machine learning

Season 2, Episode 2: A New Era of Antibiotic Discovery with James Martin

First Authors: James Martin, Benjamin Bratton, Joseph Sheehan

Episode Summary: Bacteria are rapidly evolving ways to resist antibiotics, causing minor infections to become life-threatening events. Compounding the problem, new antibiotics have been incredibly challenging to develop and pharma is economically disincentivized to invest in finding them. James Martin and his colleagues Joseph Sheehan and Benjamin Bratton took on this challenge, developing an extremely potent antibiotic that targets multiple different classes of bacteria. James tells the story of identifying this antibiotic, understanding its potential, and pinpointing how its structure begets its function. Describing the state-of-the art CRISPR screens, proteomics, and machine learning methods they used, James calls for a new era of antibiotic discovery to meet the impending wave of superbugs.

About the Author

  • James Martin performed this work as a graduate student in Professor Zemer Getai’s lab at Princeton University.

  • James’s optimism and drive to understand a problem from all angles led him and his colleagues to develop one of the most potent antibiotics ever found.

Key Takeaways

  • Our arsenal of antibiotics will soon be worthless, as bacteria evolve ways to get around their killing effects.

  • Adding new antibiotics to this arsenal has been slow because they are challenging to discover and they have poor return on investment.

  • Synergizing a number of new biological tools available, like high throughput microscopy, CRISPR, and machine learning, new antibiotics can be developed and understood faster than ever before.

  • Applying this fresh take on antibiotic discovery, a novel drug is found that targets a wide-variety of bacteria and is difficult to evolve resistance to.

Translation

  • Moving this extremely potent compound to the clinic will require some smart biochemistry to make it a better drug.

  • The research of James and his colleagues demonstrates a paradigm shift in how antibiotic discovery pipelines are performed to more easily and rapidly find these new drugs.

Paper: A Dual-Mechanism Antibiotic Kills Gram-Negative Bacteria and Avoids Drug Resistance

Season 1, Episode 1: Low-N Protein Engineering with Surge Biswas

First Author: Surojit “Surge” Biswas

Episode Summary

Protein engineering has been dominated by two opposing paradigms; directed evolution, a massive screening technique, and rational design, a completely computational approach. Surge has fused these two paradigms by developing a machine learning technique that discovers an optimal protein design by training on a low number of engineered proteins. Here, Surge discusses how this hybrid method works, how it enabled the creation of better fluorophores and enzymes, and what this method will unlock next.

About the Author

  • Surge performed this work as a graduate student at Harvard in the lab of Professor George Church. George is one of the founding fathers of synthetic biology and the lab is known for developing high throughput methods to design, build, and test bioengineered parts.

  • As CEO and co-founder of Nabla Bio, Surge is now focused on pointing the algorithms and methods developed in his academic work toward building proteins that can improve human health or protect the environment.

Key Takeaways

  • Methods from natural language processing algorithms (like Siri or Alexa) are adapted to understand how nature builds proteins.

  • These machine learning algorithms distill fundamental structural, as well as  evolutionary and and biophysical properties about proteins.

  • Fusing these models with real world data enables us to make proteins with improved or novel functionality.

  • By checking how a few mutations (low-n) affect the function of a protein, Surge evolved proteins in a computer to make better fluorescent proteins and enzymes.

  • These models know a lot about proteins in general and can therefore be applied to a wide variety of tasks that improve human health and protect the environment.

Translation

  • This methodology dramatically reduces the time, cost, and labor of evolving proteins, making it a perfect tool to create commodity proteins.

  • Based on this technology, Surge co-founded Nabla Bio whose goal is to engineer supernatural proteins that enable biology to solve the world's biggest problems.

Paper: Low-N protein engineering with data-efficient deep learning. bioRxiV, 2020