TABASCO: A Fast, Simplified Model for Molecular Generation with Improved Physical Quality

TL;DR

TABASCO is a simplified, high-throughput molecular generation model that achieves state-of-the-art validity and faster inference by relaxing traditional symmetry assumptions and using a standard transformer architecture.

Contribution

It introduces a minimalist transformer-based model for molecular generation that simplifies architecture and improves speed while maintaining physical plausibility.

Findings

Achieves state-of-the-art validity on GEOM-Drugs benchmark.

Runs approximately 10 times faster than previous models.

Emerges rotational equivariance without explicit hard-coding.

Abstract

State-of-the-art models for 3D molecular generation are based on significant inductive biases, SE(3), permutation equivariance to respect symmetry and graph message-passing networks to capture local chemistry, yet the generated molecules still struggle with physical plausibility. We introduce TABASCO which relaxes these assumptions: The model has a standard non-equivariant transformer architecture, treats atoms in a molecule as sequences and reconstructs bonds deterministically after generation. The absence of equivariant layers and message passing allows us to significantly simplify the model architecture and scale data throughput. On the GEOM-Drugs benchmark TABASCO achieves state-of-the-art PoseBusters validity and delivers inference roughly 10x faster than the strongest baseline, while exhibiting emergent rotational equivariance despite symmetry not being hard-coded. Our work offers a blueprint for training minimalist, high-throughput generative models suited to specialised tasks such as structure- and pharmacophore-based drug design. We provide a link to our implementation at github.com/carlosinator/tabasco.