optimization of cellular protein levels, in particular in multi-protein systems such as metabolic pathways 37, 38 . This trend has been largely fuelled by models that predict the relative strength of RBSs 39–42 and tools for smart RBS library design 43, 44 .…”

A machine learning Automated Recommendation Tool for synthetic biology

“…After this training, the models can be used to predict the outputs for inputs that the model has never seen before. Machine learning has been used to, e.g., predict the use of addictive substances and political views from Facebook profiles 26 , automate language translation 27 , predict pathway dynamics 28 , optimize pathways through translational control 29 , diagnose skin cancer 30 , detect tumors in breast tissues 31 , predict DNA and RNA protein-binding sequences 32 , and drug side effects 33 . However, the practice of machine learning requires statistical and mathematical expertise that is scarce, and highly competed for ref.…”