This work proposes Molrep-SCF, a multimodal self-supervised pretraining framework for molecular representation learning using SMILES sequences, 2D molecular graphs, and 3D geometric structures that consistently outperforms existing multi-modal frameworks on molecular property prediction and other tasks.
Abstract
In this work, we propose Molrep-SCF, a multimodal self-supervised pretraining framework for molecular representation learning using SMILES sequences, 2D molecular graphs, and 3D geometric structures. The three modalities are encoded using a Transformer, a graph neural network, and an invariant 3D graph neural network, respectively. To enrich geometric supervision beyond a single conformation, Molrep-SCF incorporates three selected and complementary 3D conformational views. We further introduce a 2D-guided conformational consistency refinement mechanism that uses molecular topology to guide the fusion and refinement of their geometric representations. Instead of relying on a single static conformation, our method enforces structural consistency across conformers under the guidance of 2D topological priors. Furthermore, we design a structure-aware cross-modal learning strategy with atomic-level alignment via position-specific masking, enabling fine-grained correspondence across modalities. In addition, masked reconstruction across modalities enhances deep semantic coupling and facilitates information exchange between heterogeneous representations. Extensive experiments demonstrate that Molrep-SCF consistently outperforms existing multi-modal frameworks on molecular property prediction and other tasks, showing stronger generalization and representation quality.
Molecular prediction depends on how chemical structures are represented, yet descriptors capture only partial aspects of chemical information. Here, we show that the Chemical Dice Integrator combines six complementary molecular views spanning physicochemical properties, molecular topology, two-dimensional structural im...
MoTIF-X, a motif-centered framework that uses graph-grounded chemical motifs as shared anchors for multimodal integration and interpretation, is introduced, achieving the best average classification performance across the evaluated benchmarks and generalizing to an external drug-cold-start dataset without additional fi...
Lin-Qing Mo, Jia-Yu Zhou, Bin Chen· arXiv.org· 0 citations
Abstract Motivation Self-supervised pre-training models for molecular data have demonstrated notable results across many downstream tasks. The inherent multimodal properties of molecules have also motivated efforts to capture information from different modalities. However, current multimodal molecular pre-training mode...
Kang-Jie Zheng, Jun-Wei Yang, Siyu Long et al.· Bioinform.· 0 citations
Abstract Motivation Pocket-conditioned molecular generation incorporates the three-dimensional (3D) geometry and chemical environment of protein binding sites into molecular design. However, receptor conformational variation can introduce distribution shifts between training and inference, particularly under cross-dock...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduJul 15, 2026
Assistant Professor Pat Pataranutaporn describes a new interface that lets everyday users glimpse inside an AI's neural network before their chatbot ever says a word.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.