Trustworthy Graph Neural Networks: Aspects, Methods and Trends DOI Creative Commons
He Zhang,

Bang Ye Wu,

Xingliang Yuan

et al.

arXiv (Cornell University), Journal Year: 2022, Volume and Issue: unknown

Published: Jan. 1, 2022

Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation systems and question answering to cutting-edge technologies such drug discovery in life sciences n-body simulation astrophysics. However, task performance is not the only requirement GNNs. Performance-oriented GNNs exhibited potential adverse effects vulnerability adversarial attacks, unexplainable discrimination against disadvantaged groups, or excessive resource consumption edge computing environments. To avoid these unintentional harms, it necessary build characterised by trustworthiness. this end, we propose comprehensive roadmap trustworthy view various involved. In survey, introduce basic concepts comprehensively summarise existing efforts six aspects, including robustness, explainability, privacy, fairness, accountability, environmental well-being. Additionally, highlight intricate cross-aspect relations between above aspects Finally, present thorough overview trending directions facilitating research industrialisation

Language: Английский

A roadmap for multi-omics data integration using deep learning DOI
Mingon Kang, Euiseong Ko, Tesfaye B. Mersha

et al.

Briefings in Bioinformatics, Journal Year: 2021, Volume and Issue: 23(1)

Published: Oct. 7, 2021

Abstract High-throughput next-generation sequencing now makes it possible to generate a vast amount of multi-omics data for various applications. These have revolutionized biomedical research by providing more comprehensive understanding the biological systems and molecular mechanisms disease development. Recently, deep learning (DL) algorithms become one most promising methods in analysis, due their predictive performance capability capturing nonlinear hierarchical features. While integrating translating into useful functional insights remain biggest bottleneck, there is clear trend towards incorporating analysis help explain complex relationships between layers. Multi-omics role improve prevention, early detection prediction; monitor progression; interpret patterns endotyping; design personalized treatments. In this review, we outline roadmap integration using DL offer practical perspective advantages, challenges barriers implementation data.

Language: Английский

Citations

205
A Comprehensive Overview of Globally Approved JAK Inhibitors DOI Creative Commons
Ahmed M. Shawky, Faisal A. Almalki, Ashraf N. Abdalla

et al.

Pharmaceutics, Journal Year: 2022, Volume and Issue: 14(5), P. 1001 - 1001

Published: May 6, 2022

Janus kinase (JAK) is a family of cytoplasmic non-receptor tyrosine kinases that includes four members, namely JAK1, JAK2, JAK3, and TYK2. The JAKs transduce cytokine signaling through the JAK-STAT pathway, which regulates transcription several genes involved in inflammatory, immune, cancer conditions. Targeting JAK with small-molecule inhibitors has proved to be effective treatment different types diseases. In current review, eleven received approval for clinical use have been discussed. These drugs are abrocitinib, baricitinib, delgocitinib, fedratinib, filgotinib, oclacitinib, pacritinib, peficitinib, ruxolitinib, tofacitinib, upadacitinib. aim review was provide an integrated overview chemical pharmacological data globally approved inhibitors. synthetic routes were described. addition, their inhibitory activities against uses also explained. Moreover, crystal structures summarized, primary focus on binding modes interactions. proposed metabolic pathways metabolites these illustrated. To sum up, could help design new potential therapeutic benefits inflammatory autoimmune

Language: Английский

Citations

205
Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii DOI
Gary Liu, Denise B. Catacutan, Khushi Rathod

et al.

Nature Chemical Biology, Journal Year: 2023, Volume and Issue: 19(11), P. 1342 - 1350

Published: May 25, 2023

Language: Английский

Citations

188
Chemprop: A Machine Learning Package for Chemical Property Prediction DOI Creative Commons
Esther Heid, Kevin P. Greenman, Yunsie Chung

et al.

Journal of Chemical Information and Modeling, Journal Year: 2023, Volume and Issue: 64(1), P. 9 - 17

Published: Dec. 26, 2023

Deep learning has become a powerful and frequently employed tool for the prediction of molecular properties, thus creating need open-source versatile software solutions that can be operated by nonexperts. Among current approaches, directed message-passing neural networks (D-MPNNs) have proven to perform well on variety property tasks. The package Chemprop implements D-MPNN architecture offers simple, easy, fast access machine-learned properties. Compared its initial version, we present multitude new functionalities such as support multimolecule reactions, atom/bond-level spectra. Further, incorporate various uncertainty quantification calibration methods along with related metrics pretraining transfer workflows, improved hyperparameter optimization, other customization options concerning loss functions or atom/bond features. We benchmark models trained using reaction, atom-level, spectra functionality data sets, including MoleculeNet SAMPL, observe state-of-the-art performance water-octanol partition coefficients, reaction barrier heights, atomic partial charges, absorption enables out-of-the-box training problem settings in fast, user-friendly, software.

Language: Английский

Citations

167
Leveraging artificial intelligence in the fight against infectious diseases DOI Open Access
Felix Wong, César de la Fuente‐Núñez, James J. Collins

et al.

Science, Journal Year: 2023, Volume and Issue: 381(6654), P. 164 - 170

Published: July 13, 2023

Despite advances in molecular biology, genetics, computation, and medicinal chemistry, infectious disease remains an ominous threat to public health. Addressing the challenges posed by pathogen outbreaks, pandemics, antimicrobial resistance will require concerted interdisciplinary efforts. In conjunction with systems synthetic artificial intelligence (AI) is now leading rapid progress, expanding anti-infective drug discovery, enhancing our understanding of infection accelerating development diagnostics. this Review, we discuss approaches for detecting, treating, diseases, underscoring progress supported AI each case. We suggest future applications how it might be harnessed help control outbreaks pandemics.

Language: Английский

Citations

156
Machine learning for antimicrobial peptide identification and design DOI
Fangping Wan, Felix Wong, James J. Collins

et al.

Nature Reviews Bioengineering, Journal Year: 2024, Volume and Issue: 2(5), P. 392 - 407

Published: Feb. 26, 2024

Language: Английский

Citations

52
Machine learning in preclinical drug discovery DOI
Denise B. Catacutan,

Jeremie Alexander,

Autumn Arnold

et al.

Nature Chemical Biology, Journal Year: 2024, Volume and Issue: 20(8), P. 960 - 973

Published: July 19, 2024

Language: Английский

Citations

45
A dual graph neural network for drug–drug interactions prediction based on molecular structure and interactions DOI Creative Commons

Mei Ma,

Xiujuan Lei

PLoS Computational Biology, Journal Year: 2023, Volume and Issue: 19(1), P. e1010812 - e1010812

Published: Jan. 26, 2023

Expressive molecular representation plays critical roles in researching drug design, while effective methods are beneficial to learning representations and solving related problems discovery, especially for drug-drug interactions (DDIs) prediction. Recently, a lot of work has been put forward using graph neural networks (GNNs) forecast DDIs learn representations. However, under the current GNNs structure, majority approaches from one-dimensional string or two-dimensional interaction information between chemical substructure remains rarely explored, it is neglected identify key substructures that contribute significantly Therefore, we proposed dual network named DGNN-DDI features by structure interactions. Specifically, first designed directed message passing with attention mechanism (SA-DMPNN) adaptively extract substructures. Second, order improve final features, separated into pairwise each drug’s unique Then, adopted predict probability DDI tuple. We evaluated DGNN–DDI on real-world dataset. Compared state-of-the-art methods, model improved prediction performance. also conducted case study existing drugs aiming combinations may be novel coronavirus disease 2019 (COVID-19). Moreover, visual interpretation results proved was sensitive able detect DDIs. These advantages demonstrated method enhanced performance capability modeling.

Language: Английский

Citations

44
Trustworthy Graph Neural Networks: Aspects, Methods, and Trends DOI
He Zhang,

Bang Ye Wu,

Xingliang Yuan

et al.

Proceedings of the IEEE, Journal Year: 2024, Volume and Issue: 112(2), P. 97 - 139

Published: Feb. 1, 2024

Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications such recommendation systems and question answering to cutting-edge technologies drug discovery in life sciences n-body simulation astrophysics. However, task performance is not the only requirement GNNs. Performance-oriented GNNs exhibited potential adverse effects, vulnerability adversarial attacks, unexplainable discrimination against disadvantaged groups, or excessive resource consumption edge computing environments. To avoid these unintentional harms, it necessary build characterized by trustworthiness. this end, we propose comprehensive roadmap trustworthy view various involved. In survey, introduce basic concepts comprehensively summarize existing efforts six aspects, including robustness, explainability, privacy, fairness, accountability, environmental well-being. addition, highlight intricate cross-aspect relations between above aspects Finally, present thorough overview trending directions facilitating research industrialization

Language: Английский

Citations

31
DeepDrug as an expert guided and AI driven drug repurposing methodology for selecting the lead combination of drugs for Alzheimer’s disease DOI Creative Commons
Victor O. K. Li, Yang Han,

Tushar Kaistha

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 15, 2025

Language: Английский

Citations

2