Dataset Information

Weighted feature significance: a simple, interpretable model of compound toxicity based on the statistical enrichment of structural features.

ABSTRACT: In support of the U.S. Tox21 program, we have developed a simple and chemically intuitive model we call weighted feature significance (WFS) to predict the toxicological activity of compounds, based on the statistical enrichment of structural features in toxic compounds. We trained and tested the model on the following: (1) data from quantitative high-throughput screening cytotoxicity and caspase activation assays conducted at the National Institutes of Health Chemical Genomics Center, (2) data from Salmonella typhimurium reverse mutagenicity assays conducted by the U.S. National Toxicology Program, and (3) hepatotoxicity data published in the Registry of Toxic Effects of Chemical Substances. Enrichments of structural features in toxic compounds are evaluated for their statistical significance and compiled into a simple additive model of toxicity and then used to score new compounds for potential toxicity. The predictive power of the model for cytotoxicity was validated using an independent set of compounds from the U.S. Environmental Protection Agency tested also at the National Institutes of Health Chemical Genomics Center. We compared the performance of our WFS approach with classical classification methods such as Naive Bayesian clustering and support vector machines. In most test cases, WFS showed similar or slightly better predictive power, especially in the prediction of hepatotoxic compounds, where WFS appeared to have the best performance among the three methods. The new algorithm has the important advantages of simplicity, power, interpretability, and ease of implementation.

SUBMITTER: Huang R

PROVIDER: S-EPMC2777082 | biostudies-other | 2009 Dec

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Weighted feature significance: a simple, interpretable model of compound toxicity based on the statistical enrichment of structural features.

Huang Ruili R Southall Noel N Xia Menghang M Cho Ming-Hsuang MH Jadhav Ajit A Nguyen Dac-Trung DT Inglese James J Tice Raymond R RR Austin Christopher P CP

Toxicological sciences : an official journal of the Society of Toxicology 20091004 2

In support of the U.S. Tox21 program, we have developed a simple and chemically intuitive model we call weighted feature significance (WFS) to predict the toxicological activity of compounds, based on the statistical enrichment of structural features in toxic compounds. We trained and tested the model on the following: (1) data from quantitative high-throughput screening cytotoxicity and caspase activation assays conducted at the National Institutes of Health Chemical Genomics Center, (2) data f ...[more]

PMID: 19805409

Similar Datasets

Project description:In recent years, functional brain network topological features have been widely used as classification features. Previous studies have found that network node scale differences caused by different network parcellation definitions significantly affect the structure of the constructed network and its topological properties. However, we still do not know how network scale differences affect the classification accuracy, performance of classification features, and effectiveness of the feature selection strategy using P values in terms of the machine learning method. This study used five scale parcellations, involving 90, 256, 497, 1003, and 1501 nodes. Three local properties of resting-state functional brain networks were selected (degree, betweenness centrality, and nodal efficiency), and the support vector machine method was used to construct classifiers to identify patients with major depressive disorder. We analyzed the impact of the five scales on classification accuracy. In addition, the effectiveness and redundancy of features obtained by the different scale parcellations were compared. Finally, traditional statistical significance (P value) was verified as a feature selection criterion. The results showed that the feature effectiveness of different scales was similar; in other words, parcellation with more regions did not provide more effective discriminative features. Nevertheless, parcellation with more regions did provide a greater quantity of discriminative features, which led to an improvement in the accuracy of the classification. However, due to the close distance between brain regions, the redundancy of parcellation with more regions was also greater. The traditional P value feature selection strategy is feasible with different scales, but our analysis showed that the traditional P < 0.05 threshold was too strict for feature selection. This study provides an important reference for the selection of network scales when applying topological properties of brain networks to machine learning methods.

Project description:BackgroundCausal graphs are an increasingly popular tool for the analysis of biological datasets. In particular, signed causal graphs--directed graphs whose edges additionally have a sign denoting upregulation or downregulation--can be used to model regulatory networks within a cell. Such models allow prediction of downstream effects of regulation of biological entities; conversely, they also enable inference of causative agents behind observed expression changes. However, due to their complex nature, signed causal graph models present special challenges with respect to assessing statistical significance. In this paper we frame and solve two fundamental computational problems that arise in practice when computing appropriate null distributions for hypothesis testing.ResultsFirst, we show how to compute a p-value for agreement between observed and model-predicted classifications of gene transcripts as upregulated, downregulated, or neither. Specifically, how likely are the classifications to agree to the same extent under the null distribution of the observed classification being randomized? This problem, which we call "Ternary Dot Product Distribution" owing to its mathematical form, can be viewed as a generalization of Fisher's exact test to ternary variables. We present two computationally efficient algorithms for computing the Ternary Dot Product Distribution and investigate its combinatorial structure analytically and numerically to establish computational complexity bounds.Second, we develop an algorithm for efficiently performing random sampling of causal graphs. This enables p-value computation under a different, equally important null distribution obtained by randomizing the graph topology but keeping fixed its basic structure: connectedness and the positive and negative in- and out-degrees of each vertex. We provide an algorithm for sampling a graph from this distribution uniformly at random. We also highlight theoretical challenges unique to signed causal graphs; previous work on graph randomization has studied undirected graphs and directed but unsigned graphs.ConclusionWe present algorithmic solutions to two statistical significance questions necessary to apply the causal graph methodology, a powerful tool for biological network analysis. The algorithms we present are both fast and provably correct. Our work may be of independent interest in non-biological contexts as well, as it generalizes mathematical results that have been studied extensively in other fields.

Dataset Information

Weighted feature significance: a simple, interpretable model of compound toxicity based on the statistical enrichment of structural features.

Publications

Weighted feature significance: a simple, interpretable model of compound toxicity based on the statistical enrichment of structural features.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets