Motif Prediction with Graph Neural Networks

Besta, Maciej; Grob, Raphael; Miglioli, Cesare; Bernold, Nicola; Kwasniewski, Grzegorz; Gabriel, Gjini,; Raghavendra, K.; Ashkboos, Saleh; Gianinazzi, Lukas; Dryden, Nikoli; Hoefler, Torsten

doi:10.1145/3534678.3539343

Cited by 13 publications

(3 citation statements)

References 280 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method achieves remarkable results on six popular benchmarks, including ranking first on ogbl-ppa, ogbl-citation2 and Pubmed. Lastly, note that link prediction is a special case of multi-node representation learning, which also includes triplet (Liu, Ma, and Li 2021), motif (Besta et al 2021), and subgraph (Alsentzer et al 2020) tasks, among others. Theoretically, our method is also applicable to these tasks.…”

Section: Discussionmentioning

confidence: 99%

Structural Information Enhanced Graph Representation for Link Prediction

Shi,

Hu,

Zhao

et al. 2024

AAAI

View full text Add to dashboard Cite

Link prediction is a fundamental task of graph machine learning, and Graph Neural Network (GNN) based methods have become the mainstream approach due to their good performance. However, the typical practice learns node representations through neighborhood aggregation, lacking awareness of the structural relationships between target nodes. Recently, some methods have attempted to address this issue by node labeling tricks. However, they still rely on the node-centric neighborhood message passing of GNNs, which we believe involves two limitations in terms of information perception and transmission for link prediction. First, it cannot perceive long-range structural information due to the restricted receptive fields. Second, there may be information loss of node-centric model on link-centric task. In addition, we empirically find that the neighbor node features could introduce noise for link prediction. To address these issues, we propose a structural information enhanced link prediction framework, which involves removing the neighbor node features while fitting neighborhood graph structures more focused through GNN. Furthermore, we introduce Binary Structural Transformer (BST) to encode the structural relationships between target nodes, complementing the deficiency of GNN. Our approach achieves remarkable results on multiple popular benchmarks, including ranking first on ogbl-ppa, ogbl-citation2 and Pubmed.

show abstract

Section: Discussionmentioning

confidence: 99%

Structural Information Enhanced Graph Representation for Link Prediction

Shi,

Hu,

Zhao

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Thus, motif mining plays a crucial role in identifying protein-binding sites on DNA or RNA, aiding in understanding gene regulation and control mechanisms. Several machine learning-based methods have been developed for motif detection [29][30][31]. In addition to simulation-based methods, some approaches utilize experimental mutation information (nucleotide substitutions) for aptamer candidate discovery [25,27].…”

Section: Introductionmentioning

confidence: 99%

De novo design and optimization of aptamers with AptaDiff

Wang,

Liu,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Aptamers are single-strand nucleic acid ligands, featuring high affinity and specificity to target molecules. Traditionally they are identified from large DNA/RNA libraries using in vitro methods, like Systematic Evolution of Ligands by Exponential Enrichment (SELEX). However, these libraries capture only a small fraction of theoretical sequence space, and various aptamer candidates are constrained by actual sequencing capabilities from the experiment. Addressing this, we proposed AptaDiff, the first in silico aptamer design and optimization method based on the diffusion model. Our Aptadiff can generate aptamers beyond the constraints of high-throughput sequencing data, leveraging motif-dependent latent embeddings from variational autoencoder, and can optimize aptamers by affinity-guided aptamer generation according to Bayesian optimization. Comparative evaluations revealed AptaDiff’s superiority over existing aptamer generation methods in terms of quality and fidelity across four high-throughput screening data targeting distinct proteins. Moreover, Surface Plasmon Resonance (SPR) experiments were conducted to validate the binding affinity of aptamers generated through Bayesian optimization for two target proteins. The results unveiled a significant boost of 87.9% and 60.2% in RU values1, along with a 3.6-fold and 2.4-fold decrease in KD values2for the respective target proteins. Notably, the optimized aptamers demonstrated superior binding affinity compared to top experimental candidates selected through SELEX, underscoring the promising outcomes of our AptaDiff in accelerating the discovery of superior aptamers.

show abstract

“…Its growing prevalence in recommendation systems [20,53], drug discovery [33,43], and financial risk control [10,40] urges the development of a correspondent graph analysis tool. Graph Neural Networks (GNNs) emerge as a promising approach to achieve state-of-the-art performance in node-level [23,48,58], edge-level [4,6,56], and graph-level [37,44,51] downstream tasks.…”

Section: Introductionmentioning

confidence: 99%

FedGTA: Topology-Aware Averaging for Federated Graph Learning

Li,

Wu,

Zhang

et al. 2023

Proc. VLDB Endow.

View full text Add to dashboard Cite

Federated Graph Learning (FGL) is a distributed machine learning paradigm that enables collaborative training on large-scale subgraphs across multiple local systems. Existing FGL studies fall into two categories: (i) FGL Optimization, which improves multi-client training in existing machine learning models; (ii) FGL Model, which enhances performance with complex local models and multi-client interactions. However, most FGL optimization strategies are designed specifically for the computer vision domain and ignore graph structure, presenting dissatisfied performance and slow convergence. Meanwhile, complex local model architectures in FGL Models studies lack scalability for handling large-scale subgraphs and have deployment limitations. To address these issues, we propose Federated Graph Topology-aware Aggregation (FedGTA), a personalized optimization strategy that optimizes through topology-aware local smoothing confidence and mixed neighbor features. During experiments, we deploy FedGTA in 12 multi-scale real-world datasets with the Louvain and Metis split. This allows us to evaluate the performance and robustness of FedGTA across a range of scenarios. Extensive experiments demonstrate that FedGTA achieves state-of-the-art performance while exhibiting high scalability and efficiency. The experiment includes ogbn-papers100M, the most representative large-scale graph database so that we can verify the applicability of our method to large-scale graph learning. To the best of our knowledge, our study is the first to bridge large-scale graph learning with FGL using this optimization strategy, contributing to the development of efficient and scalable FGL methods.

show abstract

Motif Prediction with Graph Neural Networks

Cited by 13 publications

References 280 publications

Structural Information Enhanced Graph Representation for Link Prediction

Structural Information Enhanced Graph Representation for Link Prediction

De novo design and optimization of aptamers with AptaDiff

FedGTA: Topology-Aware Averaging for Federated Graph Learning

Contact Info

Product

Resources

About