Filters








1,229 Hits in 3.5 sec

Meta-QSAR: a large-scale application of meta-learning to drug design and discovery

Ivan Olier, Noureddin Sadawi, G. Richard Bickerton, Joaquin Vanschoren, Crina Grosan, Larisa Soldatova, Ross D. King
2017 Machine Learning  
We then investigated the utility of algorithm selection for QSAR problems.  ...  We conclude that meta-learning outperforms base-learning methods for QSAR learning, and as this investigation is one of the most extensive ever comparisons of base and meta-learning methods ever made,  ...  reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.  ... 
doi:10.1007/s10994-017-5685-x pmid:31997851 pmcid:PMC6956898 fatcat:mjfqx65vi5hb5f4hysbcwicaea

Artificial intelligence paradigm for ligand-based virtual screening on the drug discovery of type 2 diabetes mellitus

Alhadi Bustamam, Haris Hamzah, Nadya A. Husna, Sarah Syarofina, Nalendra Dwimantara, Arry Yanuar, Devvi Sarwinda
2021 Journal of Big Data  
Feature selection in the fingerprint dataset using CatBoost is best used before making QSAR Classification and QSAR Regression models.  ...  K-modes clustering with Levenshtein distance was used for the selection method of molecules, and CatBoost was used for the feature selection method.  ...  Indonesia who contributed insights and expertise to advance this research in innumerable ways.  ... 
doi:10.1186/s40537-021-00465-3 fatcat:rfyznpfpqndl7jybtwu73u4cau

Evolutionary Computation and QSAR Research

Vanessa Aguiar-Pulido, Marcos Gestal, Maykel Cruz-Monteagudo, Juan Rabunal, Julian Dorado, Cristian Munteanu
2013 Current Computer - Aided Drug Design  
QSAR models, the current evolutionary feature selection methods and applications in QSAR and the future trend on the joint or multi-task feature selection methods. widely accepted assumption points toward  ...  Thus, this review explains the basic of the genetic algorithms and genetic programming as evolutionary computation approaches, the selection methods for highdimensional data in QSAR, the methods to build  ...  ACKNOWLEDGEMENTS Vanessa Aguiar-Pulido and Munteanu C.R. thank sponsorship from the "Plan I2C" and Isidro Parga Pondal research programs respectively, both funded by Xunta de Galicia (Spain) and the European  ... 
doi:10.2174/1573409911309020006 pmid:23700999 fatcat:zsipotcovzhlhg7wrgjfkc5wvu

A Comparative Study of the Performance for Predicting Biodegradability Classification: The Quantitative Structure–Activity Relationship Model vs the Graph Convolutional Network

Myeonghun Lee, Kyoungmin Min
2022 ACS Omega  
In addition, the performance of the models was further verified by randomly dividing the dataset into 100 different cases of training and test sets and by varying the test set ratio from 20 to 80%.  ...  A biodegradability dataset from previous studies was trained to generate prediction models by (i) the QSAR models using the Mordred molecular descriptor calculator and MACCS molecular fingerprint and (  ...  The dataset and the main source code used in this study are available at the GitHub page https://github.com/mhlee216/ Biodegradability_Prediction_QSAR_GCN.  ... 
doi:10.1021/acsomega.1c06274 pmid:35128273 pmcid:PMC8811760 fatcat:2o5kyifbtzcq3ciyjgv2k4f3we

Accelerating Big Data Quantitative Structure-Activity Prediction through LASSO-Random Forest Algorithm

Fahimeh Motamedi, Horacio Pérez-Sánchez, Alireza Mehridehnavi, Afshin Fassihi, Fahimeh Ghasemi, Jinbo Xu
2021 Bioinformatics  
First, to identify appropriate molecular descriptors by focusing on one feature-selection algorithms; and second to predict the biological activities of designed compounds.  ...  This algorithm is a regression model that selects a subset of molecular descriptors with the aim of enhancing prediction accuracy and interpretability because of removing inappropriate and irrelevant features  ...  Besides, choosing an appropriate feature selection technique is quite challenging and it is related to the features and observations.  ... 
doi:10.1093/bioinformatics/btab659 pmid:34601564 fatcat:ngjbrrdxrvbc5bri6jnj5ie6hy

Complex-Valued Neural Networks Training: A Particle Swarm Optimization Strategy

Mohammed E., Samah Refat
2016 International Journal of Advanced Computer Science and Applications  
Machine learning algorithms are important tools for QSAR analysis, as a result, they are integrated into the drug production process.  ...  This kind of relationship between molecular structure and change in biological activity is center of focus for QSAR modelling.  ...  And above all, God for His continuous guidance.  ... 
doi:10.14569/ijacsa.2016.070185 fatcat:gixxkqrmbrhldgqwxtgrpksc4q

MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics

María Jimena Martínez, Marina Razuc, Ignacio Ponzoni
2019 BioMed Research International  
The selection of the most relevant molecular descriptors to describe a target variable in the context of QSAR (Quantitative Structure-Activity Relationship) modelling is a challenging combinatorial optimization  ...  In this paper, a novel software tool for addressing this task in the context of regression and classification modelling is presented.  ...  Acknowledgments This work is kindly supported by CONICET, Grant PIP 112-2012-0100471, and UNS, Grants PGI 24/N042 and PGI 24/ZM17.  ... 
doi:10.1155/2019/2905203 fatcat:3irbz2k2avbttnkw4zei5yxohe

Inductive Queries for a Drug Designing Robot Scientist [chapter]

Ross D. King, Amanda Schierz, Amanda Clare, Jem Rowland, Andrew Sparkes, Siegfried Nijssen, Jan Ramon
2010 Inductive Databases and Constraint-Based Data Mining  
it, and we discuss the adaptation of machine learning and data mining algorithms to guide QSAR experiments.  ...  It is increasingly clear that machine learning algorithms need to be integrated in an iterative scientific discovery loop, in which data is queried repeatedly by means of inductive queries and where the  ...  In machine learning terms such QSAR learning is an example of "active learning" -where statistical/machine learning methods select examples they would like to examine next in order to optimise learning  ... 
doi:10.1007/978-1-4419-7738-0_18 fatcat:a4pvblyzljaffj5jrh5jkfim3u

Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning [article]

Sai Krishna Gottipati, Boris Sattarov, Sufeng Niu, Yashaswi Pathak, Haoran Wei, Shengchao Liu, Karam M. J. Thomas, Simon Blackburn, Connor W. Coley, Jian Tang, Sarath Chandar, Yoshua Bengio
2020 arXiv   pre-print
The proposed environment for drug discovery provides a highly challenging test-bed for RL algorithms owing to the large state space and high-dimensional continuous action space with hierarchical actions  ...  Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models.  ...  Acknowledgements The authors would like to thank Mohammad Amini for thoroughly reviewing the manuscript and Harry Zhao, Sitao Luan and Scott Fujimoto for useful discussions and feedback. 99andBeyond would  ... 
arXiv:2004.12485v2 fatcat:w2ews74xt5cwjm6mgfm3cucn4i

Feature Selection: An Assessment of Some Evolving Methodologies

A. Abdul Rasheed
2021 Turkish Journal of Computer and Mathematics Education  
Feature selection has predominant importance in various kinds of applications.  ...  The results are also discussed from the obtained features and the selected features with respect to the method chosen for study.  ...  Introduction In a predictive model, feature selection is considered as a process of selecting or choosing or reducing the number of attributes.  ... 
doi:10.17762/turcomat.v12i2.1802 fatcat:tjey2qqfw5ashoqaopnsnl6mia

An Improved Artificial Bee Colony for Feature Selection in QSAR

Yanhong Lin, Jing Wang, Xiaolin Li, Yuanzi Zhang, Shiguo Huang
2021 Algorithms  
In this paper, a binary ABC algorithm is used to select features (molecular descriptors) in QSAR.  ...  Furthermore, we propose an improved ABC-based algorithm for feature selection in QSAR, namely ABC-PLS-1.  ...  To improve the accuracy and interpretability of QSAR that is a regression and prediction problem, we apply ABC algorithm to feature selection in QSAR.  ... 
doi:10.3390/a14040120 fatcat:p7pxvieg3nbhro4p2b2nrrhwei

Using kNN Model for Automatic Feature Selection [chapter]

Gongde Guo, Daniel Neagu, Mark T. D. Cronin
2005 Lecture Notes in Computer Science  
This paper proposes a kNN model-based feature selection method aimed at improving the efficiency and effectiveness of the ReliefF method by: (1) using a kNN model as the starter selection, aimed at choosing  ...  both ordinal and nominal features; and (3) presenting a simple method of difference function calculation based on inductive information in each representative obtained by kNN model.  ...  Acknowledgment This work was supported partly by the EPSRC project PYTHIA -Predictive Toxicology Knowledge Representation and Processing Tool Based on a Hybrid Intelligent Systems Approach, Grant Reference  ... 
doi:10.1007/11551188_44 fatcat:fb6cbh3l6fg43faxnlx432h74m

Feature Selection Optimization using Hybrid Relief-f with Self-adaptive Differential Evolution

M Zainudin, Md Sulaiman, Norwati Mustapha, Thinagaran Perumal, Azree Nazri, Raihani Mohamed, Syaifulnizam Manaf
2017 International Journal of Intelligent Engineering and Systems  
Simple and powerful in implementation, we combined relief-f with DE in our proposed feature selection method to solving the optimization problem.  ...  The performance of proposed method is compared with several feature selection techniques in order to prove their superiority using ten datasets obtained from UCI machine learning repository.  ...  In addition, to find the best features, feature selection must interact with machine learning (ML) techniques [6] .  ... 
doi:10.22266/ijies2017.0430.03 fatcat:2bf4mdz3nfcl3ojhfxamdsl2am

An automated framework for QSAR model building

Samina Kausar, Andre O. Falcao
2018 Journal of Cheminformatics  
On average, about 19% of the prediction error was reduced by using feature selection producing an increase of 49% in the percentage of variance explained (PVE) compared to models without feature selection  ...  The best-optimized feature selection methodology in the developed workflow is able to remove 62-99% of all redundant data.  ...  Acknowlegements The authors gratefully acknowledge Fundação para a Ciência e Tecnologia for a doctoral Grant (SFRH/BD/111654/2015), MIMED Project Funding (PTDC/ EEI-ESS/4923/2014) and UID/CEC/00408/2013  ... 
doi:10.1186/s13321-017-0256-5 pmid:29340790 pmcid:PMC5770354 fatcat:swk5giifcfhcpd76d3tvt2xvxe

Machine Learning and Deep Learning in Chemical Health and Safety: A Systematic Review of Techniques and Applications

Zeren Jiao, Pingfan Hu, Hongfei Xu, Qingsheng Wang
2020 Journal of Chemical Health and Safety  
In this Review, commonly used ML/DL tools and concepts as well as popular ML/DL algorithms are introduced and discussed.  ...  Machine learning (ML) and deep learning (DL) are a subset of artificial intelligence (AI) that can automatically learn from data and can perform tasks such as predictions and decisionmaking.  ...  For descriptor selection, the QSAR studies also implement different feature selection methods such as random forest-based descriptor importance.  ... 
doi:10.1021/acs.chas.0c00075 fatcat:aldsumfj7bcazf4nkuhvoge7xm
« Previous Showing results 1 — 15 out of 1,229 results