Molecular Joint Representation Learning via Multi-modal Information

2022-11-25 · Tianyu Wu, Yang Tang, Qiyu Sun, Luolin Xiong

In recent years, artificial intelligence has played an important role on accelerating the whole process of drug discovery. Various of molecular representation schemes of different modals (e.g. textual sequence or graph) are developed. By digitally encoding them, different chemical information can be learned through corresponding network structures. Molecular graphs and Simplified Molecular Input Line Entry System (SMILES) are popular means for molecular representation learning in current. Previous works have done attempts by combining both of them to solve the problem of specific information loss in single-modal representation on various tasks. To further fusing such multi-modal imformation, the correspondence between learned chemical feature from different representation should be considered. To realize this, we propose a novel framework of molecular joint representation learning via Multi-Modal information of SMILES and molecular Graphs, called MMSG. We improve the self-attention mechanism by introducing bond level graph representation as attention bias in Transformer to reinforce feature correspondence between multi-modal information. We further propose a Bidirectional Message Communication Graph Neural Network (BMC GNN) to strengthen the information flow aggregated from graphs for further combination. Numerous experiments on public property prediction datasets have demonstrated the effectiveness of our model.

📄 PDF Abstract BibTeX arXiv:2211.14042

Code (0)

등록된 구현이 없습니다.

Tasks

Drug Discovery Graph Neural Networkmolecular representationProperty PredictionRepresentation Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Graph Neural Network 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Adam 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Local-Global Multimodal Contrastive Learning for Molecular Property Prediction

2026-01-30 · Xiayu Liu, Zhengyi Lu, Yunhong Liao, Chan Fan 외 arxiv

Accurate molecular property prediction requires integrating complementary information from molecular structure and chemical semantics. In this work, we propose LGM-CL, a local-global multimodal contrastive learning frame…

Molecular Property Prediction Representation Learning Contrastive Learning

Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules

2026-08-23 · Florian Rottach, Sebastian Schieferdecker, William Rudman, Randall Balestriero 외 arxiv

Despite recent advances in molecular foundation models, several limitations remain, such as chemically invalid augmentations, modality collapse, and incomplete representation of biochemical environments. To address these…

Drug Discovery

TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence

2025-06-26 · Feng Jiang, Mangal Prakash, Hehuan Ma, Jianyuan Deng 외

Molecular property prediction aims to learn representations that map chemical structures to functional properties. While multimodal learning has emerged as a powerful paradigm to learn molecular representations, prior wo…

Molecular Property Prediction molecular representation Property Prediction Representation Learning

MolFusion: Multimodal Fusion Learning for Molecular Representations via Multi-granularity Views

2024-06-26 · MuZhen Cai, Sendong Zhao, Haochun Wang, Yanrui Du 외

Artificial Intelligence predicts drug properties by encoding drug molecules, aiding in the rapid screening of candidates. Different molecular representations, such as SMILES and molecule graphs, contain complementary inf…

ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning

2025-10-19 · Yingxu Wang, Kunyu Zhang, Jiaxin Huang, Nan Yin 외 arxiv

Multimodal molecular representation learning, which jointly models molecular graphs and their textual descriptions, enhances predictive accuracy and interpretability by enabling more robust and reliable predictions of dr…

Molecular Property Prediction Representation Learning