Recently, the team led by Huo Yixin from the School of Life Sciences at Beijing Institute of Technology published a research article titled "Design of Strictly Orthogonal Biosensors for Maximizing Renewable Biofuel Overproduction" in the top tier journal "Journal of Advanced Research" in Zone 1. This study developed a machine learning based design method to address the relationship between signal molecule promiscuity and industrial orthogonality. Taking the transcription factor BmoR as an example, this method successfully reduced the modification area of BmoR, greatly accelerating the speed of obtaining ideal mutants and providing a new paradigm for the rational design of highly specific tools in synthetic biology and biomanufacturing. This work is based on Beijing Institute of Technology as the primary communication unit, with 2020 doctoral student Wu Tong as the first author, and Associate

Professor Chen Zhenya and Professor Huo Yixin as co corresponding authors.

At present, transcription factor (TF) engineering relies on a combination of random mutations and high-throughput screening, and larger region mutations can to some extent disrupt the function of transcription factors. At the same time, the presence of some non functional mutants reduces the screening efficiency of effective mutants. Focusing the transformation on the functional areas that control the orthogonality, sensitivity, and detection range of signal molecules can effectively improve the rate of obtaining ideal mutants. Based on this, identifying these key regions is crucial for efficiently designing high-performance transcription factors. Artificial intelligence has driven advances in synthetic biology and metabolic engineering, particularly in the application of machine learning in protein and enzyme engineering. Combining high-throughput screening with machine learning can accelerate the evaluation of the performance of a large number of mutants, significantly reducing the workload and cost of experiments. Based on this, this study established a semi rational design strategy based on machine learning. By locating the key regions that affect the binding of BmoR with signal molecules, the semi rational design of BmoR was carried out, achieving strict specific response of BmoR to specific signal molecules

Source: Sensor Expert Network