Person:
Esvelt, Kevin

Profile Picture

Email Address

AA Acceptance Date

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

Esvelt

First Name

Kevin

Name

Esvelt, Kevin

Filters

2015 - 201912020 - 20211

Settings

Author's Publications: search.filters.isAuthorOfPublication.c63cf12b-3be0-4c8a-9675-e119692ba55e

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Publication
    Low-N Protein Engineering With Data-Efficient Deep Learning
    (Nature Publishing Group, 2021-04-07) Biswas, Surojit; Khimulya, Grigory; Alley, Ethan; Esvelt, Kevin; Church, George
    Protein engineering has enormous academic and industrial potential. However, it is limited by the lack of experimental assays that are consistent with the design goal and sufficiently high-throughput to find rare, enhanced variants. Here we introduce a machine learning-guided paradigm that can use as few as 24 functionally assayed mutant sequences to build an accurate virtual fitness landscape and screen ten million sequences via in silico directed evolution. As demonstrated in two dissimilar proteins, avGFP and TEM-1 β-lactamase, top candidates from a single round are diverse and as active as engineered mutants obtained from previous high-throughput efforts. By distilling information from natural protein sequence landscapes, our model learns a latent representation of “unnaturalness”, which helps to guide search away from nonfunctional sequence neighborhoods. Subsequent low-N supervision then identifies improvements to the activity-of-interest. Taken together, our approach enables efficient use of resource intensive high-fidelity assays without sacrificing throughput, and helps to accelerate engineered proteins into the fermenter, field, and clinic.
  • No Thumbnail Available
    Publication
    Safeguarding Gene Drive Experiments in the Laboratory
    (American Association for the Advancement of Science (AAAS), 2015-08-28) Akbari, Omar S.; Bellen, Hugo J.; Bier, Ethan; Bullock, Simon L.; Burt, Austin; Church, George; Cook, Kevin R.; Duchek, Peter; Edwards, Owain R.; Esvelt, Kevin; Gantz, Valentino M.; Golic, Kent G.; Gratz, Scott J.; Harrison, Melissa M.; Hayes, Keith R.; James, Anthony A.; Kaufman, Thomas C.; Knoblich, Juergen; Malik, Harmit S.; Matthews, Kathy A.; O'Connor-Giles, Kate M.; Parks, Annette L.; Perrimon, Norbert; Port, Fillip; Russell, Steven; Ueda, Ryu; Wildonger, Jill
    Gene drive systems promote the spread of genetic elements through populations by assuring they are inherited more often than Mendelian segregation would predict (see the figure). Natural examples of gene drive from Drosophila include sex-ratio meiotic drive, segregation distortion, and replicative transposition. Synthetic drive systems based on selective embryonic lethality or homing endonucleases have been described previously in Drosophila melanogaster (1–3), but they are difficult to build or are limited to transgenic populations. In contrast, RNAguided gene drives based on the CRISPR/Cas9 nuclease can, in principle, be constructed by any laboratory capable of making transgenic organisms (4). They have tremendous potential to address global problems in health, agriculture, and conservation, but their capacity to alter wild populations outside the laboratory demands caution (4–7). Just as researchers working with self-propagating pathogens must ensure that these agents do not escape to the outside world, scientists working in the laboratory with gene drive constructs are responsible for keeping them confined (4, 6, 7).