26 papers · ranked by Valyu relevance
Yao Liu, Tien-Ping Tan, Zhilan Liu, Yuxin Li + 1 more
Social event detection (SED) aims to identify real-world events from large-scale social media streams and has become essential for applications in public safety, marketing analytics, and crisis management. However, the heterogeneous, hierarchical, and dynamic nature of social data poses fundamental challenges for…
Félix Vandervorst, Bruno Deprez, Wouter Verbeke, Tim Verdonck
Graph-based methods are becoming increasingly popular in machine learning due to their ability to model more complex data and relations. Whereas gradient boosted tree approaches dominate the field of supervised learning on tabular data, (deep) neural network-based approaches are dominantly used for supervised learning…
Abderaouf Bahi
Graph neural networks have moved from a niche representation-learning technique to the default model class wherever data carry relational structure. The interesting question is no longer whether message passing helps on a given dataset, but where graph structure earns its computational cost and where it does not. This…
Qingwen Wu, Sujuan Tang
Non-coding RNAs (ncRNAs) play crucial roles in regulating the initiation and progression of various cancers. Accurate identification disease-related ncRNAs would provide a unique opportunity to design better therapeutic interventions. Graph convolutional network-based methods have been proposed to identify potential…
Bi Jingjun, Dornaika, Fadi
Recently, graph-based semi-supervised learning and pseudo-labeling have gained attention due to their effectiveness in reducing the need for extensive data annotations. Pseudo-labeling uses predictions from unlabeled data to improve model training, while graph-based methods are characterized by processing data…
Setareh Rahimi, Stephen Bonner, Avid Afzal, Marta Milo + 2 more
Predicting gene essentiality across cellular contexts is a central challenge in computational biology, with implications for identifying cancer vulnerabilities. Graph neural networks (GNNs) integrate molecular interaction networks with gene-level features, but it remains unclear whether their performance gains arise…
Daniel M. Gonçalves, André Patrício, Rafael S. Costa, Rui Henriques
The growing availability and complexity of omics data have driven the development of specialized algorithms for modeling molecular systems. Although graph-based learning methods effectively represent biological interactions, they often neglect the statistical information embedded in node and edge annotations. To…
Quispe, Joel Frank Huarayo, Berton, Lilian + 2 more
—Link prediction in bipartite graphs is crucial for applications like recommendation systems and failure detection, yet it is less studied than in monopartite graphs. Contrastive methods struggle with inefficient and biased negative sampling, while non-contrastive approaches rely solely on positive samples. Existing…
Dooho Lee, Jaemin Yoo
Node representation learning has advanced rapidly, yet most existing methods rely on per-dataset training and hyperparameter tuning. This dataset-specific optimization comes from the difficulty of designing reusable graph models that generalize across diverse graph datasets. In this work, we introduce Node4All, a node…
Jiangnan Zhou, Sheng Zhang, Bing Wu, Qiuming Wang + 5 more
Existing methods for hypergraph node classification usually rely on local message passing and use a unified strategy for topological modeling across hyperedges of different sizes. However, they have two limitations in semi-supervised settings. First, representation learning mainly depends on local neighborhoods, making…
Yinfei Dai, Mengjiao Qiao, Jie Fan, Shihao Lu + 5 more
Fusarium graminearum infection of maize induces complex transcriptional reprogramming, yet existing differential-expression and local graph convolutional approaches struggle to capture long-range and multi-scale regulatory dependencies. We propose DC-FusionGNN, a dual-channel fusion graph neural network for key…
Mohammadamin Moragheb, Alireza Dehghan, Parvin Razzaghi, Sajjad Gharaghani + 1 more
Combination therapies have become a cornerstone of modern medicine, offering improved treatment outcomes and reduced side effects compared to monotherapies. However, the efficacy and safety of drug combinations depend heavily on the specific doses of each component, making the optimization of dosing regimens a crucial…
Authors not listed
Crystal structure prediction (CSP) is a valuable computational technique used to anticipate the likely crystal structures of a compound of interest. These methods have been proven useful in research and development of pharmaceutical solid forms and in guiding the discovery of materials with targeted properties. Despite…
Xiaoguang Guo, Zehong Wang, Ziming Li, Shawn Spitzel + 4 more
Graph representation learning (GRL) has evolved from topology-only graph embeddings to task-specific supervised GNNs, and more recently to reusable representations and graph foundation models (GFMs). However, existing evaluations mainly measure clean transfer, adaptation, and task coverage. It remains unclear whether…
Wang, Songbo, Yang, Renchi + 6 more
The emergence of graph neural networks (GNNs) has offered a powerful tool for semi-supervised node classification tasks. Subsequent studies have achieved further improvements through refining the message passing schemes in GNN models or exploiting various data augmentation techniques to mitigate limited supervision. In…
Aoqi Xie, Yuehua Cui
With advances in spatially resolved transcriptomics across platforms and resolutions, it is now possible to measure gene-expression profiles while preserving the tissue microenvironment. Spatial clustering is central to these analyses, and recent graph neural network (GNN)-based approaches have greatly improved their…
Marco Stock, Florin Ratajczak, Paul Bertin, Eva Hoermanseder + 6 more
Accurate reconstruction of gene regulatory networks (GRNs) from single-cell transcriptomic data remains a major methodological challenge. Recent machine learning approaches, particularly graph neural networks and graph autoencoders, have reported improved performance, yet these gains do not consistently translate to…
Authors not listed
Computational methods for predictive modeling have been increasingly utilized in the early stages of drug discovery to supplement high-throughput screening. The advent of highly efficient and complex machine learning architectures necessitates new methods of collating the plethora of topological, geometrical, and…
Authors not listed
AI-driven molecular generation encounters a "generation-synthesis gap": most computationally designed molecules cannot be synthesized in laboratories, limiting AI-assisted drug design (AIDD) applications. Current approaches to assess synthetic accessibility (SA) include computer-aided synthesis planning (CASP) tools…
Muhtasim Noor Alif, Khandakar Tanvir Ahmed, Sudipto Baul, Wei Zhang
Modern sequencing technologies can now capture multiple omic layers from the same biological system, but integrating these views into a coherent model is far from trivial. Graph-based deep learning has become an attractive strategy because it can represent complex molecular interactions and sample relationships in a…
Jinlei Han, Tuerhong Yushan, Juan Wang, Haitao Yang + 7 more
Most genomic foundation models are pretrained on independent linear assemblies and therefore do not explicitly represent population-level segment sharing or local graph connectivity. We developed TomatoPGFM, a graph-conditioned model pretrained on 54.65 Gb of sequence from 66 tomato (Solanum spp.) accessions. Sequence…
Authors not listed
Computational toxicology plays a pivotal role in modern drug discovery and environmental risk assessment; however, the reliability of predictive models on unseen chemical scaffolds remains a critical bottleneck. Deep learning architectures, despite their prevalence, are susceptible to ’silent failures’—yielding…
Kai-Yu Chan, Tatsuo Yamaguchi, Yoshihiro Izumiya, Yen-Wei Chu + 2 more
Protein interactions form large-scale networks known as protein-protein interaction networks (PPINs) or protein complex networks (PCNs). Extracting meaningful structural frameworks from these molecular relationships through mathematical modeling enables a deeper understanding of biological processes. Although static…
Authors not listed
Recent years have seen a growing interest in machine learning approaches for chemical tasks. The best existing methods focus on building base models that combine molecular graphs (“2D structures”) with atomic coordinates in 3D to predict molecular properties, typically through pre-training followed by fine-tuning on…
Authors not listed
Pharmacophores are widely used to describe protein-ligand interactions, and the Grids of Pharmacophore Interaction Fields (GRAIL) method extends this concept by representing binding pockets as interpretable sets of interaction type-specific pharmacophoric maps. In this work, we propose a hybrid framework for binding…
Authors not listed
Chemical data is fundamentally sparse, with molecular structures serving as database keys for countless properties. Current machine learning methods map structures to properties with remarkable accuracy, yet they do not leverage available property information when predicting unknowns, creating unutilized partial…