Regression- and Projection-Based Approaches in Predictive Toxicology

Eriksson, Lennart; Johansson, Erik; Lundstedt, Torbjörn

doi:10.1201/9780849350351.ch6

Cited by 10 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…prediction of LD 50 values). Algorithmic details for the presented techniques can be found in a recent book [13,25,26] as well as in general introductions to machine learning and data mining [2,4]. Most of the described techniques have been implemented in many popular statistical, data mining and chemoinformatics packages as well as in specific predictive toxicology tools.…”

Section: Construction Of Classification and Regression Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence and Data Mining for Toxicity Prediction

Helma¹,

Kazius²

2006

CAD

View full text Add to dashboard Cite

Tools for artificial intelligence and data mining can derive (Quantitative) Structure-Activity Relationships ((Q)SARs) for toxicity in an objective and reproducible manner. This review provides a conceptual description of the most important data mining algorithms for the identification of chemical features and the extraction of relationships between these descriptors and toxic activities. We will discuss the compliance of these techniques with the OECD guidelines for (Q)SAR requirements as well as performance implications. Special emphasis will be given to validation procedures for (Q)SAR models.

show abstract

Section: Construction Of Classification and Regression Modelsmentioning

confidence: 99%

“…Multiple Linear Regression (MLR) [25] has been the workhorse for (Q)SAR model development during the last decades. It attempts to identify a linear function that relates descriptors to toxicity values.…”

Section: Generalised Linear Modelsmentioning

confidence: 99%

Artificial Intelligence and Data Mining for Toxicity Prediction

Helma¹,

Kazius²

2006

CAD

View full text Add to dashboard Cite

show abstract

“…The statistical difference between the performances of any two methods is calculated using the signed test and is given in Table 4. In Table 4, the item 2.67(+) in cell (2,4), for example, indicates fuzzy kNNModel is better than crisp kNNModel in terms of performance over the seventeen datasets as the corresponding |Z|>Z 0.975 = 1.96. The item -0.24(-) in cell (2,2) indicates there is no significant difference in terms of performance between fuzzy kNNModel and SVM over seventeen datasets as the corresponding |Z|<Z 0.975 =1.96.…”

Section: Statistical Tool For Comparisonmentioning

confidence: 99%

“…The traditional manual data analysis has become inefficient and computerbased analyses are indispensable. Statistical methods [1], expert systems [2], fuzzy neural networks [3], [4] and machine learning algorithms [5], [6] are extensively studied and applied to predictive toxicology for decision making.…”

Section: Introductionmentioning

confidence: 99%

FUZZY kNNMODEL APPLIED TO PREDICTIVE TOXICOLOGY DATA MINING

Guo

Neagu

2005

Int. J. Comp. Intel. Appl.

View full text Add to dashboard Cite

show abstract

“…Traditional manual data analysis has become inefficient, and computer-based analysis is indispensable. Statistical methods (1), expert systems (2), fuzzy neural networks (3) and other machine learning algorithms (4,5), are extensively studied and applied to predictive toxicology for model development and decision making. However, due to the complexity of modelling existing toxicity data sets caused by numerous irrelevant descriptors, skewed distribution, missing values and noisy data, no dominant machine learning algorithm can be proposed to accurately model all of the toxicity data sets available.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Machine Learning Algorithms Applied to Predictive Toxicology Data Mining

et al. 2007

View full text Add to dashboard Cite

This paper reports results of a comparative study of widely used machine learning algorithms applied to predictive toxicology data mining. The machine learning algorithms involved were chosen in terms of their representability and diversity, and were extensively evaluated with seven toxicity data sets which were taken from real-world applications. Some results based on visual analysis of the correlations of different descriptors to the class values of chemical compounds, and on the relationships of the range of chosen descriptors to the performance of machine learning algorithms, are emphasised from our experiments. Some interesting findings relating to the data and the quality of the models are presented — for example, that no specific algorithm appears best for all seven toxicity data sets, and that up to five descriptors are sufficient for creating classification models for each toxicity data set with good accuracy. We suggest that, for a specific data set, model accuracy is affected by the feature selection method and model development technique. Models built with too many or too few descriptors are undesirable, and finding the optimal feature subset appears at least as important as selecting appropriate algorithms with which to build a final model.

show abstract

Regression- and Projection-Based Approaches in Predictive Toxicology

Cited by 10 publications

References 19 publications

Artificial Intelligence and Data Mining for Toxicity Prediction

Artificial Intelligence and Data Mining for Toxicity Prediction

FUZZY kNNMODEL APPLIED TO PREDICTIVE TOXICOLOGY DATA MINING

A Comparative Study of Machine Learning Algorithms Applied to Predictive Toxicology Data Mining

Contact Info

Product

Resources

About