생명과학 기술의 예견: 2021년도

“Over the coming years, synthetic biology (redesign of nature’s greatest hits) will take even greater prominence in our world. This exciting technology has already led to some incredible products, from gene treatment for inherited vision loss (Luxturna), to cultivated fish and meat, and to enzymes which can break down plastic waste. Most of these products are in early stages and still need to mature, however they promise huge advantages both in pharmaceuticals and in other areas of our lives.”

“If 2020 has shown us anything, it is the importance of investing in the life sciences industry and having a more collaborative approach to innovation! In line with already emerging trends, I think the next few years will see more bioincubators springing up across Europe to give nascent biotech companies a boost to get started. In addition, I think we’ll see an increased collaboration between academia and industry, with more spin-off biotech companies arising from promising academic research projects, and academic facilities serving as screening hubs in partnership with biotech or pharma companies for profiling their more extensive compound libraries.”

“Big data has taken center stage in many aspects of society, including the life sciences. More recently we are seeing applications of big data together with artificial intelligence and deep learning particularly in the drug discovery field. Image-based phenotypic profiling based on cell painting assays is such an example. Already, this approach has played a key role in fast-tracking early drug screens, from promising compound hits for the treatment of rare genetic diseases to repurposing of drugs to treat COVID infections.”

“With the emergence of the COVID-19 global pandemic in 2020, we saw a significant increase in labs and companies willing to invest in high-throughput automated platforms. This was driven by the need to increase sample volumes and throughput while also increasing efficiency and effectiveness with less staff. The next step in the evolution of automated systems is the incorporation of machine learning and artificial intelligence. AI-driven solutions for early stage drug discovery has been growing steadily among biopharma leaders. The pandemic has accelerated this significantly, and I think we will see major artificial intelligence breakthroughs in the areas of drug target identification and validation as well as target-based phenotypic drug discovery in 2021. With the wealth of scientific information — from hit finding and expansion through lead design/optimization to ADME (Absorption, Distribution, Metabolism, and Excretion)/toxicity predictions — I foresee AI platforms having the ability to work with data points obtained from different processes. This includes high-content, low-throughput phenotypic assays as well as high-throughput screening, structure-based design, and traditional methods. From this, I would envision AI-controlled systems being able to probe very large chemical spaces and identify the most promising drug candidates, leading to faster breakthroughs and discoveries.”