102 Hits in 7.5 sec

Robust optimization of SVM hyperparameters in the classification of bioactive compounds

Wojciech M Czarnecki, Sabina Podlewska, Andrzej J Bojarski
2015 Journal of Cheminformatics  
Results: In this study, we investigated the Bayesian and random search optimization of Support Vector Machine hyperparameters for classifying bioactive compounds.  ...  Although it can be extremely effective in finding new potentially active compounds, its application requires the optimization of the hyperparameters with which the assessment is being run, particularly  ...  Acknowledgements The study was partially supported by a Grant OPUS 2014/13/B/ST6/01792 financed by the Polish National Science Centre ( and by the Statutory Funds of the Institute  ... 
doi:10.1186/s13321-015-0088-0 pmid:26273325 pmcid:PMC4534515 fatcat:44xmljteznhvnktxmre54hh5ui

Machine Learning Enables Accurate and Rapid Prediction of Active Molecules Against Breast Cancer Cells

Shuyun He, Duancheng Zhao, Yanle Ling, Hanxuan Cai, Yike Cai, Jiquan Zhang, Ling Wang
2021 Frontiers in Pharmacology  
Breast cancer (BC) has surpassed lung cancer as the most frequently occurring cancer, and it is the leading cause of cancer-related death in women.  ...  In this study, we first collected a series of structurally diverse datasets consisting of 33,757 active and 21,152 inactive compounds for 13 breast cancer cell lines and one normal breast cell line commonly  ...  ACKNOWLEDGMENTS We acknowledge the use of computational resources from the SCUT supercomputing platform.  ... 
doi:10.3389/fphar.2021.796534 pmid:34975493 pmcid:PMC8719637 fatcat:zjfhiouxwrgyvhaenajpd26cs4

Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data

Alexios Koutsoukas, Keith J. Monaghan, Xiaoli Li, Jun Huan
2017 Journal of Cheminformatics  
Results: We show that feed-forward deep neural networks are capable of achieving strong classification performance and outperform shallow methods across diverse activity classes when optimized.  ...  Moreover, robustness of machine learning methods to different levels of artificially introduced noise was assessed.  ...  Acknowledgements The authors thank the Advanced Computing Facility of the University of Kansas ( for the support throughout this research.  ... 
doi:10.1186/s13321-017-0226-y pmid:29086090 pmcid:PMC5489441 fatcat:7mdy7aqlbjfi3kc2s6uzn46kqi

ToxTree: descriptor-based machine learning models for both hERG and Nav1.5 cardiotoxicity liability predictions [article]

Issar Arab, Khaled Barakat
2021 arXiv   pre-print
Whereas ToxTree-Nav1.5 Classifier, a pipeline of kernelized SVM models, was trained on a large manually curated set of 1550 unique compounds retrieved from both ChEMBL and PubChem publicly available bioactivity  ...  This rising concern has been reflected in the drug development arena, as the frequent emergence of cardiotoxicity from many approved drugs led to either discontinuing their use or, in some cases, their  ...  Acknowledgment The authors would like to acknowledge funding from the Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery grant.  ... 
arXiv:2112.13467v1 fatcat:5rymyaegjjfa3ms5lowtn7vntu

Convolutional architectures for virtual screening

Isabella Mendolia, Salvatore Contino, Ugo Perricone, Edoardo Ardizzone, Roberto Pirrone
2020 BMC Bioinformatics  
Early screening needs to ensure that all bioactive compounds are ranked in the first positions despite of the number of false positives, while a second screening round is aimed at increasing the prediction  ...  A novel CNN architecture is presented to this aim, which predicts bioactivity of candidate compounds on CDK1 using a combination of molecular fingerprints as their vector representation, and has been trained  ...  Acknowledgements The authors want to thank Dr. Giada De Simone for her precious work in pre-processing the data using KNIME.  ... 
doi:10.1186/s12859-020-03645-9 pmid:32938359 pmcid:PMC7493874 fatcat:qxbkupso4fgvdhkk5c2tr5jt7i

Machine Learning Data Augmentation as a Tool to Enhance Quantitative Composition–Activity Relationships of Complex Mixtures. A New Application to Dissect the Role of Main Chemical Components in Bioactive Essential Oils

Alessio Ragno, Anna Baldisserotto, Lorenzo Antonini, Manuela Sabatino, Filippo Sapienza, Erika Baldini, Raissa Buzzi, Silvia Vertuani, Stefano Manfredini
2021 Molecules  
Robust machine learning models are far more useful tools to reveal data augmentation in comparison with raw data derived models.  ...  To the best of the authors knowledge this is the first report using data augmentation to highlight the role of complex mixture components, in particular a first application of these data will be for the  ...  Conflicts of Interest: The authors declare no conflict of interest. Sample Availability: Samples of the compounds are available from the authors.  ... 
doi:10.3390/molecules26206279 pmid:34684861 pmcid:PMC8537614 fatcat:ovozxs3cwzcvhmp37nstiyf7yy

CYPstrate: A Set of Machine Learning Models for the Accurate Classification of Cytochrome P450 Enzyme Substrates and Non-Substrates

Malte Holmer, Christina de Bruyn Kops, Conrad Stork, Johannes Kirchmair
2021 Molecules  
In this work, we present a new set of machine learning models for the classification of xenobiotics into substrates and non-substrates of nine human CYP isozymes: CYPs 1A2, 2A6, 2B6, 2C8, 2C9, 2C19, 2D6  ...  The best models presented in this work are accessible free of charge via the "CYPstrate" module of the New E-Resource for Drug Discovery (NERDD).  ...  Conflicts of Interest: The authors declare no conflict of interest. Sample Availability: Not available.  ... 
doi:10.3390/molecules26154678 fatcat:3tu4vdletrgpha3vgtbbdfelni

Deep Learning-based Prediction of Drug-induced Cardiotoxicity

Chuipu Cai, Pengfei Guo, Yadi Zhou, Jingwei Zhou, Qi Wang, Fengxue Zhang, Jiansong Fang, Feixiong Cheng
2019 Journal of Chemical Information and Modeling  
In total, we assemble 7,889 compounds with well-defined experimental data on the hERG and with diverse chemical structures.  ...  In this study, we develop a deep learning approach, termed deephERG, for prediction of hERG blockers of small molecules in drug discovery and postmarketing surveillance.  ...  Acknowledgments This work was supported by the National Heart, Lung, and Blood Institute of the National Institutes of Health under Award Number K99HL138272 and R00HL138272 to F.C.  ... 
doi:10.1021/acs.jcim.8b00769 pmid:30715873 pmcid:PMC6489130 fatcat:2n3e53yaq5auzcb37yukglj25i

Discrimination of Gentiana and Its Related Species Using IR Spectroscopy Combined with Feature Selection and Stacked Generalization

Tao Shen, Hong Yu, Yuan-Zhong Wang
2020 Molecules  
Because of the phytochemical diversity and difference of bioactive compounds among species, which makes it crucial to accurately identify authentic Gentiana species.  ...  The MIR-SVM model had a higher classification accuracy rate than the other models that were based on the results of the calibration sets and prediction sets.  ...  Chemical and pharmacological researches have indicated that the composition of bioactive compounds is diverse according to different Gentiana species [2, 6] .  ... 
doi:10.3390/molecules25061442 pmid:32210010 pmcid:PMC7144467 fatcat:m2qpicfswfhatl2bgzsy2y4rtu

Essential Oils Biofilm Modulation Activity and Machine Learning Analysis on Pseudomonas aeruginosa Isolates from Cystic Fibrosis Patients

Marco Artini, Rosanna Papa, Filippo Sapienza, Mijat Božović, Gianluca Vrenna, Vanessa Tuccio Guarna Assanti, Manuela Sabatino, Stefania Garzoli, Ersilia Vita Fiscarelli, Rino Ragno, Laura Selan
2022 Microorganisms  
EOs are complex mixtures of different classes of organic compounds, usually used for the treatment of upper respiratory tract infections in traditional medicine.  ...  Machine learning (ML) algorithms were applied to develop classification models in order to suggest a possible antibiofilm action for each chemical component of the studied EOs.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/microorganisms10050887 fatcat:p6sauouszfadjc35z5uhsv5vsq

Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure

Anika Liu, Moritz Walter, Peter Wright, Aleksandra Bartosik, Daniela Dolciami, Abdurrahman Elbasir, Hongbin Yang, Andreas Bender
2021 Biology Direct  
One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure.  ...  labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models.  ...  Acknowledgments We thank CAMDA and the FDA for organizing the CAMDA CMap Drug Safety Challenge 2019 and for providing us with the opportunity to present our contributions at the CAMDA/ISMB conference.  ... 
doi:10.1186/s13062-020-00285-0 pmid:33461600 fatcat:zb2xdv3erzeejkymeh62aztr5m

Validating the validation: reanalyzing a large-scale comparison of deep learning and machine learning models for bioactivity prediction

Matthew C. Robinson, Robert C. Glen, Alpha A. Lee
2020 Journal of Computer-Aided Molecular Design  
However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should be benchmarked and validated.  ...  We reanalyze the data generated by a recently published large-scale comparison of machine learning models for bioactivity prediction and arrive at a somewhat different conclusion.  ...  Acknowledgements AAL acknowledges the support of the Winton  ... 
doi:10.1007/s10822-019-00274-0 pmid:31960253 fatcat:2bs3ok3uibhy7oyxnvo4kta5ca

Predicting anticancer hyperfoods with graph convolutional networks

Guadalupe Gonzalez, Shunwang Gong, Ivan Laponogov, Michael Bronstein, Kirill Veselkov
2021 Human Genomics  
and classification tasks, which can result in sub-optimal learned drug representations with respect to the classification task.  ...  representations to optimize model performance in the prediction of anticancer therapeutics.  ...  In the second, the learned representations were fed to an SVM for the anticancer therapeutic classification task.  ... 
doi:10.1186/s40246-021-00333-4 pmid:34099048 pmcid:PMC8182908 fatcat:p2rrzxq5k5fw3fclpdrqqjd45i

Prediction of Drug-Likeness Using Deep Autoencoder Neural Networks

Qiwan Hu, Mudong Feng, Luhua Lai, Jianfeng Pei
2018 Frontiers in Genetics  
The performance of the models outperforms previously reported models. In addition, we develop a drug/non-drug-like model (ZINC World Drug vs.  ...  ZINC All Purchasable), which distinguishes drugs and common compounds, with a classification accuracy of 96.99%.  ...  In all case, we applied Bayesian optimization (Hyperas, a python library based on hyperopt 2 ) to optimize the hyperparameter, such as the number of hidden layer nodes K, the value of L2 weight regularizer  ... 
doi:10.3389/fgene.2018.00585 pmid:30538725 pmcid:PMC6277570 fatcat:7lwnokde7nbrtkhssehqqvqx34

DEEPScreen: High Performance Drug-Target Interaction Prediction with Convolutional Neural Networks Using 2-D Structural Compound Representations [article]

Ahmet Sureyya Rifaioglu, Volkan Atalay, Maria Jesus Martin, Rengul Cetin-Atalay, Tunca Dogan
2018 bioRxiv   pre-print
The method proposed here can be employed to computationally scan a large portion of the recorded drug candidate compound and protein spaces to aid the experimentalists working in the field of drug discovery  ...  DEEPScreen system was trained for 704 target proteins (using ChEMBL curated bioactivity data) and finalized with rigorous hyper-parameter optimization tests.  ...  In most of the ML method development studies, hyperparameters are arbitrarily pre-selected without further optimization (especially when there are high number of models as in DEEPScreen), due to extremely  ... 
doi:10.1101/491365 fatcat:7aieghtxtnf2dpkiqd4mz4fedi
« Previous Showing results 1 — 15 out of 102 results