Timezone: »

 
Poster
Biological Sequence Design with GFlowNets
Moksh Jain · Emmanuel Bengio · Alex Hernandez-Garcia · Jarrid Rector-Brooks · Bonaventure Dossou · Chanakya Ekbote · Jie Fu · Tianyu Zhang · Michael Kilgour · Dinghuai Zhang · Lena Simine · Payel Das · Yoshua Bengio

Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #115
in Poster Session 2 »

Design of de novo biological sequences with desired properties, like protein and DNA sequences, often involves an active loop with several rounds of molecule ideation and expensive wet-lab evaluations. These experiments can consist of multiple stages, with increasing levels of precision and cost of evaluation, where candidates are filtered. This makes the diversity of proposed candidates a key consideration in the ideation phase. In this work, we propose an active learning algorithm leveraging epistemic uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candidate solutions, with the objective to obtain a diverse batch of useful (as defined by some utility function, for example, the predicted anti-microbial activity of a peptide) and informative candidates after each round. We also propose a scheme to incorporate existing labeled datasets of candidates, in addition to a reward function, to speed up learning in GFlowNets. We present empirical results on several biological sequence design tasks, and we find that our method generates more diverse and novel batches with high scoring candidates compared to existing approaches.

Keywords: APP: Chemistry and Drug Discovery · DL: Algorithms · MISC: Online Learning, Active Learning and Bandits

Author Information

Moksh Jain (MILA / University of Montreal)
Emmanuel Bengio (McGill University)
Alex Hernandez-Garcia (Mila - Quebec AI Institute)
Jarrid Rector-Brooks (Mila, Universite de Montreal)
Bonaventure Dossou (Mila, Google Research)
Chanakya Ekbote (Mila)
Jie Fu (Mila, University of Montreal)
Tianyu Zhang (Mila)
Michael Kilgour (New York University)
Dinghuai Zhang (Mila, Meta)
Lena Simine (McGill University)
Payel Das (IBM Research AI)
Yoshua Bengio (Mila - Quebec AI Institute)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors