PackFlow: Generative Molecular Crystal Structure Prediction via Reinforcement Learning Alignment

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Subramanian, Akshay, Pan, Elton, Nam, Juno, Weiler, Maurice, Qu, Shuhui, Park, Cheol Woo, Jaakkola, Tommi S., Olivetti, Elsa, Gomez-Bombarelli, Rafael
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914344554463232
author Subramanian, Akshay
Pan, Elton
Nam, Juno
Weiler, Maurice
Qu, Shuhui
Park, Cheol Woo
Jaakkola, Tommi S.
Olivetti, Elsa
Gomez-Bombarelli, Rafael
author_facet Subramanian, Akshay
Pan, Elton
Nam, Juno
Weiler, Maurice
Qu, Shuhui
Park, Cheol Woo
Jaakkola, Tommi S.
Olivetti, Elsa
Gomez-Bombarelli, Rafael
contents Organic molecular crystals underpin technologies ranging from pharmaceuticals to organic electronics, yet predicting solid-state packing of molecules remains challenging because candidate generation is combinatorial and stability is only resolved after costly energy evaluations. Here we introduce PackFlow, a flow matching framework for molecular crystal structure prediction (CSP) that generates heavy-atom crystal proposals by jointly sampling Cartesian coordinates and unit-cell lattice parameters given a molecular graph. This lattice-aware generation interfaces directly with downstream relaxation and lattice-energy ranking, positioning PackFlow as a scalable proposal engine within standard CSP pipelines. To explicitly steer generation toward physically favourable regions, we propose physics alignment, a reinforcement learning post-training stage that uses machine-learned interatomic potential energies and forces as stability proxies. Physics alignment improves physical validity without altering inference-time sampling. We validate PackFlow's performance against heuristic baselines through two distinct evaluations. First, on a broad unseen set of molecular systems, we demonstrate superior candidate generation capability, with proposals exhibiting greater structural similarity to experimental polymorphs. Second, we assess the full end-to-end workflow on two unseen CSP blind-test case studies, including relaxation and lattice-energy analysis. In both settings, PackFlow outperforms heuristics-based methods by concentrating probability mass in low-energy basins, yielding candidates that relax into lower-energy minima and offering a practical route to amortize the relax-and-rank bottleneck.
format Preprint
id arxiv_https___arxiv_org_abs_2602_20140
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PackFlow: Generative Molecular Crystal Structure Prediction via Reinforcement Learning Alignment
Subramanian, Akshay
Pan, Elton
Nam, Juno
Weiler, Maurice
Qu, Shuhui
Park, Cheol Woo
Jaakkola, Tommi S.
Olivetti, Elsa
Gomez-Bombarelli, Rafael
Chemical Physics
Organic molecular crystals underpin technologies ranging from pharmaceuticals to organic electronics, yet predicting solid-state packing of molecules remains challenging because candidate generation is combinatorial and stability is only resolved after costly energy evaluations. Here we introduce PackFlow, a flow matching framework for molecular crystal structure prediction (CSP) that generates heavy-atom crystal proposals by jointly sampling Cartesian coordinates and unit-cell lattice parameters given a molecular graph. This lattice-aware generation interfaces directly with downstream relaxation and lattice-energy ranking, positioning PackFlow as a scalable proposal engine within standard CSP pipelines. To explicitly steer generation toward physically favourable regions, we propose physics alignment, a reinforcement learning post-training stage that uses machine-learned interatomic potential energies and forces as stability proxies. Physics alignment improves physical validity without altering inference-time sampling. We validate PackFlow's performance against heuristic baselines through two distinct evaluations. First, on a broad unseen set of molecular systems, we demonstrate superior candidate generation capability, with proposals exhibiting greater structural similarity to experimental polymorphs. Second, we assess the full end-to-end workflow on two unseen CSP blind-test case studies, including relaxation and lattice-energy analysis. In both settings, PackFlow outperforms heuristics-based methods by concentrating probability mass in low-energy basins, yielding candidates that relax into lower-energy minima and offering a practical route to amortize the relax-and-rank bottleneck.
title PackFlow: Generative Molecular Crystal Structure Prediction via Reinforcement Learning Alignment
topic Chemical Physics
url https://arxiv.org/abs/2602.20140