Filters








7,131 Hits in 3.7 sec

Multiple-Instance Case-Based Learning for Predictive Toxicology [chapter]

Eva Armengol, Enric Plaza
2004 Lecture Notes in Computer Science  
We present a new approach to lazy learning, based on the notion of multiple-instance, which is capable of seamlessly working with multiple descriptions.  ...  Machine Learning (ML) in general, and lazy learning techniques in particular, have been applied to the task of predictive toxicology.  ...  A Predictive Toxicology Challenge (PTC) [15] was held in 2001 focusing on machine learning techniques for predicting the toxicity of compounds.  ... 
doi:10.1007/978-3-540-30478-4_18 fatcat:uhaxodtopra27ons6n4b4lvxde

An Effective Combination Based on Class-Wise Expertise of Diverse Classifiers for Predictive Toxicology Data Mining [chapter]

Daniel Neagu, Gongde Guo, Shanshan Wang
2006 Lecture Notes in Computer Science  
The classification methods used to generate classifiers for combination are chosen in terms of their representability and diversity and include the Instance-based Learning algorithm (IBL), Decision Tree  ...  This paper presents a study on the combination of different classifiers for toxicity prediction. Two combination operators for the Multiple-Classifier System definition are also proposed.  ...  The parameter LR for MLP in Table 3 stands for learning rate; the parameter k for IBL stands for the number of nearest neighbours used for classifying new instances and the parameter C for SVM stands  ... 
doi:10.1007/11811305_18 fatcat:3zwecjy67baw7gg72z4drx25v4

A Data-Driven Approach for Improved Effective Classification in Predictive Toxicology

Daniel Neagu, Gongde Guo
2006 2006 IEEE International Conference on Computational Cybernetics  
The paper proposes a correlative data-oriented fusion algorithm to develop effective models based on multisource data for classification applied to predictive toxicology.  ...  Prediction of toxic effects of chemical compounds based on experiments involving animals and human beings is very expensive in terms of time, social and financial cost.  ...  Predictive Toxicology models are based on restricted numbers of experimental data, for which generalization is still challenging.  ... 
doi:10.1109/icccyb.2006.305708 fatcat:i32rvd6cl5gizom3vg6tbdtqwy

A comparison of machine learning algorithms for chemical toxicity classification using a simulated multi-scale data model

Richard Judson, Fathi Elloumi, R Woodrow Setzer, Zhen Li, Imran Shah
2008 BMC Bioinformatics  
Conclusion: We have developed a novel simulation model to evaluate machine learning methods for the analysis of data sets in which in vitro bioassay data is being used to predict in vivo chemical toxicology  ...  Filter-based feature selection generally improved performance, most strikingly for LDA.  ...  EPA's National Center for Computational Toxicology and approved for publication.  ... 
doi:10.1186/1471-2105-9-241 pmid:18489778 pmcid:PMC2409339 fatcat:o7yqmd66afhsnpn5k3yfs76vuu

Predicting In Vitro Neurotoxicity Induced by Nanoparticles Using Machine Learning

Irini Furxhi, Finbarr Murphy
2020 International Journal of Molecular Sciences  
This is the first tissue-specific machine learning tool for neurotoxicity prediction caused by nanoparticles in in vitro systems. The model performs better than non-tissue specific models.  ...  Machine learning techniques have been applied in the field of nanotoxicology with encouraging results. A neurotoxicity classification model for diverse nanoparticles is presented in this study.  ...  [50] built models based on perturbation theory using data from multiple literature sources to predict aggregated toxicological endpoints in a binary form for different NPs.  ... 
doi:10.3390/ijms21155280 pmid:32722414 fatcat:qqbht3m75vachoklz4xs2x5l7a

Perpest model, a case-based reasoning approach to predict ecological risks of pesticides

Paul J. Van den Brink, Jan Roelsma, Egbert H. van Nes, Marten Scheffer, Theo C. M. Brock
2002 Environmental Toxicology and Chemistry  
This model is based on case-based reasoning, a technique that solves new problems (e.g., what is the effect of pesticide A?) by using past experience (e.g., published microcosm experiments).  ...  This allows the model to predict effects of pesticides for which no effects on a semifield scale have been published.  ...  The PERPEST model is available; e-mail the first author for more information.  ... 
doi:10.1002/etc.5620211132 pmid:12389932 fatcat:n7wlhuhbjbh7bccljjdbwfzuoy

PERPEST MODEL, A CASE-BASED REASONING APPROACH TO PREDICT ECOLOGICAL RISKS OF PESTICIDES

Paul J. Van den Brink, Jan Roelsma, Egbert H. Van Nes, Marten Scheffer, Theo C.M. Brock
2002 Environmental Toxicology and Chemistry  
This model is based on case-based reasoning, a technique that solves new problems (e.g., what is the effect of pesticide A?) by using past experience (e.g., published microcosm experiments).  ...  This allows the model to predict effects of pesticides for which no effects on a semifield scale have been published.  ...  The PERPEST model is available; e-mail the first author for more information.  ... 
doi:10.1897/1551-5028(2002)021<2500:pmacbr>2.0.co;2 pmid:12389932 fatcat:pte76p4zdvhbbh36htd465paiy

Collaborative development of predictive toxicology applications

Barry Hardy, Nicki Douglas, Christoph Helma, Micha Rautenberg, Nina Jeliazkova, Vedrin Jeliazkov, Ivelina Nikolova, Romualdo Benigni, Olga Tcheremenskaia, Stefan Kramer, Tobias Girschick, Fabian Buchwald (+22 others)
2010 Journal of Cheminformatics  
: ToxPredict which predicts and reports on toxicities for endpoints for an input chemical structure, and ToxCreate which builds and validates a predictive toxicity model based on an input toxicology dataset  ...  OpenTox provides an interoperable, standards-based Framework for the support of predictive toxicology data management, algorithms, modelling, validation and reporting.  ...  Acknowledgements OpenTox OpenTox -An Open Source Predictive Toxicology Framework, http://www. opentox.org, is funded under the EU Seventh Framework Program: HEALTH-  ... 
doi:10.1186/1758-2946-2-7 pmid:20807436 pmcid:PMC2941473 fatcat:pzvkgrzm5jhk7b7zqcztauxbqe

The State-of-the Art of Environmental Toxicogenomics: Challenges and Perspectives of "Omics" Approaches Directed to Toxicant Mixtures

Martins, Dreij, Costa
2019 International Journal of Environmental Research and Public Health  
These examples illustrate the importance of exploring multiple "omes" and the purpose of "omics" and multi-"omics" for building truly predictive models of hazard and risk.  ...  Despite costs and demanding computations, the systems toxicology framework, of which "omics" is a major component, endeavors extracting adverse outcome pathways for complex mixtures.  ...  As before, important lessons can be learned from ecotoxicologists. For instance, Song et al.  ... 
doi:10.3390/ijerph16234718 pmid:31779274 pmcid:PMC6926496 fatcat:4vzjevw64jcqnj4safypkispoa

Comparative Study of Classification Algorithms Using Molecular Descriptors in Toxicological DataBases [chapter]

Max Pereira, Vítor Santos Costa, Rui Camacho, Nuno A. Fonseca, Carlos Simões, Rui M. M. Brito
2009 Lecture Notes in Computer Science  
In this study we evaluate the use of several Machine Learning algorithms to find useful rules to the elucidation and prediction of toxicity using 1D and 2D molecular descriptors.  ...  Only a few of these will be selected for biological evaluation and further refinement through chemical synthesis.  ...  A classification system TIPT (Tree Induction for Predictive Toxicology) based on the tree was then applied and compared with neural networks models in terms of accuracy and understandability.  ... 
doi:10.1007/978-3-642-03223-3_11 fatcat:ca6duj4zqjcdngw7bta6ag2kxy

Predictive Modeling of Chemical Hazard by Integrating Numerical Descriptors of Chemical Structures and Short-term Toxicity Assay Data

Ivan Rusyn, Alexander Sedykh, Yen Low, Kathryn Z. Guyton, Alexander Tropsha
2012 Toxicological Sciences  
Using several case studies, we illustrate the benefits of a hybrid modeling approach, namely improvements in the accuracy of models, enhanced interpretation of the most predictive features, and expanded  ...  Quantitative structure-activity relationship (QSAR) models are widely used for in silico prediction of in vivo toxicity of drug candidates or environmental chemicals, adding value to candidate selection  ...  For example, in the simplest instance, predictions from a QSAR model and a biological model would be averaged into a final consensus score.  ... 
doi:10.1093/toxsci/kfs095 pmid:22387746 pmcid:PMC3327873 fatcat:jib5s7h3gngyxlxo2ovicjpkve

Big-data and machine learning to revamp computational toxicology and its use in risk assessment

Thomas Luechtefeld, Craig Rowlands, Thomas Hartung
2018 Toxicology Research  
The creation of large toxicological databases and advances in machine-learning techniques have empowered computational approaches in toxicology.  ...  Multi-label learning Recent advances in machine learning have resulted in models that can handle missing data and model multiple targets at once (multi-label learning, in case of toxicology for example  ...  This decision tree illustrates how instance-based learning can be used in concert with supervised learning methods via feature generation.  ... 
doi:10.1039/c8tx00051d pmid:30310652 pmcid:PMC6116175 fatcat:ms7njv5sbnh6dfbv5lhospcowi

Data quality in predictive toxicology: identification of chemical structures and calculation of chemical properties

C Helma, S Kramer, B Pfahringer, E Gottmann
2000 Environmental Health Perspectives  
It is based on a case study where machine learning techniques were applied to data from noncongeneric compounds and a complex toxicologic end point (carcinogenicity).  ...  Articles Every technique for toxicity prediction and for the detection of structure-activity relationships relies on the accurate estimation and representation of chemical and toxicologic properties.  ...  For this reason we decided to remove toxicologically irrelevant entities (e.g., multiple instances of the same entity, H 2 O, HCl, etc.), represent salts with covalent bonds, and remove compounds with  ... 
doi:10.1289/ehp.001081029 pmid:11102292 pmcid:PMC1240158 fatcat:ogvb7hui5vb53nxg7g664hyyxm

Data Quality in Predictive Toxicology: Identification of Chemical Structures and Calculation of Chemical Properties

Christoph Helma, Stefan Kramer, Bernhard Pfahringer, Eva Gottmann
2000 Environmental Health Perspectives  
It is based on a case study where machine learning techniques were applied to data from noncongeneric compounds and a complex toxicologic end point (carcinogenicity).  ...  Articles Every technique for toxicity prediction and for the detection of structure-activity relationships relies on the accurate estimation and representation of chemical and toxicologic properties.  ...  For this reason we decided to remove toxicologically irrelevant entities (e.g., multiple instances of the same entity, H 2 O, HCl, etc.), represent salts with covalent bonds, and remove compounds with  ... 
doi:10.2307/3434954 fatcat:cz5tdnekdvcrfhkct4yy3dxbsy

Cross-organism toxicogenomics with group factor analysis

Tommi Suvitaival, Juuso A Parkkinen, Seppo Virtanen, Samuel Kaski
2014 Systems Biomedicine  
This is a key step toward developing methods for predictive toxicology.  ...  The associations can also be used for predicting one data view based on another, for example, predicting toxic outcomes based on transcriptomic responses.  ... 
doi:10.4161/sysb.29291 fatcat:qkdfrtrbvbdytnjtto5xc2n76y
« Previous Showing results 1 — 15 out of 7,131 results