Identifying suitable reaction conditions is critical for chemical synthesis, as they directly affect yield, selectivity, and transformation feasibility. While recent methods have shown promising results, most approaches either encode reactants and products independently or rely on rule-based reaction graphs, both of which constrain the ability of the model to capture condition-relevant structural transformations. In this work, we propose TRACE, a transformation-aware graph refinement framework for reaction condition prediction. TRACE constructs atom-level joint graphs that integrate both reactant and product structures to represent condition-relevant transformations. A structure-aware encoder enriches atom features with local chemical context, followed by a dynamic interaction refinement module that adaptively infers task-specific edges. To further guide the model toward condition-relevant patterns, a mechanism regularized graph encoder incorporates reaction center information, enabling more accurate modeling of transformation mechanisms. Experiments on benchmark datasets show that TRACE achieves state-of-the-art performance across multiple condition types. The integration of transformation-aware refinement leads to improvements in prediction accuracy and generalization, while maintaining robust performance in challenging and realistic synthesis planning scenarios.

Multi-objective molecular optimization is a fundamental yet inherently challenging task in drug discovery, as it requires simultaneously optimizing multiple, often conflicting, molecular properties. Although recent deep learning methods have shown promise, they often lack objective-specific specialization and dynamic coordination, making them ineffective in handling competing objectives and difficult to scale in complex, high-dimensional molecular design tasks. Inspired by the division of labor among domain experts in medicinal chemistry, we propose MAMO, a multi-agent framework for molecular design that simulates expert collaboration. Each agent specializes in optimizing a single objective, and their interactions are orchestrated by a central scheduling module that dynamically reallocates tasks based on evaluation feedback. This coordination mechanism enables interpretable and goal-conditioned optimization while adaptively balancing conflicting objectives. Extensive experiments on benchmark datasets demonstrate that MAMO consistently achieves superior performance in both objective quality and Pareto diversity, particularly in scenarios with strong inter-objective conflict. Our results highlight the potential of multi-agent coordination strategies for scalable and conflict-aware molecular design.

Xuanbai Ren, Luoda Tan, Pei Liu, Tengfei Ma, Xiangzheng Fu, Longyue Wang, Yiping Liu, Xiangxiang Zeng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Protein-protein interactions (PPIs) are fundamental molecular events in the human body, playing a pivotal role in disease treatment and intervention. However, existing approaches for protein representation often rely on simplistic PPI network models, which face two key challenges: (i) neglecting explicit residue-based binding relationships critical to protein interactions, and (ii) failing to integrate residue-level binding data with protein interaction networks, limiting their ability to uncover the binding mechanisms of PPIs. To address these issues, we propose an Enhanced protein network representation framework with Explicit structural binding information for improved PPI prediction, named E$^{2}$PPI. Specifically, E$^{2}$PPI extracts residue-level interactions between paired proteins using both single-protein structural analysis and inter-protein binding representation modules. To seamlessly integrate residue-level binding data with the semantics of protein interactions, we introduce an enhanced protein network representation module. This design enables the model to capture the interaction and binding mechanisms of PPIs, thereby improving its classification performance. Benchmark experiments demonstrate that E$^{2}$PPI outperforms state-of-the-art models, especially for few-shot and novel proteins, showcasing its superior generalization capabilities.

Inductive Knowledge Graph Completion (KGC) aims to infer missing facts between newly emerged entities within knowledge graphs (KGs), posing a significant challenge. While recent studies have shown promising results in inferring such entities through knowledge subgraph reasoning, they suffer from (i) the semantic inconsistencies of similar relations, and (ii) noisy interactions inherent in KGs due to the presence of unconvincing knowledge for emerging entities. To address these challenges, we propose a Semantic Structure-aware Denoising Network (S2DN) for inductive KGC. Our goal is to learn adaptable general semantics and reliable structures to distill consistent semantic knowledge while preserving reliable interactions within KGs. Specifically, we introduce a semantic smoothing module over the enclosing subgraphs to retain the universal semantic knowledge of relations. We incorporate a structure refining module to filter out unreliable interactions and offer additional knowledge, retaining robust structure surrounding target links. Extensive experiments conducted on three benchmark KGs demonstrate that S2DN surpasses the performance of state-of-the-art models. These results demonstrate the effectiveness of S2DN in preserving semantic consistency and enhancing the robustness of filtering out unreliable interactions in contaminated KGs.

Modeling the impact of amino acid mutations on the binding affinity between antibodies and antigens plays a pivotal role in antibody therapeutics development. While numerous deep learning-based methods have shown promising results, accurately modeling the impact of mutations on binding interfaces remains a significant challenge, as even small changes can substantially affect binding affinity. To address this issue, we propose VQH-AM, a Vector Quantization-based Heterogeneous graph neural network for antibody Affinity Maturation prediction. Specifically, we construct atom-level heterogeneous graphs for both wild-type and mutant antibody-antigen complexes to model their binding interfaces. Atomic representations extracted by the heterogeneous graph neural networks are then quantized via a context-aware codebook designed to capture semantic atomic patterns. Finally, both the original and quantized atomic representations are integrated and used to predict the affinity maturation outcomes. Benchmark experiments demonstrate that VQH-AM consistently outperforms state-of-the-art methods across multiple evaluation metrics. The source code is available at: https://github.com/zwzhen-hnu/VQH-AM.

Knowledge graph completion (KGC) aims to alleviate the inherent incompleteness of knowledge graphs (KGs), a crucial task for numerous applications such as recommendation systems and drug repurposing. The success of knowledge graph embedding (KGE) models provokes the question about the explainability: ``\textit{Which the patterns of the input KG are most determinant to the prediction}?'' Particularly, path-based explainers prevail in existing methods because of their strong capability for human understanding. In this paper, based on the observation that a fact is usually determined by the synergy of multiple reasoning chains, we propose a novel explainable framework, dubbed KGExplainer, to explore synergistic pathways. KGExplainer is a model-agnostic approach that employs a perturbation-based greedy search algorithm to identify the most crucial synergistic paths as explanations within the local structure of target predictions. To evaluate the quality of these explanations, KGExplainer distills an evaluator from the target KGE model, allowing for the examination of their fidelity. We experimentally demonstrate that the distilled evaluator has comparable predictive performance to the target KGE. Experimental results on benchmark datasets demonstrate the effectiveness of KGExplainer, achieving a human evaluation accuracy of 83.3\% and showing promising improvements in explainability. Code is available at \url{https://github.com/xiaomingaaa/KGExplainer}

Identifying drug-drug interactions (DDIs) is critical for ensuring drug safety and advancing drug development, a topic that has garnered significant research interest. While existing methods have made considerable progress, approaches relying solely on known DDIs face a key challenge when applied to drugs with limited data: insufficient exploration of the space of unlabeled pairwise drugs. To address these issues, we innovatively introduce S$^2$VM, a Self-supervised Visual pretraining framework for pair-wise Molecules, to fully fuse structural representations and explore the space of drug pairs for DDI prediction. S$^2$VM incorporates the explicit structure and correlations of visual molecules, such as the positional relationships and connectivity between functional substructures. Specifically, we blend the visual fragments of drug pairs into a unified input for joint encoding and then recover molecule-specific visual information for each drug individually. This approach integrates fine-grained structural representations from unlabeled drug pair data. By using visual fragments as anchors, S$^2$VM effectively captures the spatial information of local molecular components within visual molecules, resulting in more comprehensive embeddings of drug pairs. Experimental results show that S$^2$VM achieves state-of-the-art performance on widely used benchmarks, with Macro-F1 score improvements of 4.21% and 3.31%, respectively. Further extensive results and theoretical analysis demonstrate the effectiveness of S$^2$VM for both few-shot and novel drugs.

Medication recommendation systems are developed to recommend suitable medications tailored to specific patient. Previous researches primarily focus on learning medication representations, which have yielded notable advances. However, these methods are limited to capturing personalized patient representations due to the following primary limitations: (i) unable to capture the differences in the impact of diseases/procedures on patients across various patient health states; (ii) fail to model the direct causal relationships between medications and specific health state of patients, resulting in an inability to determine which specific disease each medication is treating. To address these limitations, we propose CausalMed, a patient health state-centric model capable of enhancing the personalization of patient representations. Specifically, CausalMed first captures the causal relationship between diseases/procedures and medications through causal discovery and evaluates their causal effects. Building upon this, CausalMed focuses on analyzing the health state of patients, capturing the dynamic differences of diseases/procedures in different health states of patients, and transforming diseases/procedures into medications on direct causal relationships. Ultimately, CausalMed integrates information from longitudinal visits to recommend medication combinations. Extensive experiments on real-world datasets show that our method learns more personalized patient representation and outperforms state-of-the-art models in accuracy and safety.

Molecular interaction prediction plays a crucial role in forecasting unknown interactions between molecules, such as drug-target interaction (DTI) and drug-drug interaction (DDI), which are essential in the field of drug discovery and therapeutics. Although previous prediction methods have yielded promising results by leveraging the rich semantics and topological structure of biomedical knowledge graphs (KGs), they have primarily focused on enhancing predictive performance without addressing the presence of inevitable noise and inconsistent semantics. This limitation has hindered the advancement of KG-based prediction methods. To address this limitation, we propose BioKDN (BiomedicalKnowledge GraphDenoisingNetwork) for robust molecular interaction prediction. BioKDN refines the reliable structure of local subgraphs by denoising noisy links in a learnable manner, providing a general module for extracting task-relevant interactions. To enhance the reliability of the refined structure, BioKDN maintains consistent and robust semantics by smoothing relations around the target interaction. By maximizing the mutual information between reliable structure and smoothed relations, BioKDN emphasizes informative semantics to enable precise predictions. Experimental results on real-world datasets show that BioKDN surpasses state-of-the-art models in DTI and DDI prediction tasks, confirming the effectiveness and robustness of BioKDN in denoising unreliable interactions within contaminated KGs.

Molecular interaction prediction is essential in various applications including drug discovery and material science. The problem becomes quite challenging when the interaction is represented by unmapped relationships in molecular networks, namely molecular interaction, because it easily suffers from (i) insufficient labeled data with many false-positive samples, and (ii) ignoring a large number of biological entities with rich information in the knowledge graph. Most of the existing methods cannot properly exploit the information of knowledge graph and molecule graph simultaneously. In this paper, we propose a large-scaleKnowledgeGraph enhancedMulti-TaskLearning model, namely KG-MTL, which extracts the features from both knowledge graph and molecular graph in a synergistic way. Moreover, we design an effectiveShared Unitthat helps the model to jointly preserve the semantic relations of drug entity and the neighbor structures of the compound in both knowledge graph and molecular graph. Extensive experiments on four real-world datasets demonstrate that our proposed KG-MTL outperforms the state-of-the-art methods on two representative molecular interaction prediction tasks: drug-target interaction prediction and compound-protein interaction prediction. The source code of KG-MTL is available athttps://github.com/xzenglab/KG-MTL.

MOTIVATION: Adverse drug-drug interactions (DDIs) are crucial for drug research and mainly cause morbidity and mortality. Thus, the identification of potential DDIs is essential for doctors, patients and the society. Existing traditional machine learning models rely heavily on handcraft features and lack generalization. Recently, the deep learning approaches that can automatically learn drug features from the molecular graph or drug-related network have improved the ability of computational models to predict unknown DDIs. However, previous works utilized large labeled data and merely considered the structure or sequence information of drugs without considering the relations or topological information between drug and other biomedical objects (e.g. gene, disease and pathway), or considered knowledge graph (KG) without considering the information from the drug molecular structure. RESULTS: Accordingly, to effectively explore the joint effect of drug molecular structure and semantic information of drugs in knowledge graph for DDI prediction, we propose a multi-scale feature fusion deep learning model named MUFFIN. MUFFIN can jointly learn the drug representation based on both the drug-self structure information and the KG with rich bio-medical information. In MUFFIN, we designed a bi-level cross strategy that includes cross- and scalar-level components to fuse multi-modal features well. MUFFIN can alleviate the restriction of limited labeled data on deep learning models by crossing the features learned from large-scale KG and drug molecular graph. We evaluated our approach on three datasets and three different tasks including binary-class, multi-class and multi-label DDI prediction tasks. The results showed that MUFFIN outperformed other state-of-the-art baselines. AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/xzenglab/MUFFIN.

Drug-drug interaction (DDI) prediction is a challenging problem in pharmacology and clinical application, and effectively identifying potential DDIs during clinical trials is critical for patients and society. Most of existing computational models with AI techniques often concentrate on integrating multiple data sources and combining popular embedding methods together. Yet, researchers pay less attention to the potential correlations between drug and other entities such as targets and genes. Moreover, recent studies also adopted knowledge graph (KG) for DDI prediction. Yet, this line of methods learn node latent embedding directly, but they are limited in obtaining the rich neighborhood information of each entity in the KG. To address the above limitations, we propose an end-to-end framework, called Knowledge Graph Neural Network (KGNN), to resolve the DDI prediction. Our framework can effectively capture drug and its potential neighborhoods by mining their associated relations in KG. To extract both high-order structures and semantic relations of the KG, we learn from the neighborhoods for each entity in the KG as their local receptive, and then integrate neighborhood information with bias from representation of the current entity. This way, the receptive field can be naturally extended to multiple hops away to model high-order topological information and to obtain drugs potential long-distance correlations. We have implemented our method and conducted experiments based on several widely-used datasets. Empirical results show that KGNN outperforms the classic and state-of-the-art models.