Inside the atoms

Ni, Jingchao; Tong, Hanghang; Wang, Fan; Zhang, Xiang

doi:10.1145/2623330.2623643

Cited by 50 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome the limitation of prior efforts on isolated graph analysis, in recent years, increasing research efforts have been focused on interdependent networks and their applications. For example, Ni et al employed interdependent networks to illustrate the academic influence of scholars based on their research area and publications [34]. Laird et al studied the interdependent relationship between cancer pain and depression [23].…”

Section: Related Workmentioning

confidence: 99%

“…And since all the edges in these interdependent networks indicate causal dependencies, we further call it interdependent causal networks. Interdependent networks have been widely used in the study of various topics, including the academic influence of scholars [34], the spreading pattern of rumors in the complex social network [32], and etc. However, existing methods only consider physical or statistical correlations, but not causation, and thus cannot be directly applied for locating root causes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Graph Neural Networks for Causal Discovery and Root Cause Localization

Wang¹,

Chen²,

Ni³

et al. 2023

Preprint

View full text Add to dashboard Cite

The goal of root cause analysis is to identify the underlying causes of system problems by discovering and analyzing the causal structure from system monitoring data. It is indispensable for maintaining the stability and robustness of large-scale complex systems. Existing methods mainly focus on the construction of a single effective isolated causal network, whereas many real-world systems are complex and exhibit interdependent structures (i.e., multiple networks of a system are interconnected by cross-network links). In interdependent networks, the malfunctioning effects of problematic system entities can propagate to other networks or different levels of system entities. Consequently, ignoring the interdependency results in suboptimal root cause analysis outcomes.In this paper, we propose REASON, a novel framework that enables the automatic discovery of both intra-level (i.e., withinnetwork) and inter-level (i.e., across-network) causal relationships for root cause localization. REASON consists of Topological Causal Discovery and Individual Causal Discovery. The Topological Causal Discovery component aims to model the fault propagation in order to trace back to the root causes. To achieve this, we propose novel hierarchical graph neural networks to construct interdependent causal networks by modeling both intra-level and inter-level nonlinear causal relations. Based on the learned interdependent causal networks, we then leverage random walk with restarts to model the network propagation of a system fault. The Individual Causal Discovery component focuses on capturing abrupt change patterns of a single system entity. This component examines the temporal patterns of each entity's metric data (i.e., time series), and estimates its likelihood of being a root cause based on the Extreme Value theory. Combining the topological and individual causal scores, the top 𝐾 system entities are identified as root causes. Extensive experiments on three real-world datasets with case studies demonstrate the effectiveness and superiority of the proposed framework.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hierarchical Graph Neural Networks for Causal Discovery and Root Cause Localization

Wang¹,

Chen²,

Ni³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…GoG, also known as Network of Networks, is a special graph where the nodes in the top-level graph are also graphs. , GoGs can be constructed naturally by connecting independent lower level graphs by predefined associations, or similarity can be measured by a graph kernel . GoG can also emerge from partitioning a large graph into different subgraphs based on topology or predefined rules.…”

Section: Introductionmentioning

confidence: 99%

EGGNet, a Generalizable Geometric Deep Learning Framework for Protein Complex Pose Scoring

Wang,

Brand,

Adolf-Bryfogle

et al. 2024

ACS Omega

View full text Add to dashboard Cite

Computational prediction of molecule−protein interactions has been key for developing new molecules to interact with a target protein for therapeutics development. Previous work includes two independent streams of approaches: (1) predicting protein−protein interactions (PPIs) between naturally occurring proteins and (2) predicting binding affinities between proteins and small-molecule ligands [also known as drug−target interaction (DTI)]. Studying the two problems in isolation has limited the ability of these computational models to generalize across the PPI and DTI tasks, both of which ultimately involve noncovalent interactions with a protein target. In this work, we developed Equivariant Graph of Graphs neural Network (EGGNet), a geometric deep learning (GDL) framework, for molecule−protein binding predictions that can handle three types of molecules for interacting with a target protein: (1) small molecules, (2) synthetic peptides, and (3) natural proteins. EGGNet leverages a graph of graphs (GoG) representation constructed from the molecular structures at atomic resolution and utilizes a multiresolution equivariant graph neural network to learn from such representations. In addition, EGGNet leverages the underlying biophysics and makes use of both atom-and residue-level interactions, which improve EGGNet's ability to rank candidate poses from blind docking. EGGNet achieves competitive performance on both a public protein− small-molecule binding affinity prediction task (80.2% top 1 success rate on CASF-2016) and a synthetic protein interface prediction task (88.4% area under the precision−recall curve). We envision that the proposed GDL framework can generalize to many other protein interaction prediction problems, such as binding site prediction and molecular docking, helping accelerate protein engineering and structure-based drug development.

show abstract

“…GoG, also known as Network of Networks (NoN), is a special graph where the nodes in the top-level graph are also graphs [2, 3]. GoGs can be constructed naturally by connecting independent lower-level graphs by pre-defined associations [4], or similarity measured by a graph kernel [5].…”

Section: Introductionmentioning

confidence: 99%

EGGNet, a generalizable geometric deep learning framework for protein complex pose scoring

Wang

Brand

Adolf-Bryfogle

et al. 2023

Preprint

View full text Add to dashboard Cite

Computational prediction of molecule-protein interactions has been key for developing new molecules to interact with a target protein for therapeutics development. Literature includes two independent streams of approaches: (1) predicting protein-protein interactions between naturally occurring proteins and (2) predicting the binding affinities between proteins and small molecule ligands (aka drug target interaction, or DTI). Studying the two problems in isolation has limited computational models' ability to generalize across tasks, both of which ultimately involve non- covalent interactions with a protein target. In this work, we developed Equivariant Graph of Graphs neural Network (EGGNet), a geometric deep learning framework for molecule-protein binding predictions that can handle three types of molecules for interacting with a target protein: (1) small molecules, (2) synthetic peptides and (3) natural proteins. EGGNet leverages a graph of graphs (GoGs) representation constructed from the molecule structures at atomic-resolution and utilizes a multi-resolution equivariant graph neural network (GNN) to learn from such representations. In addition, EGGNet gets inspired by biophysics and makes use of both atom- and residue-level interactions, which greatly improve EGGNet's ability to rank candidate poses from blind docking. EGGNet achieves competitive performance on both a public protein-small molecule binding affinity prediction task (80.2% top-1 success rate on CASF-2016) and an synthetic protein interface prediction task (88.4% AUPR). We envision that the proposed geometric deep learning framework can generalize to many other protein interaction prediction problems, such as binding site prediction and molecular docking, helping to accelerate protein engineering and structure-based drug development.

show abstract

Inside the atoms

Cited by 50 publications

References 35 publications

Hierarchical Graph Neural Networks for Causal Discovery and Root Cause Localization

Hierarchical Graph Neural Networks for Causal Discovery and Root Cause Localization

EGGNet, a Generalizable Geometric Deep Learning Framework for Protein Complex Pose Scoring

EGGNet, a generalizable geometric deep learning framework for protein complex pose scoring

Contact Info

Product

Resources

About