225 Hits in 4.3 sec

Incremental predictive clustering trees for online semi-supervised multi-target regression

Aljaž Osojnik, Panče Panov, Sašo Džeroski
2020 Machine Learning  
In this paper, we propose a method for online semi-supervised multi-target regression. It is based on incremental trees for multi-target regression and the predictive clustering framework.  ...  We compare the proposed iSOUP-PCT method with supervised tree methods, which do not use unlabeled examples, and to an oracle method, which uses unlabeled examples as though they were labeled.  ...  In many application domains, e.g., quantitive structure-activity relationship (QSAR) modeling, unlabeled examples are abundant and cheap to produce, while labeling examples can incur significant costs.  ... 
doi:10.1007/s10994-020-05918-z fatcat:alx6s4ypvzf7jkg3cq6kvuspfi

Machine learning in chemoinformatics and drug discovery

Yu-Chen Lo, Stefano E. Rensi, Wen Torng, Russ B. Altman
2018 Drug Discovery Today  
To process the chemical data, we first reviewed multiple processing layers in the chemoinformatics pipeline followed by the introduction of commonly used machine learning models in drug discovery and QSAR  ...  databases to design drugs with important biological properties.  ...  A special case of supervised learning is semi-supervised learning or tranductive learning, in which a small amount of labeled data is mixed with labeled data in the training process to improve the learning  ... 
doi:10.1016/j.drudis.2018.05.010 pmid:29750902 pmcid:PMC6078794 fatcat:ckxznjxuujajle6iqycgi74d7i

Semi-supervised oblique predictive clustering trees

Tomaž Stepišnik, Dragi Kocev
2021 PeerJ Computer Science  
Semi-supervised learning combines supervised and unsupervised learning approaches to learn predictive models from both labeled and unlabeled data.  ...  Semi-supervised predictive clustering trees (SSL-PCTs) are a prominent method for semi-supervised learning that achieves good performance on various predictive modeling tasks, including structured output  ...  Among the intrinsically semi-supervised methods (Van Engelen & Hoos, 2020) , semi-supervised predictive clustering trees (Levatić, 2017) are a prominent method.  ... 
doi:10.7717/peerj-cs.506 pmid:33987461 pmcid:PMC8101547 fatcat:saqwqyeg4zguvlnb7jqbufsioi

A Data Science Approach to Bioinformatics

Palepu Narasimha Rakesh
2021 International Journal for Research in Applied Science and Engineering Technology  
Molecular mechanics techniques also used to provide the semi quantitative prediction of the binding affinity.  ...  These techniques use machine learning, linear regression, neural nets or other statistical methods to derive predictive binding affinity equations.  ...  outliers or activity cliffs. 5) Validation of QSAR model performance. 6) Applicability in a real-world setting.  ... 
doi:10.22214/ijraset.2021.37221 fatcat:yuibbaqx7zec5plg7bykcwmeau

Application of random forest based on semi-automatic parameter adjustment for optimization of anti-breast cancer drugs

Jiajia Liu, Zhihui Zhou, Shanshan Kong, Zezhong Ma
2022 Frontiers in Oncology  
Then, using the Semi-automatic parameter adjustment method to adjust the parameters of Random Forest, XGBoost and Gradient-enhanced algorithms to find the optimal parameters.  ...  Finally, the accuracy of the results is verified by training the model with the preliminarily selected data, which provides an innovative solution for the optimization of the properties of anti- breast  ...  In practical QSAR modeling, pIC50 is generally used to represent the bioactivity value.  ... 
doi:10.3389/fonc.2022.956705 fatcat:dqk2jjx2n5bpzcvm46e2zrrvm4

Feature Ranking for Semi-supervised Learning [article]

Matej Petković, Sašo Džeroski, Dragi Kocev
2020 arXiv   pre-print
To address these challenges, we propose semi-supervised learning of feature ranking.  ...  To the best of our knowledge, this is the first work that treats the task of feature ranking within the semi-supervised structured output prediction context.  ...  Furthermore, we compared the performance of the semi-supervised feature ranking methods with their supervised counterparts.  ... 
arXiv:2008.03937v1 fatcat:7nipvmrnf5fyto6h24kpyprhh4

Machine Learning Methods in Drug Discovery

Lauv Patel, Tripti Shukla, Xiuzhen Huang, David W. Ussery, Shanzhi Wang
2020 Molecules  
The applications that produce promising results and methods will be reviewed.  ...  The methods for designing drug targets and novel drug discovery now routinely combine machine learning and deep learning algorithms to enhance the efficiency, efficacy, and quality of developed outputs  ...  Supervised and unsupervised learning can be combined as semi-supervised and reinforcement learning, where both functions can be utilized for various data sets [28] .  ... 
doi:10.3390/molecules25225277 pmid:33198233 fatcat:xlc7ystwjzdkveob74rvkuvfpy

Nano-(Q)SAR for Cytotoxicity Prediction of Engineered Nanomaterials

Buglak, Zherdev, Dzantiev
2019 Molecules  
Some studies reveal that QSAR models are better than classification SAR models, while other reports conclude that SAR is more precise than QSAR.  ...  The quasi-QSAR method appears to be the most promising tool, as it allows accurately taking experimental conditions into account. However, experimental artifacts are a major concern in this case.  ...  Four tree methods (functional tree, C4.5 decision tree, random tree, and simple classification and regression trees (CART)) were used for model development.  ... 
doi:10.3390/molecules24244537 pmid:31835808 pmcid:PMC6943593 fatcat:zmgil6dbyne65gxxvqq4da2stq

Computational approaches to chemical hazard assessment

Thomas Luechtefeld
2017 ALTEX: Alternatives to Animal Experimentation  
The ease of access to chemical data paired with numerous modeling packages has resulted in an increase in the power of computational models for toxicology.  ...  in computational toxicology, and ends with a high-level perspective of the algorithms used to create computational toxicology models.  ...  The authors would like to thank Mr Sean Doughty for help with editing this manuscript. Thomas Hartung, MD PhD Correspondence to  ... 
doi:10.14573/altex.1710141 pmid:29101769 pmcid:PMC5848496 fatcat:wtlpphi6zzgovpwwijhnoda47e

A Review on Applications of Computational Methods in Drug Screening and Design

Xiaoqian Lin, Xiu Li, Xubo Lin
2020 Molecules  
., molecular docking, pharmacophore modeling, and QSAR) as well as structure- and ligand-based classical/de novo drug design were introduced and discussed.  ...  Last, we explored the development of machine learning methods and their applications in aforementioned computational methods to speed up the drug discovery process.  ...  (ADME) and lowest toxicity properties at different environments, which belong to the application range of QSAR models.  ... 
doi:10.3390/molecules25061375 pmid:32197324 fatcat:n4p3cpcgtjdyhdjitu2kcngxae

Machine Learning Based Toxicity Prediction: From Chemical Structural Description to Transcriptome Analysis

Yunyi Wu, Guanyu Wang
2018 International Journal of Molecular Sciences  
We also discuss the input parameter to the machine learning algorithm, especially its shift from chemical structural description only to that combined with human transcriptome data analysis, which can  ...  Among its many applications, toxicity prediction is essential to reduce the cost and labor of a drug's preclinical and clinical trials, because a lot of drug evaluations (cellular, animal, and clinical  ...  Otherwise, the accuracy of deep learning would increase markedly due to semi-supervised learning characteristics.  ... 
doi:10.3390/ijms19082358 pmid:30103448 fatcat:mjgeejthrzex7kbyxgncnncgla

Guest editors' preface to the special issue on conformal prediction and its applications

Harris Papadopoulos, Vladimir Vovk, Alexander Gammerman
2014 Annals of Mathematics and Artificial Intelligence  
The framework has also been extended to additional problem settings such as semi-supervised learning, anomaly detection [17] , feature selection [2] , outlier detection, change detection in streams  ...  The use of CP enables the proposed approach to both produce reliable confidence measures with each prediction and to automatically adjust the number of prototypes to be used in the model.  ... 
doi:10.1007/s10472-014-9429-3 fatcat:ojgy3bxqqna23g6ygh3esg4frq

Antimicrobial Isoflavones and Derivatives from Erythrina (Fabaceae): Structure Activity Perspective (Sar & Qsar) on Experimental and Mined Values Against Staphylococcus Aureus

Nicholas J. Sadgrove, Tiago B. Oliveira, Gugulethu P. Khumalo, Sandy F. van Vuuren, Ben-Erik van Wyk
2020 Antibiotics  
Furthermore, to make quantitative predictions of MIC values (Quantitative SAR: QSAR) 'pace regression' was utilized and validated (R² = 0.778, Q² = 0.727 and P² = 0.555).  ...  While antimicrobial results continue to validate the traditional use of E. lysistemon extracts (or Erythrina generally) in therapeutic applications consistent with anti-infection, it is surprising that  ...  Acknowledgments: To the traditional herbalists in the Johannesburg muthi markets for advice and provision of materials. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/antibiotics9050223 pmid:32365905 pmcid:PMC7277434 fatcat:h4gaff6ecnda3bh4kv4hbi73kq

QSAR Models for Human Carcinogenicity: An Assessment Based on Oral and Inhalation Slope Factors

Cosimo Toma, Alberto Manganaro, Giuseppa Raitano, Marco Marzo, Domenico Gadaleta, Diego Baderna, Alessandra Roncaglioni, Nynke Kramer, Emilio Benfenati
2020 Molecules  
The models performed well in classification, with accuracies for the external set of 0.76 and 0.74 for oral and inhalation exposure, respectively, and r2 values of 0.57 and 0.65 in the regression models  ...  Several classification models can now predict both human and rat carcinogenicity, but there are few models to quantitatively assess carcinogenicity in humans.  ...  Classification Models Binary classification models were built by the Classification and Regression Tree (CART) modelling approach.  ... 
doi:10.3390/molecules26010127 pmid:33383938 fatcat:cdzag424ajg53gscxa5ineqi2i

Machine Learning in Chemical Product Engineering: The State of the Art and a Guide for Newcomers

Cindy Trinh, Dimitrios Meimaroglou, Sandrine Hoppe
2021 Processes  
the development of ML modeling approaches.  ...  and develop constantly and quickly new molecules and materials with tailor-made properties.  ...  The authors in [46] employed semi-supervised local kernel regression for the soft sensor modeling of the rubber-mixing process.  ... 
doi:10.3390/pr9081456 fatcat:tb2fredhnjghhm7lsj5qb2bipq
« Previous Showing results 1 — 15 out of 225 results