STAR-VAE: Latent Variable Transformers for Scalable and Controllable Molecular Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kwon, Bum Chul, Shapira, Ben, Raboh, Moshiko, Sethi, Shreyans, Murarka, Shruti, Morrone, Joseph A, Hu, Jianying, Suryanarayanan, Parthasarathy
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915597381533696
author Kwon, Bum Chul
Shapira, Ben
Raboh, Moshiko
Sethi, Shreyans
Murarka, Shruti
Morrone, Joseph A
Hu, Jianying
Suryanarayanan, Parthasarathy
author_facet Kwon, Bum Chul
Shapira, Ben
Raboh, Moshiko
Sethi, Shreyans
Murarka, Shruti
Morrone, Joseph A
Hu, Jianying
Suryanarayanan, Parthasarathy
contents The chemical space of drug-like molecules is vast, motivating the development of generative models that must learn broad chemical distributions, enable conditional generation by capturing structure-property representations, and provide fast molecular generation. Meeting the objectives depends on modeling choices, including the probabilistic modeling approach, the conditional generative formulation, the architecture, and the molecular input representation. To address the challenges, we present STAR-VAE (Selfies-encoded, Transformer-based, AutoRegressive Variational Auto Encoder), a scalable latent-variable framework with a Transformer encoder and an autoregressive Transformer decoder. It is trained on 79 million drug-like molecules from PubChem, using SELFIES to guarantee syntactic validity. The latent-variable formulation enables conditional generation: a property predictor supplies a conditioning signal that is applied consistently to the latent prior, the inference network, and the decoder. Our contributions are: (i) a Transformer-based latent-variable encoder-decoder model trained on SELFIES representations; (ii) a principled conditional latent-variable formulation for property-guided generation; and (iii) efficient finetuning with low-rank adapters (LoRA) in both encoder and decoder, enabling fast adaptation with limited property and activity data. On the GuacaMol and MOSES benchmarks, our approach matches or exceeds baselines, and latent-space analyses reveal smooth, semantically structured representations that support both unconditional exploration and property-aware generation. On the Tartarus benchmarks, the conditional model shifts docking-score distributions toward stronger predicted binding. These results suggest that a modernized, scale-appropriate VAE remains competitive for molecular generation when paired with principled conditioning and parameter-efficient finetuning.
format Preprint
id arxiv_https___arxiv_org_abs_2511_02769
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STAR-VAE: Latent Variable Transformers for Scalable and Controllable Molecular Generation
Kwon, Bum Chul
Shapira, Ben
Raboh, Moshiko
Sethi, Shreyans
Murarka, Shruti
Morrone, Joseph A
Hu, Jianying
Suryanarayanan, Parthasarathy
Machine Learning
Artificial Intelligence
Biomolecules
The chemical space of drug-like molecules is vast, motivating the development of generative models that must learn broad chemical distributions, enable conditional generation by capturing structure-property representations, and provide fast molecular generation. Meeting the objectives depends on modeling choices, including the probabilistic modeling approach, the conditional generative formulation, the architecture, and the molecular input representation. To address the challenges, we present STAR-VAE (Selfies-encoded, Transformer-based, AutoRegressive Variational Auto Encoder), a scalable latent-variable framework with a Transformer encoder and an autoregressive Transformer decoder. It is trained on 79 million drug-like molecules from PubChem, using SELFIES to guarantee syntactic validity. The latent-variable formulation enables conditional generation: a property predictor supplies a conditioning signal that is applied consistently to the latent prior, the inference network, and the decoder. Our contributions are: (i) a Transformer-based latent-variable encoder-decoder model trained on SELFIES representations; (ii) a principled conditional latent-variable formulation for property-guided generation; and (iii) efficient finetuning with low-rank adapters (LoRA) in both encoder and decoder, enabling fast adaptation with limited property and activity data. On the GuacaMol and MOSES benchmarks, our approach matches or exceeds baselines, and latent-space analyses reveal smooth, semantically structured representations that support both unconditional exploration and property-aware generation. On the Tartarus benchmarks, the conditional model shifts docking-score distributions toward stronger predicted binding. These results suggest that a modernized, scale-appropriate VAE remains competitive for molecular generation when paired with principled conditioning and parameter-efficient finetuning.
title STAR-VAE: Latent Variable Transformers for Scalable and Controllable Molecular Generation
topic Machine Learning
Artificial Intelligence
Biomolecules
url https://arxiv.org/abs/2511.02769