Skip to content
Book Open access

Foundation-Assisted Cross-Domain Meta-Learning for Few-Shot Molecular Property Prediction

Nov 2026 · Proceedings of the 35th ACM International Conference on Information and Knowledge Management · pp. 1906-1916 · 0 citations

Abstract

Molecular property prediction is important for drug discovery, but labeled molecules are often limited for new prediction tasks. The difficulty is amplified in cross-domain few-shot settings, where target tasks differ from available source tasks and the model must adapt from sparse target-domain supervision. Existing few-shot and transferable few-shot methods mainly condition adaptation on the target support set, which can be unstable when the support molecules provide limited coverage of the target distribution. We propose Foundation-Assisted Cross-Domain Meta-Learning for Few-Shot Molecular Property Prediction (FACML), which augments cross-domain episodic learning with property-aware priors from a frozen Structure-Property Multi-Modal foundation model (SPMM). FACML represents each molecule using SPMM-derived SMILES features and graph features, and constructs support Property Vector (PV) prototypes and query PV representations from SPMM-predicted PVs based on molecular SMILES. A property-conditioned relation graph then integrates molecular nodes and PV-based prior nodes to refine episode representations for target-task adaptation. Across cross-dataset few-shot molecular property prediction benchmarks, FACML improves the average ROC-AUC over the strongest baseline by 6.36% and 8.12% under the 1-shot and 10-shot settings, respectively. An auxiliary zero-target-label analysis further examines the use of SPMM-generated molecules when labeled target support molecules are unavailable.

Read PDF

Similar papers

Oct 2026

Cross-Modal Semantic Alignment for Cold-Start Drug-Target Interaction Prediction.

Drug-target interaction (DTI) prediction is essential for drug discovery, yet existing models often suffer from limited generalization when drugs or targets are unseen during training. This challenge is particularly severe in cold-start settings, where interaction records are unavailable for novel entities and effectiv...

Jia He, Le-Sheng Chen, Wen-Qi Fang et al. · 0 citations
Sep 2026

FGMDTI: Fine-grained Multimodal Learning for Drug-Target Interaction Prediction via Bidirectional Cross-Attention.

Drug-target interaction (DTI) prediction is critical for drug discovery and repositioning. Existing methods often rely on coarse-grained representations and fail to capture the reciprocal nature of molecular recognition. We propose FGMDTI, a fine-grained multimodal framework that models bidirectional interactions betwe...

Meng-De Li, Chi Zhou, Wen-Bin Liu et al. · 0 citations
Open access Nov 2026

MSER-DDI: molecular and semantic event representations for few-shot and unseen-event drug–drug interaction prediction

Sparse event annotations limit drug-drug interaction (DDI) prediction, particularly for rare events and event categories absent from training data. We propose MSER-DDI, a framework with two independently trained pathways that represent target events using labeled drug pairs or textual descriptions. The sampl...

Wen Li, Yan-Xiu Fu, Xiang-Qiong Wu et al. · 0 citations

Drug-Target Interaction Prediction via Hierarchical Sequential Cross-Attention over Chemical and Protein Language Models

This paper proposes a sequence-only DTI prediction architecture that combines two pre-trained language models, ChemBERTa for drug SMILES strings and ESM-2 for protein amino acid sequences, with a hierarchical interaction module, and implements a sequential bidirectional cross-attention mechanism inspired by the induced...

Khadidja Henni, Hamza Abdelali, Abdelkrim Aries et al. · 0 citations
Oct 2026

MMB-DTI: A Multimodal State Space Framework with Bidirectional Cross-Attention for Drug-Target Interaction Prediction.

Comprehensive evaluations across six benchmark datasets demonstrate that MMB-DTI achieves highly competitive predictive performance, significantly outperforming state-of-the-art baselines, and highlights that coupling linear-time state space modeling with topological complementarity yields a robust and discriminative p...

Fang Fang, Jin-Jin Li, Cheng-Ye Huang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.