Engineering Biology by Design
Engineering biology is at present one big revolution. We are witnessing an exciting singularity moment where molecular biology, biotechnology and systems and control engineering are converging into a promising; novel discipline. In the last decade, I had the privilege of becoming part of that revolution; looking forward to the burgeoning field of synthetic biology.
I work on intelligent biodesign automation through reverse engineering biology. We automate flows for synbio planner agile designs. Our mission is to foster sustainable industrial biotechnology of bio-based compounds (biomaterials, pharmaceuticals, next-generation chemicals) through the principles of control engineering and machine learning. I envision building artificial intelligence assistants for bionics systems; from biosensors to bio-inspired robotics.
I believe that the field of machine learning is at the moment exponentially exploding thanks to the wide availability of more powerful, scalable and efficient algorithms, as well as community-driven open source tools. Deep learning and tensor graph learning machines are certainly becoming more widespread as we see a constant inflow of innovative solutions dealing with complex problems. Machine learning technology is in constant development in pair with the increasingly bigger datasets that we generate. The main challenge is how to efficiently extract information and how to learn from large continuous data streams. In biotechnology, the trend is motivated by a synthetic biology bottom-up approach generating large amounts of genomics, transcriptomics, proteomics, metabolomics and other “omics” data. Such big data need to be digested and what we seek is to learn predictive models from these data that can be related to macroscopic phenomena, for instance the challenge of relating the production of some valuable chemical to the concerted behaviour of millions of bacteria controlled by millions of small machine-like proteins.