Applications of artificial intelligence and machine learning in dynamic pathway engineering.

Dynamic pathway engineering aims to build metabolic production systems embedded with intracellular control mechanisms for improved performance. These control systems enable host cells to self-regulate the temporal activity of a production pathway in response to perturbations, using a combination of biosensors and feedback circuits for controlling expression of heterologous enzymes. Pathway design, however, requires assembling together multiple biological parts into suitable circuit architectures, as well as careful calibration of the function of each component. This results in a large design space that is costly to navigate through experimentation alone. Methods from artificial intelligence (AI) and machine learning are gaining increasing attention as tools to accelerate the design cycle, owing to their ability to identify hidden patterns in data and rapidly screen through large collections of designs. In this review, we discuss recent developments in the application of machine learning methods to the design of dynamic pathways and their components. We cover recent successes and offer perspectives for future developments in the field. The integration of AI into metabolic engineering pipelines offers great opportunities to streamline design and discover control systems for improved production of high-value chemicals.

Bayesian Optimization for Design of Multiscale Biological Circuits.

Recent advances in synthetic biology have enabled the construction of molecular circuits that operate across multiple scales of cellular organization, such as gene regulation, signaling pathways, and cellular metabolism. Computational optimization can effectively aid the design process, but current methods are generally unsuited for systems with multiple temporal or concentration scales, as these are slow to simulate due to their numerical stiffness. Here, we present a machine learning method for the efficient optimization of biological circuits across scales. The method relies on Bayesian optimization, a technique commonly used to fine-tune deep neural networks, to learn the shape of a performance landscape and iteratively navigate the design space toward an optimal circuit. This strategy allows the joint optimization of both circuit architecture and parameters, and provides a feasible approach to solve a highly nonconvex optimization problem in a mixed-integer input space. We illustrate the applicability of the method on several gene circuits for controlling biosynthetic pathways with strong nonlinearities, multiple interacting scales, and using various performance objectives. The method efficiently handles large multiscale problems and enables parametric sweeps to assess circuit robustness to perturbations, serving as an efficient in silico screening method prior to experimental implementation.

Integration of datasets for individual prediction of DNA methylation-based biomarkers.

BACKGROUND: Epigenetic scores (EpiScores) can provide biomarkers of lifestyle and disease risk. Projecting new datasets onto a reference panel is challenging due to separation of technical and biological variation with array data. Normalisation can standardise data distributions but may also remove population-level biological variation. RESULTS: We compare two birth cohorts (Lothian Birth Cohorts of 1921 and 1936 - nLBC1921 = 387 and nLBC1936 = 498) with blood-based DNA methylation assessed at the same chronological age (79 years) and processed in the same lab but in different years and experimental batches. We examine the effect of 16 normalisation methods on a novel BMI EpiScore (trained in an external cohort, n = 18,413), and Horvath's pan-tissue DNA methylation age, when the cohorts are normalised separately and together. The BMI EpiScore explains a maximum variance of R2=24.5% in BMI in LBC1936 (SWAN normalisation). Although there are cross-cohort R2 differences, the normalisation method makes a minimal difference to within-cohort estimates. Conversely, a range of absolute differences are seen for individual-level EpiScore estimates for BMI and age when cohorts are normalised separately versus together. While within-array methods result in identical EpiScores whether a cohort is normalised on its own or together with the second dataset, a range of differences is observed for between-array methods. CONCLUSIONS: Normalisation methods returning similar EpiScores, whether cohorts are analysed separately or together, will minimise technical variation when projecting new data onto a reference panel. These methods are important for cases where raw data is unavailable and joint normalisation of cohorts is computationally expensive.

Identification of BvgA-Dependent and BvgA-Independent Small RNAs (sRNAs) in Bordetella pertussis Using the Prokaryotic sRNA Prediction Toolkit ANNOgesic.

Noncoding small RNAs (sRNAs) are crucial for the posttranscriptional regulation of gene expression in all organisms and are known to be involved in the regulation of bacterial virulence. In the human pathogen Bordetella pertussis, which causes whooping cough, virulence is controlled primarily by the master two-component system BvgA (response regulator)/BvgS (sensor kinase). In this system, BvgA is phosphorylated (Bvg+ mode) or nonphosphorylated (Bvg- mode), with global transcriptional differences between the two. B. pertussis also carries the bacterial sRNA chaperone Hfq, which has previously been shown to be required for virulence. Here, we conducted transcriptomic analyses to identify possible B. pertussis sRNAs and to determine their BvgAS dependence using transcriptome sequencing (RNA-seq) and the prokaryotic sRNA prediction program ANNOgesic. We identified 143 possible candidates (25 Bvg+ mode specific and 53 Bvg- mode specific), of which 90 were previously unreported. Northern blot analyses confirmed all of the 10 ANNOgesic candidates that we tested. Homology searches demonstrated that 9 of the confirmed sRNAs are highly conserved among B. pertussis, Bordetella parapertussis, and Bordetella bronchiseptica, with one that also has homologues in other species of the Alcaligenaceae family. Using coimmunoprecipitation with a B. pertussis FLAG-tagged Hfq, we demonstrated that 3 of the sRNAs interact directly with Hfq, which is the first identification of sRNA binding to B. pertussis Hfq. Our study demonstrates that ANNOgesic is a highly useful tool for the identification of sRNAs in this system and that its combination with molecular techniques is a successful way to identify various BvgAS-dependent and Hfq-binding sRNAs. IMPORTANCE Noncoding small RNAs (sRNAs) are crucial for posttranscriptional regulation of gene expression in all organisms and are known to be involved in the regulation of bacterial virulence. We have investigated the presence of sRNAs in the obligate human pathogen B. pertussis, using transcriptome sequencing (RNA-seq) and the recently developed prokaryotic sRNA search program ANNOgesic. This analysis has identified 143 sRNA candidates (90 previously unreported). We have classified their dependence on the B. pertussis two-component system required for virulence, namely, BvgAS, based on their expression in the presence/absence of the phosphorylated response regulator BvgA, confirmed several by Northern analyses, and demonstrated that 3 bind directly to B. pertussis Hfq, the RNA chaperone involved in mediating sRNA effects. Our study demonstrates the utility of combining RNA-seq, ANNOgesic, and molecular techniques to identify various BvgAS-dependent and Hfq-binding sRNAs, which may unveil the roles of sRNAs in pertussis pathogenesis.