AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

A Model to Search for Synthesizable Molecules

NeurIPS 2019 · Probabilistic and scientific modeling › Molecules and proteins · approach: Structure-based 3D molecule generation · 71 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
Generate products by selecting available reactants and applying the Molecular TransformerMolecule Chef · USPTO-derived training setvalidity (%): 85.86 -> 99.05; 100.00Mixed
Generate products by selecting available reactants and applying the Molecular TransformerMolecule Chef · USPTO-derived training setnovelty (%): 93.37 -> 89.11; 95.88Hurt
Use gradient steps from a learned QED predictor instead of a random walkMolecule Chef latent-space optimization · Local optimization of QEDbest QED scoreHelped
Use the reachable-product subset rather than products with out-of-vocabulary reactantsMolecule Chef retrosynthesis · USPTO test setcorrelation of reconstructed and original QEDHelped
Generate molecules through reactant selection and predicted reactions rather than direct CVAE or GVAE generationMolecule Chef · Qualitative random walks in latent spaceexpert-assessed chemical stability and safetyHelped

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