The paper reports a large-scale, compute-controlled study of Chemical Language Models (CLMs) involving over 30,000 experiments across different molecular representations, tokenizations, model sizes, datasets, and architectures. It finds clear scaling trends in pretraining loss but shows that these improvements do not translate into proportional gains in goal-directed molecular design, with chemical syntax saturating early while semantic properties develop more slowly. The authors release a new suite of models, NovoMolGen, that achieves state-of-the-art results in drug discovery tasks, highlighting a disconnect between representation learning and downstream design and calling for new pretraining paradigms that target chemical semantics.
By Roshan Balaji, Kamran Chitsaz, Quentin Fournier, Nirav Pravinbhai Bhatt, Sarath Chandar
arXiv:2607. 02212v1 Announce Type: cross Abstract: Aqueous solubility is a key property in early-stage drug discovery, but most predictive models merge physicochemical descriptors and molecular graph information into a single representation, obscuring whether a prediction is driven by global chemistry, molecular structure, or both.
By Sampreeti Bhattacharya, Arkaprava Roy
arXiv:2608. 10480v1 Announce Type: new Abstract: Large language models (LLMs) are widely applied across chemical tasks, such as molecular property prediction, which underpins drug discovery.
By Junwoo Park, Minyoung Shin, Cheol Soon Lee, Sujee Lee
arXiv:2609.37384v1 Announce Type: new
Abstract: Molecular representation learning is central to computer-aided drug discovery. Molecular graphs, SMILES strings, and 3D conformations provide complemen...
By Linqing Mo, Jiayu Zhou, Bin Chen
arXiv:2606. 11508v1 Announce Type: new Abstract: Accurate prediction of absorption, distribution, metabolism, and excretion (ADME) properties is critical to drug discovery, but remains challenging because ADME endpoints are noisy, interdependent, and often data-limited.
By Yifan Xue, Srimukh Prasad Veccham, Saee Paliwal, Tyler Shimko, Micha Livne
Large language models (LLMs) are widely applied across chemical tasks, such as molecular property prediction, which underpins drug discovery. Molecular LLMs represent a molecule through several modalities, notably a 1D SMILES sequence or a 2D molecular graph.
arXiv:2602. 04119v2 Announce Type: replace Abstract: The application of generative models for experimental drug discovery campaigns is severely limited by the difficulty of designing molecules de novo that can be synthesized in practice.
By Hyeonah Kim, Minsu Kim, Celine Roget, Dionessa Biton, Louis Vaillancourt, Yves V. Brun, Yoshua Bengio, Alex Hernandez-Garcia
arXiv:2608. 04257v1 Announce Type: new Abstract: Blood-brain barrier permeability (BBBP) prediction is a critical screening task in central nervous system drug discovery, where candidate molecules must be assessed for whether they can cross, or should be prevented from crossing, the blood-brain barrier.
By Marco Vieto Vega, Long D. Nguyen, Binh P. Nguyen
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
VINCENT is a post‑training framework that provides validated, chemically coherent explanations for drug synergy predictions by extracting atom‑pair evidence from attention and gradient signals, grouping them into motifs, and refining these motifs through repeated local perturbations. On a literature‑annotated subset of 25 drug pairs, VINCENT achieves a mean motif recall of 0.826, outperforming baselines (0.49–0.66). Across 71 test pairs, its validated interaction scores yield a TP/TN separation of 3.36, indicating more accurate recovery of literature‑supported molecular regions and better alignment with predictor behavior.
By Fan-Sheng Chuang, Xuchen Li, Yujing Bian, Kaixiong Zhou
arXiv:2607. 25322v1 Announce Type: new Abstract: Multimodal drug discovery enables drug representation learning beyond chemical structure by incorporating cellular responses such as gene expression and cell morphology.
By Jintao Huang, Lu Leng, Ziyuan Yang
arXiv:2606. 03435v1 Announce Type: new Abstract: Cell Painting combines multiplexed fluorescent staining, high-content imaging, and quantitative analysis to generate high-dimensional phenotypic readouts to support diverse downstream tasks such as mechanism-of-action (MoA) inference, toxicity prediction, and construction of drug-disease atlases.
By Yuxin Zhang, Yiyao Li, Ping Shu Ho, Simon See, Zhenqin Wu, Kevin Tsia