Knowledge Graph-Enhanced Long-CoT for Complex Biomolecular Reasoning

VitaGraph: building a knowledge graph for biologically relevant learning tasks

The complexity of human biology poses ongoing challenges, driving global interdisciplinary research. Artificial intelligence has become a powerful tool in computational biology, where graph data structures model entities like protein–protein interaction (PPI) networks and gene functional networks. These networks support crucial tasks in network medicine, including gene–disease association prediction, drug repurposing, and polypharmacy side-effect analysis. Reliable machine learning predictions require high-quality data. We present VitaGraph, a comprehensive multi-purpose biological knowledge graph built by integrating and refining multiple public datasets. Extending the Drug Repurposing Knowledge Graph, our pipeline: (a) resolves inconsistencies and redundancies, (b) consolidates information from leading public sources, and (c) enriches graph nodes with expressive features such as molecular fingerprints and gene ontologies. Incorporating biologically and chemically meaningful features enhances machine learning models’ ability to learn accurate, structured embedding spaces. The resulting resource offers a coherent, reliable platform to advance computational biology and precision medicine while enabling benchmarking of graph-based models and offering the opportunity to tackle tasks such as drug repurposing, PPI prediction, and side-effect prediction, among others.

THGAgents: Traceable Biomedical Hypothesis Generation via Dynamic Causal Reasoning

KLaR: fusing knowledge graphs and language models for biomedical target discovery

Abstract Motivation Biomedical knowledge relevant to disease mechanisms and therapeutic discovery is distributed across structured knowledge graphs (KGs) and unstructured text. Although pretrained language models provide strong semantic embeddings, adapting them to biomedical link prediction typically requires domain-specific fine-tuning and may weaken explicit structural constraints. An open challenge is to enhance link prediction with principled knowledge–language fusion while keeping language encoders lightweight and controllable. Results We propose KLaR, a knowledge–language representation framework for biomedical KG link prediction. Given a query entity, KLaR encodes its local k-hop neighborhood with a relational GNN and constructs mechanism-consistent textual contexts by template-based textualization of random-walk paths within the same subgraph. These contexts are embedded using a frozen sentence-embedding model (without external retrieval or task-specific fine-tuning), and structural and textual views are aligned and fused via gated integration. To model heterogeneous biomedical interactions, KLaR uses a sparse mixture-of-experts decoder for triple scoring. On PharmKG, HetioNet, and DTINet, KLaR yields consistent gains over structure-only and KG–language hybrid baselines under standard filtered evaluation. We additionally report text-only LLM reference results under a candidate-restricted protocol due to the infeasibility of full-entity ranking for prompted generation. Case studies suggest that KLaR can recover biologically plausible disease–gene and drug–target associations missing from the original graphs, supporting hypothesis generation without domain-specific language model fine-tuning. Availability and implementation Code and processed data are available at: https://github.com/stardj/KLaR.

Ontology-Free Biomedical Knowledge Graph Induction (OF-Bio-KG)

Adapting large language models (LLMs) to new domains using techniques like pre-training or fine-tuning can be computationally intensive. This challenge has motivated researchers and practitioners to explore alternative strategies, such as Retrieval-based augmentation mechanisms, to reduce training cost while preserving model adaptability. These mechanisms enable LLMs to generate responses grounded in external and previously unseen data. Among these approaches, RetrievalAugmented Generation (RAG) is the widely adopted due to its relatively low computational overhead. However, conventional RAG pipelines exhibit some limitations, including weak semantic coherence across retrieved contexts, limited structural reasoning capability, and the absence of explicit relational representations. To overcome these limitations, recent research has shifted toward the integration of Knowledge Graphs (KGs), which provide structured semantic representations and explicit relational modeling. KG-based approaches looks promising but the typically depend on manually designed ontologies, resulting in scalability constraints and domain adaptation challenges. To address these limitations, we propose OF-BIO-KG, a framework for automated, ontology-free knowledge graph construction. Our approach begins by projecting domain data into a vector database to identify semantically coherent clusters. An LLM then labels these clusters as conceptual nodes and infers both hierarchical and cross-cluster relationships. These nodes and links are persisted in a graph database. By eliminating the need for predefined schemas, our framework offers a scalable, computationally efficient solution for domain-specific LLM adaptation.

MolBioKG: Grounding Out-of-Graph Molecules in Biomedical Knowledge Graphs via Multi-Resolution Structural Anchoring

Biomedical knowledge graphs (KGs) accelerate drug discovery, but standard pipelines assume query molecules already exist as graph entities, leaving unregistered molecules disconnected. We address this cold-start challenge, termed the out-of-graph molecule problem, by introducing MolBioKG. This two-layer system grounds unseen molecules in biomedical evidence via multi-resolution structural anchoring. It connects an index of 2.74 million molecules (represented by scaffolds, fragments, functional groups, and fingerprints) to a 9.6-million-edge KG. Given only a SMILES string, MolBioKG retrieves structurally related graph entities and traverses their biomedical neighborhoods without task-specific training. It features two inference mechanisms: static multi-anchor retrieval using Reciprocal Rank Fusion, and Adapt-KG, a tool-using LLM policy for adaptive traversal. Evaluated across in-graph link recovery, complex multi-hop reasoning, and out-of-graph generalization, MolBioKG outperforms strong baselines. Notably, it raises Hits@10 from 0.585 to 0.876 in multi-hop reasoning and out-of-graph target recall from 0.145 to 0.269, all while ensuring predictions retain traceable structural anchors and source-attributed KG evidence.

Learning Graph Rationales to Compress Long Chains of Thought in Multimodal Reasoning

Recent advances in multimodal large reasoning models (MLRMs) have demonstrated impressive capabilities on complex multimodal tasks, yet their reliance on long Chain-of-Thoughts (CoTs) often leads to redundant reasoning and high computational cost. Existing chain-based distillation and refinement approaches alleviate redundancy to some extent but remain limited when handling ultra-long reasoning chains, suffering from weakened dependency modeling, accumulated redundancy, and the omission of critical reasoning steps. To this end, in this paper, we propose GRACE, a Graph-based Rationalized CoT Compression framework that transforms long CoTs into reasoning graphs to enable efficient CoT compression, where reasoning steps are represented as nodes and semantic dependencies as edges. Specifically, after constructing the reasoning graph, GRACE applies a graph rationale learning approach with a selector–predictor architecture. Among them, the selector estimates node-level rationale scores to sample a compact rationale subgraph, while the predictor leverages this subgraph for final prediction. The resulting subgraph serves as the distilled core rationale, retaining essential reasoning while removing irrelevant steps. Finally, the compressed CoTs are then used to build supervised fine-tuning datasets for further MLRMs tuning. Experiments on multiple multimodal benchmarks show that GRACE substantially improves inference efficiency and interpretability without sacrificing accuracy.