The paper proposes a three‑stage training pipeline that begins with procedural pretraining on abstract, procedurally generated data, followed by molecular pretraining on SMILES, and finally downstream fine‑tuning for molecular property prediction. Experiments show that procedural pretraining improves downstream performance—e.g., a 4.8% error reduction on Lipophilicity—especially when labeled data are scarce, and that the benefit peaks at an intermediate procedural training budget. Analysis indicates that transferable knowledge resides mainly in attention layers, while feed‑forward layers may over‑specialize.
By Moritz Friedemann, Zachary Shinnick, Philip Torr, Bruno Andreis
The paper introduces MolPAIR, a framework that enhances tabular foundation models (TFMs) for predicting molecular properties under structural shifts by incorporating molecule-level and molecular-pair contexts without task‑specific parameter updates. MolPAIR refines initial predictions from a global TFM by using a second frozen TFM to predict differences in prediction errors between a query molecule and labeled reference molecules. Experiments on 58 MoleculeACE and Polaris tasks show that MolPAIR improves performance on 46 tasks across multiple molecular representations and TFM backbones, demonstrating that explicit molecular comparisons strengthen tabular in‑context learning for structural generalization.
By Jinmo Lee, Dooho Lee, Minho Jeong, Jaemin Yoo
Monroe is a new molecular foundation model that improves upon existing models by pre‑training on over 81 million molecules from the PM6 quantum chemistry dataset, enhancing stereochemistry representation, and introducing novel training losses such as conformer denoising and embedding decorrelation. It also incorporates a prior‑data‑fitted model (TabPFN) for downstream in‑context prediction and demonstrates superior performance on Polaris benchmarks and activity cliff tests. Ablation studies show that the PFN‑based downstream approach can upgrade other models, producing state‑of‑the‑art variants MiniMol_PFN and CheMeleon_PFN.
By Blazej Banaszewski, Andrew W. Fitzgibbon
arXiv:2606. 31126v1 Announce Type: new Abstract: Predicting biomolecular properties from limited labeled data is a central bottleneck in protein engineering and small-molecule design.
By Davy Guan, Lu Zhang, Asiri Wijesinghe, Allen Zhu, He Zhao, Helen Power, F. Hafna Ahmed, Andrew Warden, Cheng Soon Ong, Daniel M. Steinberg
arXiv:2610.19906v1 Announce Type: new
Abstract: LLMs have achieved strong performance on chemical prediction benchmarks. However, existing evaluation methods typically provide target entity identity...
By Yanyi Su, Yu Zeng, Hongshuai Wang, Chenyan Wang, Zhifeng Gao, Xiaohui Yang
The study evaluates whether a portfolio of compact, semantically named descriptor blocks can match the performance of a 2048‑dimensional CheMeleon embedding in low‑data molecular assays. Using a fixed 11‑dimensional physicochemical base and greedily adding provenance‑screened blocks, the portfolio achieves a mean test AUC of 0.762 across nine ADME/Tox assays, comparable to CheMeleon’s 0.764 and better than Mordred’s 0.756. The results meet a predeclared pooled parity threshold but not all per‑assay thresholds, and further analysis confirms the competitiveness of the auditable representation while highlighting unresolved assay‑level differences.
By Yiqi Yao, Miquel Duran-Frigola
AC-JEPA is a plug‑in for supervised fine‑tuning that predicts masked intermediate states in both directions of a cross‑modal translation task, combining a joint‑embedding objective with causal token‑level supervision. It is designed to be robust to imperfect paired data by learning from continuous latent targets derived from pseudo‑labels, rather than hard categorical supervision. In optical chemical structure recognition, AC‑JEPA outperforms plain supervised fine‑tuning, achieving 76.07 % accuracy on clean pairs and 80.23 % when self‑training with pseudo‑labels, whereas SFT alone drops to 63.47 % under the same conditions.
By Chaofei Hong, Ziyang Chen, Baochen Wang, Christina Yi Jin, Qing Zhang
arXiv:2608. 10595v1 Announce Type: cross Abstract: Proteolysis-targeting chimeras (PROTACs) induce protein degradation by recruiting a target protein to an E3 ubiquitin ligase, making degradation a joint outcome of the degrader molecule and its biological context.
By Dong Xu, Zhangfan Yang, Jiantao Wu, Zexuan Zhu, Jianqiang Li, Junkai Ji
The paper introduces GRACE, a 3D collision cross section (CCS) predictor that incorporates geometric residual adduct conditioning via early fusion. GRACE adapts a pretrained molecular geometry encoder with an adduct token and low‑rank attention adapters, achieving the lowest mean percentage differences on random, scaffold, and adduct‑sensitive splits of a curated dataset of over 9,000 experimental CCS records. Diagnostic analyses attribute its performance to residual learning that removes the dominant mass‑CCS trend and to early fusion that enhances adduct‑sensitive prediction.
By Parthasarathy Suryanarayanan, Susanta Das, Shreyans Sethi, Kenneth M. Merz, Jr., Joseph A. Morrone
arXiv:2603. 25857v3 Announce Type: replace Abstract: The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction.
By Matthias Busch, Marius Tacke, Sviatlana V. Lamaka, Mikhail L. Zheludkevich, Christian J. Cyron, Christian Feiler, Roland C. Aydin
arXiv:2606. 09664v1 Announce Type: new Abstract: Bayesian optimization (BO) is a central tool for sample-efficient design, and latent-space Bayesian optimization (LSBO) extends it to structured objects such as molecules and proteins.
By Tuan A. Vu, Harri L\"ahdesm\"aki, Julien Martinelli
arXiv:2603.03517v2 Announce Type: replace-cross
Abstract: General-purpose large language models (LLMs) that rely on in-context learning do not reliably deliver the scientific understanding and perfor...
By Maksim Kuznetsov, Zulfat Miftahutdinov, Rim Shayakhmetov, Mikolaj Mizera, Roman Schutski, Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Thomas MacDougall, Mathieu Reymond, Mihir Bafna, Kaeli Kaymak-Loveless, Eugene Babin, Maxim Malkov, Mathias Lechner, Ramin Hasani, Alexander Amini, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov