Automatic knowledge extraction from chemical structures: the case of mutagenicity prediction

Ferrari, Thomas; Cattaneo, Daniele; Gini, Giuseppina; Bakhtyari, Nazanin Golbamaki; Manganaro, Alberto; Benfenati, Emilio

doi:10.1080/1062936x.2013.773376

Cited by 127 publications

(86 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm generates substructures; relevant SAs are automatically selected on the basis of their prediction performance for a training set. The application of this modeling approach to the CAESAR data set extended the previous work [ 25 ] by extracting two sets of rules: one for mutagenicity (112 rules) and the other for non-mutagenicity (93 rules) ( see Note 6 ).…”

Section: Description Of the Model Model Statisticsmentioning

confidence: 78%

See 1 more Smart Citation

In Silico Prediction of Chemically Induced Mutagenicity: How to Use QSAR Models and Interpret Their Results

Mombelli

Raitano

Benfenati

2016

Methods in Molecular Biology

View full text Add to dashboard Cite

Information on genotoxicity is an essential piece of information gathering for a comprehensive toxicological characterization of chemicals. Several QSAR models that can predict Ames genotoxicity are freely available for download from the Internet and they can provide relevant information for the toxicological profiling of chemicals. Indeed, they can be straightforwardly used for predicting the presence or absence of genotoxic hazards associated with the interactions of chemicals with DNA.Nevertheless, and despite the ease of use of these models, the scientific challenge is to assess the reliability of information that can be obtained from these tools. This chapter provides instructions on how to use freely available QSAR models and on how to interpret their predictions.

show abstract

Section: Description Of the Model Model Statisticsmentioning

confidence: 78%

“…SARpy (SAR in python) is a QSAR method that identifi es relevant fragments and extracts a set of rules directly from data without any a priori knowledge [ 25 ]. The algorithm generates substructures; relevant SAs are automatically selected on the basis of their prediction performance for a training set.…”

Section: Description Of the Model Model Statisticsmentioning

confidence: 99%

In Silico Prediction of Chemically Induced Mutagenicity: How to Use QSAR Models and Interpret Their Results

Mombelli

Raitano

Benfenati

2016

Methods in Molecular Biology

View full text Add to dashboard Cite

show abstract

“…For the automatic extraction of SAs we used the SARpy software, described in Ferrari et al (2013). Briefly, SARpy extracts sets of rules by automatically generating and selecting substructures without any a priori knowledge, solely on the basis of their prediction performance on a training set used as input.…”

Section: Methodsmentioning

confidence: 99%

A New Structure-Activity Relationship (SAR) Model for Predicting Drug-Induced Liver Injury, Based on Statistical and Expert-Based Structural Alerts

et al. 2016

View full text Add to dashboard Cite

The prompt identification of chemical molecules with potential effects on liver may help in drug discovery and in raising the levels of protection for human health. Besides in vitro approaches, computational methods in toxicology are drawing attention. We built a structure-activity relationship (SAR) model for evaluating hepatotoxicity. After compiling a data set of 950 compounds using data from the literature, we randomly split it into training (80%) and test sets (20%). We also compiled an external validation set (101 compounds) for evaluating the performance of the model. To extract structural alerts (SAs) related to hepatotoxicity and non-hepatotoxicity we used SARpy, a statistical application that automatically identifies and extracts chemical fragments related to a specific activity. We also applied the chemical grouping approach for manually identifying other SAs. We calculated accuracy, specificity, sensitivity and Matthews correlation coefficient (MCC) on the training, test and external validation sets. Considering the complexity of the endpoint, the model performed well. In the training, test and external validation sets the accuracy was respectively 81, 63, and 68%, specificity 89, 33, and 33%, sensitivity 93, 88, and 80% and MCC 0.63, 0.27, and 0.13. Since it is preferable to overestimate hepatotoxicity rather than not to recognize unsafe compounds, the model's architecture followed a conservative approach. As it was built using human data, it might be applied without any need for extrapolation from other species. This model will be freely available in the VEGA platform.

show abstract

“…VEGA 4 Non-Iterative Client (VEGANIC) v1.0.8, a standalone JAVA-based software was employed and three different SAR models were applied to the current dataset: Mutagenicity model CAESAR (Ferrari and Gini, 2010) version 2.1.12, Mutagenicity SarPy model version 1.0.6-DEV (Ferrari et al, 2013), and Benigni–Bossa Mutagenicity (TOXTREE; Benigni et al, 2008) version 1.0.0-DEV. The input structural data of the chemicals were given in SMILES format (Weininger, 1988).…”

Section: Methodsmentioning

confidence: 99%

Combining QSAR Modeling and Text-Mining Techniques to Link Chemical Structures and Carcinogenic Modes of Action

Papamokos

Silins

2016

Front. Pharmacol.

View full text Add to dashboard Cite

There is an increasing need for new reliable non-animal based methods to predict and test toxicity of chemicals. Quantitative structure-activity relationship (QSAR), a computer-based method linking chemical structures with biological activities, is used in predictive toxicology. In this study, we tested the approach to combine QSAR data with literature profiles of carcinogenic modes of action automatically generated by a text-mining tool. The aim was to generate data patterns to identify associations between chemical structures and biological mechanisms related to carcinogenesis. Using these two methods, individually and combined, we evaluated 96 rat carcinogens of the hematopoietic system, liver, lung, and skin. We found that skin and lung rat carcinogens were mainly mutagenic, while the group of carcinogens affecting the hematopoietic system and the liver also included a large proportion of non-mutagens. The automatic literature analysis showed that mutagenicity was a frequently reported endpoint in the literature of these carcinogens, however, less common endpoints such as immunosuppression and hormonal receptor-mediated effects were also found in connection with some of the carcinogens, results of potential importance for certain target organs. The combined approach, using QSAR and text-mining techniques, could be useful for identifying more detailed information on biological mechanisms and the relation with chemical structures. The method can be particularly useful in increasing the understanding of structure and activity relationships for non-mutagens.

show abstract

Automatic knowledge extraction from chemical structures: the case of mutagenicity prediction

Cited by 127 publications

References 29 publications

In Silico Prediction of Chemically Induced Mutagenicity: How to Use QSAR Models and Interpret Their Results

In Silico Prediction of Chemically Induced Mutagenicity: How to Use QSAR Models and Interpret Their Results

A New Structure-Activity Relationship (SAR) Model for Predicting Drug-Induced Liver Injury, Based on Statistical and Expert-Based Structural Alerts

Combining QSAR Modeling and Text-Mining Techniques to Link Chemical Structures and Carcinogenic Modes of Action

Contact Info

Product

Resources

About