Generating molecules with desired chemical properties is a crucial and promising area of research in drug discovery, as it has the potential to accelerate the identification of novel therapeutic compounds. Recent developments in diffusion models have showcased their remarkable generative capabilities, effectively handling continuous data modalities such as images and audio. However, when it comes to generating discrete data, particularly molecular representations like SMILES strings and molecular graphs, these models encounter significant challenges, especially in few-shot learning scenarios where only a limited number of samples are available. In this paper, we explore the potential of diffusion models for generating continuous representations of molecules-molecular images. Specifically, we propose ProtoDiff, a diffusion-based method that incorporates few-shot learning for molecular image generation. We frame molecular image generation as a few-shot controllable generation problem that extracts prototypes from a limited set of molecules to guide the generation process and introduces a novel sparsity regularization in the objective function of diffusion to emphasize the meaningful pixels of molecules, i.e., the limited pixels of the chemical bonds. We train and evaluate ProtoDiff on the ChEMBL dataset, achieving new state-of-the-art results on the majority of molecular generation tasks.

Deep generative models, such as diffusion models, have shown promising progress in image generation and audio generation via simplified continuity assumptions. However, the development of generative modeling techniques for generating multi-modal data, such as parametric CAD sequences, still lags behind due to the challenges in addressing long-range constraints and parameter sensitivity. In this work, we propose a novel framework for quantitatively constrained CAD generation, termed Target-Guided Bayesian Flow Network (TGBFN). For the first time, TGBFN handles the multi-modality of CAD sequences (i.e., discrete commands and continuous parameters) in a unified continuous and differentiable parameter space rather than in the discrete data space. In addition, TGBFN penetrates the parameter update kernel and introduces a guided Bayesian flow to control the CAD properties. To evaluate TGBFN, we construct a new dataset for quantitatively constrained CAD generation. Extensive comparisons across single-condition and multi-condition constrained generation tasks demonstrate that TGBFN achieves state-of-the-art performance in generating high-fidelity, condition-aware CAD sequences. The code is available at https://github.com/scu-zwh/TGBFN.

MOTIVATION: The burgeoning field of target-specific drug design has attracted considerable attention, focusing on identifying compounds with high binding affinity toward specific target pockets. Nevertheless, existing target-specific deep generative models encounter notable challenges. Some models heavily rely on elaborate datasets and complicated training methodologies, while others neglect the multi-constraint optimization problem inherent in drug design, resulting in generated molecules with irrational structures or chemical properties. RESULTS: To address these issues, we propose a novel framework (TargetSA) that leverages adaptive simulated annealing (SA) for target-specific molecular generation and multi-constraint optimization. The SA process explores the discrete structural space of molecules, progressively converging toward the optimal solution that fulfills the predefined objective. To propose novel compounds, we first predict promising editing positions based on historical experience, and then iteratively edit molecular graphs through four operations (insertion, replacement, deletion, and cyclization). Together, these operations collectively constitute a complete operation set, facilitating a thorough exploration of the drug-like space. Furthermore, we introduce a reversible sampling strategy to re-accept currently suboptimal solutions, greatly enhancing the generation quality. Empirical evaluations demonstrate that TargetSA achieves state-of-the-art performance in generating high-affinity molecules (average vina dock -9.09) while maintaining desirable chemical properties. AVAILABILITY AND IMPLEMENTATION: https://github.com/XueZhe-Zachary/TargetSA.