How the Science Labs of Today Are Integrating the Tools of Tomorrow
Science labs might have the reputation as being at the forefront of technology adoption, but they have actually been slow to adopt automation in recent years. Researchers would rather spend their money on other equipment and supplies, and an endless supply of grad students who need to learn lab techniques, makes automation less of a priority. However, as prices come down, the benefits in increased accuracy are likely to change researchers’ minds.
This is not to say that automation is new to science labs. A lot of research requires repeated steps, such as sucking up small amounts of fluid and placing it into test tubes. If a scientist must do this several times to replicate an experiment, it would be better—and more accurate—to have a machine do it. To a limited degree, science labs do have such technology. At the same time, many advances are being seen in factories and even fast food restaurants that are not being found in science labs.
A few science labs are catching up, using robots and deep learning (artificial intelligence, or AI) to help them with their experiments. For example, Imperial College London, in the United Kingdom, will be developing a facility using robots to set up experiments, automation to conduct the analyses, and deep learning to discover how to conduct future experiments.
At the same time, deep learning will allow researchers from physics to biology to conduct better and more innovative experiments. More complex sciences such as biology could certainly benefit from deep learning, as very complex patterns may be hidden from human researchers, but become obvious to AI. Further, the huge amount of biological data—from DNA sequences to neurological mapping—makes data analysis using practically anything but deep learning nearly impossible.
Deep learning would allow a molecular biology lab, for example, to use AI to analyze stretches of DNA for new proteins, or to find common features among proteins, pointing to an evolutionary common ancestor for those proteins. AI could also be used to create new kinds of proteins, new synthetic materials, and so on, creating a number of new technological advances in materials science, organic chemistry, and biotechnology.
The combination of robots able to make more precise measurements and conduct more accurate experiments, more automated analysis at the moment the experiment ends, and deep learning to help in the planning of future experiments has the potential to truly revolutionize the way science is done. This will accelerate scientific discoveries.
The potential for the expansion of basic scientific knowledge, the creation of new technologies, and new medical discoveries are endless.
For the latest news, videos, and podcasts in the Science Industry, be sure to subscribe to our industry publication.
Follow us on social media for the latest updates in B2B!