[Sds-seminars] FW: S&DS Virtual Seminar, Mengdi Wang, 10/17 @ 4pm-5pm, "Thompson Sampling-Guided Directed Evolution for Sequence Optimization"

[elizavette.torres at yale.edu]

 <https://statistics.yale.edu/>     <https://statistics.yale.edu/>
Department of Statistics and Data Science

 <https://statistics.yale.edu/seminars/mengdi-wang> Mengdi Wang, Princeton
University



Date: Monday, October 17, 2022

Talk Time: 4:00PM to 5:00PM

Zoom meeting link:
https://yale.zoom.us/j/92411077917?pwd=aXhnTnFGRXFoaTVDczNjeFFKeWpTQT09  /
Password: 24











Title: Thompson Sampling-Guided Directed Evolution for Sequence Optimization



Information and Abstract:

Directed Evolution (DE), a landmark wet-lab method originated in 1960s,
enables discovery of novel protein designs via evolving a population of
candidate sequences. Recent advances in biotechnology has made it possible
to collect high-throughput data, allowing the use of machine learning to map
out a protein’s sequence-to-function relation. There is a growing interest
in machine learning-assisted DE for accelerating protein optimization. Yet
the theoretical understanding of DE, as well as the use of machine learning
in DE, remains limited.
In this paper, we connect DE with the bandit learning theory and make a
first attempt to study regret minimization in DE. We propose a Thompson
Sampling-guided Directed Evolution (TS-DE) framework for sequence
optimization, where the sequence-to-function mapping is unknown and querying
a single value is subject to costly and noisy measurements. TS-DE updates a
posterior of the function based on collected measurements. It uses a
posterior-sampled function estimate to guide the crossover recombination and
mutation steps in DE. In the case of a linear model, we show that TS-DE
enjoys a Bayesian regret of order $\tilde
O(d^{2}\sqrt{MT})$\footnote{$\tilde O(\cdot)$ ignores the logarithmic
terms.}, where $d$ is feature dimension, $M$ is population size and $T$ is
number of rounds. This regret bound is nearly optimal, confirming that
bandit learning can provably accelerate DE. It may have implications for
more general sequence optimization and evolutionary algorithms.



3:30pm -  Pre-talk meet & greet Zoom Link: :
<https://yale.zoom.us/j/92411077917?pwd=aXhnTnFGRXFoaTVDczNjeFFKeWpTQT09>
https://yale.zoom.us/j/92411077917?pwd=aXhnTnFGRXFoaTVDczNjeFFKeWpTQT09
Password: 24

Join from PC, Mac, Linux, iOS or Android:
<https://yale.zoom.us/j/92411077917?pwd=aXhnTnFGRXFoaTVDczNjeFFKeWpTQT09>
https://yale.zoom.us/j/92411077917?pwd=aXhnTnFGRXFoaTVDczNjeFFKeWpTQT09
Password: 24
Or Telephone：203-432-9666 (2-ZOOM if on-campus) or 646 568 7788
Meeting ID: 924 1107 7917







For more details and upcoming events visit our website at
<http://statistics.yale.edu/> http://statistics.yale.edu/.


Department of Statistics and Data Science


Yale University
24 Hillhouse Avenue
New Haven, CT 06511

t 203.432.0666
f 203.432.0633





-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221017/2182d889/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.jpg
Type: image/jpeg
Size: 2925 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221017/2182d889/attachment.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.jpg
Type: image/jpeg
Size: 19009 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221017/2182d889/attachment-0001.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image003.jpg
Type: image/jpeg
Size: 4049 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221017/2182d889/attachment-0002.jpg>