AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modeling

Andrei Rekesh, Miruna Cretu, Dmytro Shevchuk, Pietro Lio, Robert A. Batey, Mike Tyers, Michał Koziarski, Cheng-Hao Liu

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Structure-based 3D molecule generation · 8 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
use SynCoGen reaction-graph plus coordinate co-generation instead of atom and coordinate generation (SemlaFlow)3D molecule generation · SynSpace de novo generationSyntheseus solve rate (%): 36 -> 72Improved
use SynCoGen instead of SemlaFlow retrained on SynSpace (ablation)3D molecule generation · SynSpace de novo generationRDKit validity (%): 72.0 -> 96.7Improved
use SynCoGen instead of SemlaFlow retrained on SynSpace (ablation)3D molecule generation · SynSpace de novo generationPoseBusters validity (%): 60.3 -> 87.2Improved
use SynCoGen instead of SemlaFlow on diversity3D molecule generation · SynSpace de novo generationdiversity: 0.85 -> 0.78Hurt
use SynCoGen instead of SemlaFlow on novelty3D molecule generation · SynSpace de novo generationnovelty (%): 99.6 -> 93.9Hurt
add chemistry-sensitive graph constraints and self-conditioning (ablation)SynCoGen · SynSpace de novo generationgeneration qualityImproved
add inference annealing on coordinates (ablation)SynCoGen · samplingperformanceImproved
use SynCoGen instead of DiffLinker for fragment linkingfragment linking · fragment linking (3 targets)retrosynthesis solve rate (%): 0 -> 58-79Improved
use SynCoGen instead of ShEPhERD, CGFlow-ZS and SynFormer for pharmacophore-conditioned generationpharmacophore conditioning · 10 targets (PDB and LIT-PCBA)best docking score wins: best on 8/10 targets (best sample), 7/10 (median)Improved
train on larger SynSpace-L vocabulary (ablation)SynCoGen · SynSpace-L de novo generationvalidity and synthesizabilityNo clear effect

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