Machine Learning for Machines

Kebotix is a startup in Boston combining machine learning and robotics to accelerate the discovery of advanced materials.

ML at Kebotix


The process of discovering a new molecule in the material science field is not so different from trying on a million pair of shoes, only to find out that sandals would have been more appropriate. Whether searching for compounds to combat pollution or infection, material scientists spend much of their time analyzing new molecules with little promise. In an effort to speed up the process, MIT startup Kebotix has developed a “self-driving lab” that merges machine learning (ML) and robotics to rapidly prototype new materials1.

Although robots have been a part of large-scale chemistry labs for some time now, automated analysis has only recently become a reality due to the novel application of ML algorithms. Scientists at Kebotix have designed ML programs that work in tandem with their robotic lab partners, using feedback from the output of a previous experiment to modify the input of the next experiment. Essentially, the robotic arms can conduct tests unaided and tweak chemical parameters by “thinking” carefully about the results.

While the self-driving lab creates significant value for human chemists who would otherwise be analyzing test results most of the day, the management team at Kebotix must consider the trade-offs associated with automated material discovery. For example, Kebotix scientists have created a layer in their neural network “to weed out designs that stray too far from the original.”1 Though the layer keeps the range of possibilities sufficiently narrow for ease of iteration, it prevents the robot from taking creative, divergent paths to a discovery. To be clear, the tunnel vision of the robot-program pair may not limit its abilities at all but simply define where humans need to intervene in the discovery process.


Kebotix Management


Describing Kebotix as “the materials company of the 21st century,” CEO Jill S. Becker has set ambitious goals for the company’s growth over the next several years2. Though still in the early stages of VC funding, Kebotix has already secured a $5 million investment from One Way Ventures and counts Baidu, a leader in ML, among its investors. Interestingly, Kebotix has been operating in “stealth mode”—a reference to exceptionally disruptive projects conducted in secret within large corporations3. Based on its management structure of mostly scientists and engineers, Kebotix is still primarily focused on product development with less emphasis on commercialization in the short-term4.



Short-term and Medium-term Recommendation


            In the short-term, Kebotix is developing self-driven electronics a proof of concept for its robot-ML pairing1. The electronics industry is an ideal target due to the lack of regulatory hurdles that are present in pharmaceuticals and other discovery-intensive industries. When considering medium-term expansion into other classes of materials, Kebotix will undoubtedly have to understand whether the robot-ML pairing provides a unique competitive advantage. In the case of pharmaceuticals, the discovery process is fairly advanced and could be cost-prohibitive for the Kebotix team1. However, one area in which the company can provide a competitive advantage is coupling the pre-existing ML algorithms with molecular simulations developed in academic settings.

The area of simulation presents a powerful opportunity for Kebotix, given that the materials industry is founded upon many years of chemistry advancements. With the robot-ML pair knowing almost nothing about chemistry from the outset, the inclusion of simulation results in training data could vastly accelerate and improve the materials discovery process. MIT professor Alán Aspuru-Guzik, the Chief Visionary Officer of Kebotix, has stated in his research that virtual libraries contain hundreds of millions of candidates, but when used alone, they are limited by the search strategy employed to explore the range of chemical options5. Seeing that simulation and ML can experience the same setbacks, namely the limitations to new molecular discoveries, it is not immediately clear that the two technologies would be complementary. However, the rich data proffered by simulations would help scientists at Kebotix refine their current learning algorithms. In other words, the copious amounts of simulation data could reduce the learning time for Kebotix’s algorithms and potentially make the robot-ML technology competitive with human-led molecular design in other industries relying upon chemical discovery processes.


Open Questions


  1. What other trade-offs should Kebotix consider when fine-tuning its ML algorithms? Or does the feedback loop completely remove human bias?
  2. What is the role of the scientist/principal investigator in the new robot-ML model of material discovery?


(Word Count: 715)



1Will Knight, “A robot scientist will dream up new materials to advance computing and fight pollution” MIT Technology Review, November 7 2018,


2“Harvard Scientists Launch Breakthrough AI and Robotics Tech Company, Kebotix, for Rapid Innovation of Materials”, BusinessWire, November 7 2018,


3Paddy Miller and Thomas Wedell-Wedellsborg, “The Case for Stealth Innovation”, Harvard Business Review, March 2013 website, 2018,


5Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

Rafael Gómez-Bombarelli, Jennifer N. Wei, David Duvenaud, José Miguel Hernández-Lobato, Benjamín Sánchez-Lengeling, Dennis Sheberla, Jorge Aguilera-Iparraguirre, Timothy D. Hirzel, Ryan P. Adams, and Alán Aspuru-Guzik

ACS Central Science 2018 4 (2), 268-276

DOI: 10.1021/acscentsci.7b00572




Climate Connect: Bridging the gap in Utilities


3D Printed Cars – The Future of Auto Manufacturing or a Pipe Dream?

Student comments on Machine Learning for Machines

  1. Akash, this is a brilliant article about using research to drive further research! I think as investigators continue to rely on systems like this to tweak decisions in their iterative testing process, they can use their time to do more of the divergent thinking you talked about. My understanding of ML is that we are relying on machines to identify pathways to an acceptable convergence but in a field like this where sometimes divergent thinking provides solutions, I think there is always a role for humans. In addition, while Kebotix’s products would help reduce the impact of bias by choosing the best path forward rather than on intuition but at the same time, the researchers’ bias might be what would lead to a breakthrough!

  2. This is such a well-researched and interesting read, Akash! I think it’s fascinating how ML and robotics can be used in discovery and innovation. I have been a doubter of the ability for ML to prove truly useful in innovation for the limitation you presented, namely the the tunnel vision of the robot-program pair. However, after reading your essay I’m starting to think that ML can present data from repeated simulation for human to observe patterns more easily, and save human time for the more value-adding activities of speculation and creation. This touches on your question #2. On your question #1, I think it is difficult for ML to truly eliminate human bias because human judgment is required as the input, as well as for screening and interpretation of the output. Would love to hear your thoughts though. Also would love to hear about how you learned about this company. Thanks a gain!

  3. I think it definitely will not remove people out of the loop. Fundamentally, human still needs to make the decision as to what materials combination to test with, what material structure to test. This approach can further reduce human supervision but will never replace the role of human in this processes. Thus it is inevitable the direction and objective of the test will still contain human bias and it makes time to scientists to focus on noval ideas and application that requires more creativity.

Leave a comment