Filters








4,024 Hits in 5.0 sec

Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery [article]

Zhengyang Wang, Meng Liu, Youzhi Luo, Zhao Xu, Yaochen Xie, Limei Wang, Lei Cai, Qi Qi, Zhuoning Yuan, Tianbao Yang, Shuiwang Ji
2021 arXiv   pre-print
Specifically, we represent molecules as both graphs and sequences. Built on these representations, we develop novel deep models for learning from molecular graphs and sequences.  ...  With the advances of deep learning methods, computational approaches for predicting molecular properties are gaining increasing momentum.  ...  graph neural network framework 32 .  ... 
arXiv:2012.01981v3 fatcat:oldovpd55rbevbjtwdahueb4mm

Describe Molecules by a Heterogeneous Graph Neural Network with Transformer-like Attention for Supervised Property Predictions

Daiguo Deng, Zengrong Lei, Xiaobin Hong, Ruochi Zhang, Fengfeng Zhou
2022 ACS Omega  
A geometric graph could describe a molecular structure with atoms as the nodes and bonds as the edges. Therefore, a graph neural network may be trained to better represent a molecular structure.  ...  Machine learning and deep learning have facilitated various successful studies of molecular property predictions.  ...  We created a new molecular heterogeneity setting for the graph neural network, including 11 types of nodes and 4 types of chemical bonds.  ... 
doi:10.1021/acsomega.1c06389 pmid:35128279 pmcid:PMC8811943 fatcat:bslay4atnjg6tnursq4mzgowju

InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization [article]

Fan-Yun Sun, Jordan Hoffmann, Vikas Verma, Jian Tang
2020 arXiv   pre-print
This paper studies learning the representations of whole graphs in both unsupervised and semi-supervised scenarios.  ...  with state-of-the-art semi-supervised models.  ...  state-ofart methods on molecular property prediction tasks using semi-supervised learning.  ... 
arXiv:1908.01000v3 fatcat:hty2enrcivgttoafunwv2ajjma

Artificial Intelligence in Drug Discovery: Applications and Techniques [article]

Jianyuan Deng, Zhibo Yang, Iwao Ojima, Dimitris Samaras, Fusheng Wang
2021 arXiv   pre-print
In this survey, we first give an overview on drug discovery and discuss related applications, which can be reduced to two major tasks, i.e., molecular property prediction and molecule generation.  ...  We also provide a GitHub repository (https://github.com/dengjianyuan/Survey_AI_Drug_Discovery) with the collection of papers and codes, if applicable, as a learning resource, which is regularly updated  ...  The neural networks templates are from Visuals by dair.ai (https://github.com/dair-ai/ml-visuals). Supporting Information Available https://github.com/dengjianyuan/Survey AI Drug Discovery  ... 
arXiv:2106.05386v4 fatcat:w2at5y5jyffrxiejsupmwiimhq

A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications [article]

Jun Xia, Yanqiao Zhu, Yuanqi Du, Stan Z. Li
2022 arXiv   pre-print
In this paper, we provide the first comprehensive survey for PGMs. We firstly present the limitations of graph representation learning and thus introduce the motivation for graph pre-training.  ...  The knowledge implicitly encoded in model parameters can benefit various downstream tasks and help to alleviate several fundamental issues of learning on graphs.  ...  However, there are still many non-Euclidean graph datasets in real-world applications such as social networks and biochemical graphs which existing neural networks can not handle with.  ... 
arXiv:2202.07893v2 fatcat:vidcathokrfibe53yuc3xaihzy

Deep learning for drug repurposing: methods, databases, and applications [article]

Xiaoqin Pan, Xuan Lin, Dongsheng Cao, Xiangxiang Zeng, Philip S. Yu, Lifang He, Ruth Nussinov, Feixiong Cheng
2022 arXiv   pre-print
In this review, we introduce guidelines on how to utilize deep learning methodologies and tools for drug repurposing.  ...  Next, we discuss recently developed sequence-based and graph-based representation approaches as well as state-of-the-art deep learning-based methods.  ...  Graph Convolutional Network (GCN) [83] is an approach for semi-supervised learning on graphstructured data.  ... 
arXiv:2202.05145v1 fatcat:5oqujy2daffdpa33b4cbrg6hqy

Machine learning in chemoinformatics and drug discovery

Yu-Chen Lo, Stefano E. Rensi, Wen Torng, Russ B. Altman
2018 Drug Discovery Today  
Here, we present basic principles and recent case studies to demonstrate the utility of machine learning techniques in chemoinformatics analyses; and we discuss limitations and future directions to guide  ...  With the rapid explosion of chemical 'big' data from HTS and combinatorial synthesis, machine learning has become an indispensable tool for drug designers to mine chemical information from large compound  ...  Supervised machine learning models include regression analysis, k-nearest neighbor (kNN), Bayesian probabilistic learning, SVMs, random forests and neural networks.  ... 
doi:10.1016/j.drudis.2018.05.010 pmid:29750902 pmcid:PMC6078794 fatcat:ckxznjxuujajle6iqycgi74d7i

Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

Jiarui Chen, Yain-Whar Si, Chon-Wai Un, Shirley W. I. Siu
2021 Journal of Cheminformatics  
Inspired by the success of semi-supervised learning (SSL) algorithms, we propose a Graph Convolution Neural Network (GCN) to predict chemical toxicity and trained the network by the Mean Teacher (MT) SSL  ...  While traditional machine learning (ML) methods have been used in the field with some success, the limited availability of annotated toxicity data is the major hurdle for further improving model performance  ...  A solution for machine learning on non-Euclidean data is Graph Convolutional Neural Network (GCN) [22] .  ... 
doi:10.1186/s13321-021-00570-8 pmid:34838140 pmcid:PMC8627024 fatcat:sddotck6incb3ibddh7ybasptm

Graph Neural Network Based Coarse-Grained Mapping Prediction [article]

Zhiheng Li, Geemi P. Wellawatte, Maghesree Chakraborty, Heta A. Gandhi, Chenliang Xu, Andrew D. White
2020 arXiv   pre-print
We present a graph neural network based CG mapping predictor called DEEP SUPERVISED GRAPH PARTITIONING MODEL(DSGPM) that treats mapping operators as a graph segmentation problem.  ...  DSGPM is trained on a novel dataset, Human-annotated Mappings (HAM), consisting of 1,206 molecules with expert annotated mapping operators.  ...  We thank the Center for Integrated Research Computing at the University of Rochester for providing the computational resources required to complete this study.  ... 
arXiv:2007.04921v2 fatcat:onui4ecadjbb7h727xilzvk3oq

Graph Neural Networks: Methods, Applications, and Opportunities [article]

Lilapati Waikhom, Ripon Patgiri
2021 arXiv   pre-print
This article provides a comprehensive survey of graph neural networks (GNNs) in each learning setting: supervised, unsupervised, semi-supervised, and self-supervised learning.  ...  Taxonomy of each graph based learning setting is provided with logical divisions of methods falling in the given learning setting.  ...  APPLICATIONS Standard neural networks work on an array, whereas GNN works on graphs.  ... 
arXiv:2108.10733v2 fatcat:j3rfmkiwenebvmfyboasjmx4nu

MONN: a Multi-Objective Neural Network for Predicting Pairwise Non-Covalent Interactions and Binding Affinities between Compounds and Proteins [article]

Shuya Li, Fangping Wan, Hantao Shu, Tao Jiang, Dan Zhao, Jianyang Zeng
2019 bioRxiv   pre-print
MONN uses convolution neural networks on molecular graphs of compounds and primary sequences of proteins to effectively capture the intrinsic features from both inputs, and also takes advantage of the  ...  Comprehensive evaluation demonstrated that while the previous neural attention based approaches fail to exhibit satisfactory interpretability results without extra supervision, MONN can successfully predict  ...  affinity value a ∈ R. protein pair, a graph convolution module and a convolution neural network (CNN) module are first used to extract the atom and residue features from the input molecular graph and  ... 
doi:10.1101/2019.12.30.891515 fatcat:ed64rsta3bb2pekrf7ik5a232u

Unsupervised Learning in Drug Design from Self-Organization to Deep Chemistry

Jaroslaw Polanski
2022 International Journal of Molecular Sciences  
The recent success of Deep Learning (DL) has inspired a renaissance of neural networks for their potential application in deep chemistry.  ...  Neural networks (NN) were an early tool that cheminformatics tested for converting data into drugs. However, the initial interest faded for almost two decades.  ...  Self-Organizing Mapping of Molecular Representations Basically, neural networks (NN) are computer algorithms based on an alleged similarity to the human brain.  ... 
doi:10.3390/ijms23052797 pmid:35269939 pmcid:PMC8910896 fatcat:yhd7sglydnfrvlk5i7p2wkybe4

A Supervised Approach to 3D Structural Classification of Proteins [chapter]

Virginio Cantoni, Alessio Ferone, Alfredo Petrosino, Gabriella Sanniti di Baja
2013 Lecture Notes in Computer Science  
In this paper we propose to employ a recently presented structural representation of the proteins and exploit the learning capabilities of the graph neural network model to perform the classification task  ...  A more general supervised neural network model, is called Graph Neural Network (GNN).  ...  Protein 1MK5 Graph Neural Networks In the recent years, many powerful machine learning methods have been developed to deal with one dimensional data, even though more complex data structures can be employed  ... 
doi:10.1007/978-3-642-41190-8_35 fatcat:qurcb3basfbwrmh6ibg23cirz4

Self-Supervised Graph Transformer on Large-Scale Molecular Data [article]

Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbing Huang, Junzhou Huang
2020 arXiv   pre-print
Recent researches abstract molecules as graphs and employ Graph Neural Networks (GNNs) for molecular representation learning.  ...  With carefully designed self-supervised tasks in node-, edge- and graph-level, GROVER can learn rich structural and semantic information of molecules from enormous unlabelled molecular data.  ...  Therefore, supervised deep learning of graphs, especially with Graph Neural Networks(GNNs) [25, 46] have shown promising results in many tasks, such as molecular property prediction [13, 23] and virtual  ... 
arXiv:2007.02835v2 fatcat:eslpqc752jeyhf7doif7dunyke

Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction [article]

Yingheng Wang, Yaosen Min, Xin Chen, Ji Wu
2020 arXiv   pre-print
MIRACLE treats a DDI network as a multi-view graph where each node in the interaction graph itself is a drug molecular graph instance.  ...  We use GCNs and bond-aware attentive message passing networks to encode DDI relationships and drug molecular graphs in the MIRACLE learning stage, respectively.  ...  Recently, graph-based methods like neural fingerprint [6] , message passing network [9] and graph representation learning [11] have proved to be successful on molecular tasks, several graph neural  ... 
arXiv:2010.11711v2 fatcat:ryzrp7rosnblhc3bpcgnrmvxp4
« Previous Showing results 1 — 15 out of 4,024 results