[HTML][HTML] Adaptive machine learning for protein engineering

BL Hie, KK Yang - Current opinion in structural biology, 2022 - Elsevier
Abstract Machine-learning models that learn from data to predict how protein sequence
encodes function are emerging as a useful protein engineering tool. However, when using …

In vitro continuous protein evolution empowered by machine learning and automation

T Yu, AG Boob, N Singh, Y Su, H Zhao - Cell Systems, 2023 - cell.com
Directed evolution has become one of the most successful and powerful tools for protein
engineering. However, the efforts required for designing, constructing, and screening a large …

Biological sequence design with gflownets

M Jain, E Bengio, A Hernandez-Garcia… - International …, 2022 - proceedings.mlr.press
Abstract 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 …

Sample efficiency matters: a benchmark for practical molecular optimization

W Gao, T Fu, J Sun, C Coley - Advances in neural …, 2022 - proceedings.neurips.cc
Molecular optimization is a fundamental goal in the chemical sciences and is of central
interest to drug and material design. In recent years, significant progress has been made in …

Accelerating bayesian optimization for biological sequence design with denoising autoencoders

S Stanton, W Maddox, N Gruver… - International …, 2022 - proceedings.mlr.press
Bayesian optimization (BayesOpt) is a gold standard for query-efficient continuous
optimization. However, its adoption for drug design has been hindered by the discrete, high …

Gflownets for ai-driven scientific discovery

M Jain, T Deleu, J Hartford, CH Liu… - Digital …, 2023 - pubs.rsc.org
Tackling the most pressing problems for humanity, such as the climate crisis and the threat
of global pandemics, requires accelerating the pace of scientific discovery. While science …

Reinforced genetic algorithm for structure-based drug design

T Fu, W Gao, C Coley, J Sun - Advances in Neural …, 2022 - proceedings.neurips.cc
Abstract Structure-based drug design (SBDD) aims to discover drug candidates by finding
molecules (ligands) that bind tightly to a disease-related protein (targets), which is the …

Differentiable scaffolding tree for molecular optimization

T Fu, W Gao, C **ao, J Yasonik, CW Coley… - arxiv preprint arxiv …, 2021 - arxiv.org
The structural design of functional molecules, also called molecular optimization, is an
essential chemical science and engineering task with important applications, such as drug …

Toward real-world automated antibody design with combinatorial Bayesian optimization

A Khan, AI Cowen-Rivers, A Grosnit, PA Robert… - Cell Reports …, 2023 - cell.com
Antibodies are multimeric proteins capable of highly specific molecular recognition. The
complementarity determining region 3 of the antibody variable heavy chain (CDRH3) often …

Group SELFIES: a robust fragment-based molecular string representation

AH Cheng, A Cai, S Miret, G Malkomes, M Phielipp… - Digital …, 2023 - pubs.rsc.org
We introduce Group SELFIES, a molecular string representation that leverages group tokens
to represent functional groups or entire substructures while maintaining chemical robustness …