Molformer: Motif-Based Transformer on 3D Heterogeneous Molecular Graphs
نویسندگان
چکیده
Procuring expressive molecular representations underpins AI-driven molecule design and scientific discovery. The research mainly focuses on atom-level homogeneous graphs, ignoring the rich information in subgraphs or motifs. However, it has been widely accepted that substructures play a dominant role identifying determining properties. To address such issues, we formulate heterogeneous graphs (HMGs) introduce novel architecture to exploit both motifs 3D geometry. Precisely, extract functional groups as for small molecules employ reinforcement learning adaptively select quaternary amino acids motif candidates proteins. Then HMGs are constructed with motif-level nodes. better accommodate those HMGs, variant of Transformer named Molformer, which adopts self-attention layer distinguish interactions between multi-level Besides, is also coupled multi-scale mechanism capture fine-grained local patterns increasing contextual scales. An attentive farthest point sampling algorithm proposed obtain representations. We validate Molformer across broad range domains, including quantum chemistry, physiology, biophysics. Extensive experiments show outperforms achieves comparable performance several state-of-the-art baselines. Our work provides promising way utilize informative from perspective graph construction. code available at https://github.com/smiles724/Molformer.
منابع مشابه
Motif-based Convolutional Neural Network on Graphs
This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to model the key properties of local connectivity and translation invariance, using highorder connection patterns or motifs. We develop a novel deep architecture ...
متن کاملVoter model on heterogeneous graphs.
We study the voter model on heterogeneous graphs. We exploit the nonconservation of the magnetization to characterize how consensus is reached. For a network of N nodes with an arbitrary but uncorrelated degree distribution, the mean time to reach consensus T(N) scales as Nmu(2)1/mu(2), where mu(k) is the kth moment of the degree distribution. For a power-law degree distribution n(k) approximat...
متن کاملWind Turbine Transformer Optimum Design Assuming a 3D Wound Core
A wind turbine transformer (WTT) is designed using a 3D wound core while the transformer’s total owning cost (TOC) and its inrush current performance realized as the two objective functions in a multi-objective optimization process. Multi-objective genetic algorithm is utilized to derive Pareto optimal solutions. The effects of inrush current improvement on other operating and design parameters...
متن کاملMotif-Based Attack Detection in Network Communication Graphs
We propose an original approach which allows the characterization of network communication graphs with the network motifs. As an example we checked our approach by the use of network topology analysis methods applied to communication graphs. We have tested our approach on a simulated attacks inside a scale-free network and data gathered in real networks, showing that the motif distribution refl...
متن کاملMotifNet: a motif-based Graph Convolutional Network for directed graphs
Deep learning on graphs and in particular, graph convolutional neural networks, have recently attracted significant attention in the machine learning community. Many of such techniques explore the analogy between the graph Laplacian eigenvectors and the classical Fourier basis, allowing to formulate the convolution as a multiplication in the spectral domain. One of the key drawback of spectral ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2023
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v37i4.25662