The Agile BioFoundry and Lygos, Inc. are joining forces to generate the largest multi-omics dataset for guiding the development of organic acids. Over the course of the project, scientists will produce more than 500,000 data points from a series of experiments. ABF is now using its artificial neural networks to train machine learning algorithms and provide actionable recommendations to help optimize strain performance, increase operational efficiencies and enhance production.
Machine Learning Takes on Synthetic Biology: Algorithms Can Bioengineer Cells for You
Engineering biological systems to specification–for example, designing a microbe to produce a cancer-fighting agent–requires a detailed mechanistic understanding of how all the parts of a cell work. Typically, this knowledge is acquired through years of painstaking work and a fair amount of trial and error. But Berkeley Lab scientists have created an Automated Recommendation Tool (ART) that adapts machine learning algorithms to the needs of synthetic biology to guide development systematically. With a limited set of training data, the algorithms are able to predict how changes in a cell’s DNA or biochemistry will affect its behavior, then make recommendations for the next engineering cycle along with probabilistic predictions for attaining the desired goal. The work was led by Hector Garcia Martin, a researcher in Berkeley Lab’s Biological Systems and Engineering (BSE) Division and Tijana Radivojevic, a BSE data scientist. In a pair of papers recently published in the journal Nature Communications, they presented the algorithm and demonstrated its capabilities.
Read more in the Berkeley Lab News Center.
Using Machine Learning to Estimate COVID-19’s Seasonal Cycle
A cross-disciplinary team of Berkeley Lab scientists with expertise in climate modeling, data analytics, machine learning, and geospatial analytics is launching a project to determine if the novel coronavirus might be seasonal. The team will apply machine-learning methods to a plethora of health and environmental datasets, combined with high-resolution climate models and seasonal forecasts.
Advancing Watershed Understanding through Exascale Simulation and Machine Learning
ExaSheds is a new project led by Berkeley Lab PI Carl Steefel of the Earth and Environmental Science Area (EESA) and Oak Ridge National Lab co-PI Scott Painter. It represents the first systematic effort to leverage powerful machine learning and exascale computing, applied to ever-larger and more-complex data obtained from watershed field observations, to gain a predictive understanding of watershed behavior. The project is funded by DOE Biological and Environmental Research and will initially take advantage of datasets being collected at the East River, Colorado watershed site, which has been developed as part of Berkeley Lab’s DOE Watershed Function Science Focus Area (SFA). The interdisciplinary research team includes Environmental Genomics and Systems Biology (EGSB) Division co-deputy Ben Brown, as well as partners at Lawrence Livermore and Pacific Northwest National Labs.
Read more from EESA.
New Machine Learning Method Sees the Forests and the Trees
While it may be the era of supercomputers and big data, without smart methods to mine all that data, it’s only so much digital detritus. Now researchers at Berkeley Lab and UC Berkeley have come up with a novel machine learning method that enables scientists to derive insights from systems of previously intractable complexity in record time.
Was this page useful?

