AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

LIMO: Latent Inceptionism for Targeted Molecule Generation

Peter Eckmann, Kunyang Sun, Bo Zhao, Mudong Feng, Michael Gilson, Rose Yu

ICML 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Structure-based 3D molecule generation · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
Predict properties from the decoded molecular representation instead of directly from latent z (ablation)LIMO · QED and penalized logP maximizationoptimization score: penalized logP 6.52 -> 10.5; QED 0.910 -> 0.947Improved
Predict properties from decoded molecules rather than directly from latent z (ablation)LIMO · 1,000-molecule unseen test setr^2: 0.04 -> 0.38Improved
Replace the fully connected VAE encoder and decoder with 8-layer, 512 hidden dimension LSTMs (ablation)LIMO · QED maximizationmaximum QED: 0.3Hurt
Add a self-attention layer after the LSTM encoder (ablation)LIMO with LSTM encoder · Molecule generation performanceperformanceNo clear effect
Use LIMO rather than the strongest reported baselinePenalized logP maximization · Penalized logP maximization (top 1)penalized logP: 45.0 vs 10.5Hurt
Use LIMO rather than GCPNLogP targeting (-2.5 < logP < -2.0) · LogP targetingsuccess (%): 85.5 vs 10.4Hurt
Use LIMO rather than GCPN for logP targetingLogP targeting (-2.5 < logP < -2.0) · LogP targetingdiversity: 0.392 -> 0.914Improved
Apply LIMO for similarity-constrained p-logP maximization at δ=0.0 and δ=0.2Similarity-constrained p-logP optimization · δ=0.0 and δ=0.2p-logP improvement: δ=0.0: 7.0 ± 1.4 -> 10.1 ± 2.3; δ=0.2: 5.1 ± 1.8 -> 5.8 ± 2.6Improved
Apply LIMO for similarity-constrained p-logP maximization at higher similarity thresholdsSimilarity-constrained p-logP optimization · δ=0.4 and δ=0.6p-logP improvement: δ=0.4: LIMO 3.6 ± 2.3; δ=0.6: LIMO 1.8 ± 2.0No clear effect
Use LIMO rather than GCPN for docking-based affinity optimizationSingle-objective binding affinity maximization · ESR1K_D (nM): 6.4 -> 0.72Improved
Optimize binding affinity together with QED and SA instead of affinity aloneLIMO · ESR1 ligand generationdrug-likeness and synthesizabilityImproved
Use LIMO rather than GCPN for multi-objective ligand generationMulti-objective binding affinity optimization · ESR1 and ACAA1K_D (AutoDock-GPU, nM): ESR1: 810 -> 4.6; ACAA1: 8500 -> 28Improved

Later papers that compared with this method

1 later accepted paper reports LIMO as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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