REVIEW 4 cited by
MolFM: A Multimodal Molecular Foundation Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Molecular knowledge resides within three different modalities of information sources: molecular structures, biomedical documents, and knowledge bases. Effective incorporation of molecular knowledge from these modalities holds paramount significance in facilitating biomedical research. However, existing multimodal molecular foundation models exhibit limitations in capturing intricate connections between molecular structures and texts, and more importantly, none of them attempt to leverage a wealth of molecular expertise derived from knowledge graphs. In this study, we introduce MolFM, a multimodal molecular foundation model designed to facilitate joint representation learning from molecular structures, biomedical texts, and knowledge graphs. We propose cross-modal attention between atoms of molecular structures, neighbors of molecule entities and semantically related texts to facilitate cross-modal comprehension. We provide theoretical analysis that our cross-modal pre-training captures local and global molecular knowledge by minimizing the distance in the feature space between different modalities of the same molecule, as well as molecules sharing similar structures or functions. MolFM achieves state-of-the-art performance on various downstream tasks. On cross-modal retrieval, MolFM outperforms existing models with 12.13% and 5.04% absolute gains under the zero-shot and fine-tuning settings, respectively. Furthermore, qualitative analysis showcases MolFM's implicit ability to provide grounding from molecular substructures and knowledge graphs. Code and models are available on https://github.com/BioFM/OpenBioMed.
Forward citations
Cited by 4 Pith papers
-
Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?
Morpher adapts pre-trained GNNs to language using multi-modal prompts and a projector, achieving few-shot, cross-domain, and zero-shot unseen-class classification with weak text supervision.
-
OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery
A new 29.7K-image benchmark for reading molecule diagrams into functional groups, descriptions, IUPAC names, and SMILES, with a fine-tuned VLM outperforming a recognize-then-generate pipeline on most subtasks.
-
GeomCLIP: Contrastive Geometry-Text Pre-training for Molecules
GeomCLIP aligns 3D molecular geometries with biomedical text via contrastive and denoising pretraining and reports improved performance on property prediction, retrieval, and captioning.
-
DEFEND: A Large-scale 1M Dataset and Foundation Model for Tobacco Addiction Prevention
A new 1M-image tobacco product dataset and a multimodal model that combines contrastive, coherence, and description losses, with reported gains over prior baselines.
Discussion (0). Continue with ORCID to comment.