Main menu


Biotechnology:Discovery of Enzymes by Artificial Intelligence

Biotechnology:Discovery of Enzymes by Artificial Intelligence

Biotechnology: Discovery of Enzymes by Artificial Intelligence

Associate Professor Christopher J. Vavricka, Graduate School of Science, Technology and Innovation, Kobe University, Assistant Professor Shunsuke Takahashi, Faculty of Science and Technology, Tokyo Electric University, Michihiro Araki, Deputy Director, AI Health and Pharmaceutical Research Center, Institute of Pharmaceutical Sciences, Health and Nutrition, Kobe University A research group led by Professor Masahisa Hasunuma of the Advanced Bioengineering Research Center has succeeded in producing microorganisms for plant-derived pharmaceutical raw materials by developing a machine learning prediction model capable of discovering unknown enzymes and linking it with metabolic engineering. In the future, it is expected to accelerate the bioproduction of various useful substances, functional materials, and general-purpose chemicals. The results of this research were published in the British scientific journal Nature Communications on March 16 .With the progress of synthetic biology in recent years, microbial fermentation production of plant-derived pharmaceutical raw materials is expected.

When targeting BIA, which is widely used as a raw material for analgesics, the problem was that some of the enzymes that make up the metabolic pathway were unknown.

To solve the problem of enzyme discovery, we developed  by biotechology a machine learning prediction model and linked it to the DBTL workflow of design ( D esign) -construction ( B uild) -evaluation ( T est) -learning ( L earn).

He discovered an unknown enzyme (missing link) and succeeded in producing BIA by Escherichia coli.

The AI ​​x bio method developed in this research can be applied to the production of various pharmaceutical raw materials, functional materials, and general-purpose chemicals, and is expected to contribute to the SDGs through environment-friendly bioproduction.

 biotechnology: Research background

Many of the world's Biotechnmedicines are made from compounds extracted from plants. Since these compounds (raw materials for pharmaceutical products) are abundant in plants, large-scale cultivation and industrial treatment are required to obtain them, which has brought about an environmental and economic burden. Benzylisoquinoline alkaloids (BIA) are widely used as raw materials for analgesics, and this situation has been a long-standing problem in mass production.

On the other hand, recent progress in biotechnology has been remarkable, and by introducing and expressing plant-derived genes in microorganisms, it is possible to implement the metabolic pathways of plants in microorganisms and produce useful substances that are not originally produced by microorganisms. It has become. By culturing a large amount of microorganisms that are easy to cultivate, useful substances are efficiently fermented and produced, which can reduce the burden on the environment and economy of the production process. Such a method is called a synthetic biology approach, and is a new trend in biotechnology-based manufacturing (bioproduction). BIA is also expected to apply this approach, but there were technical challenges.

In order to produce BIA by microorganisms, it is necessary to construct a long metabolic pathway consisting of many enzymatic reactions, but the problem was that some of the plant-derived enzymes were unknown. This "missing link" is a problem that often occurs in bioproduction using synthetic biology approaches, and in many cases it has traditionally been impossible to solve even with the great amount of time and effort of molecular biologists. In this research, by using biotechnology, we have developed a machine learning algorithm that predicts the enzyme reaction, and succeeded in discovering the enzyme required for BIA production by applying the prediction model.

 Biotechnology: Research content 

Biotechnology: Research content
In this biotechnology  research, we constructed a DBTL workflow consisting of design, build, test, and learning in order to search for unknown enzymes (Fig. 1). In this new concept, chemical reactions are designed by information science, recombinant enzymes are produced by genetic engineering, enzyme functions are evaluated by metabolic engineering, and enzymes are searched by machine learning. By turning this cycle, the enzymes that catalyze unknown reactions are narrowed down, and finally they are discovered.

This biotechnology study develops a machine learning algorithm that predicts enzyme reactions and builds a new prediction model by plugging it into the DBTL workflow, which produces an enzyme that produces precursor chemicals (BIA) for opioid analgesics. I found. The breakthrough of this research lies in the development of real-time machine learning, in which, in addition to the data processing of the design step, a predictive model of AI is established using the data newly acquired in the laboratory experiment. This is the first biotechology study to prove its effectiveness.

Biotechnology: the next deployment

We aim for mass production of BIA using the obtained enzyme. The AI ​​x bio method developed in this biotechnology research can be applied to the production of various pharmaceutical raw materials, functional materials, and general-purpose chemicals (bioproduction), and makes a great contribution to SDGs through environmentally friendly processes. Can be expected.

Biotechnology: Acknowledgments

This biotechnology's research is a research and development project of the National Research and Development Corporation New Energy and Industrial Technology Development Organization "Development of high-performance product production technology using organisms such as plants / Development of high-performance product production technology using microorganisms" and "Realization of carbon recycling" It was carried out with the support of "Development of bio-derived product production technology to accelerate the development of new enzyme resources from the database space".