AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

ICML 2022 · Probabilistic and scientific modeling › Bayesian optimization · approach: Local and high-dimensional Bayesian optimization · 22 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use LaMBO instead of genetic optimizerssequence design optimization · Bigrams, logP + QED, DRD3 docking + SA, Stability + SASArelative hypervolume improvementHelped
use DAE-generated proposals instead of uniform mutation proposals (ablation)model-based GA + MTGP + NEHVI · Bigrams, logP + QED, DRD3 docking + SA, Stability + SASArelative hypervolume improvementHelped
optimize DAE proposals by gradient descent on the query loss (ablation)LaMBO · Bigramsrelative hypervolume improvementHelped
add proposal entropy penalty (ablation)LaMBO · Bigramsrelative hypervolume improvementHurt
use NEHVI instead of averaged normalized objectives (ablation)LaMBO · Stability + SASAhypervolume: 1.51 -> 1.57Helped
use LaMBO rather than LSBOsingle-objective sequence optimization · penalized logPobjective value: 27.84 -> 50Helped
optimize fluorescent protein stability and SASA with LaMBORFP variants · in vitro protein designnumber of ancestor proteins with discovered non-dominated variants: three of the fiveHelped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy