• Corpus ID: 7978746

VEGA-QSAR: AI Inside a Platform for Predictive Toxicology

@inproceedings{Benfenati2013VEGAQSARAI,
  title={VEGA-QSAR: AI Inside a Platform for Predictive Toxicology},
  author={Emilio Benfenati and Alberto Manganaro and Giuseppina C. Gini},
  booktitle={PAI@AI*IA},
  year={2013}
}
Computer simulation and predictive models are widely used in engineering, much less considered in life sciences. We present an initiative aimed to establish a dialogue within the community of scientists, regulators, industry representatives, offering a platform which combines the predictive capability of computer models, with some explanation tools, which may be convincing and helpful for human users to derive a conclusion. The resulting system covers a large set of toxicological endpoints. 

Figures from this paper

QSPR models for bioconcentration factor (BCF): are they able to predict data of industrial interest?
TLDR
Whether models built on public data only have adequate performances when challenged to predict industrial compounds is analyzed, and a new BCF model has been built using ISIDA fragment descriptors, support vector regression and random forest machine-learning methods.
QSAR modeling of cumulative environmental end-points for the prioritization of hazardous chemicals.
TLDR
This paper reviews a selection of QSAR models developed for cumulative multivariate endpoints, which were derived by mathematical combination of multiple effects and properties to address environmentally relevant properties of chemicals.
Modelling quantitative structure activity–activity relationships (QSAARs): auto-pass-pass, a new approach to fill data gaps in environmental risk assessment under the REACH regulation
TLDR
A Pass-Pass Quantitative Structure-Activity-Activity Relationship (PP QSAAR) model for direct prediction of the toxicity of a larger set of compounds, combing the application of an already predicted model for another species, and molecular descriptors is developed.
A large comparison of integrated SAR/QSAR models of the Ames test for mutagenicity$
TLDR
This study evaluated different strategies for combining results of models for Ames mutagenicity, starting from a set of 10 diverse individual models, each built on a dataset of around 6000 compounds, and used the new data to build a family of integrated models.
Machine learning models based on molecular descriptors to predict human and environmental toxicological factors in continental freshwater
TLDR
A method, based on machine learning algorithms, that used molecular descriptors to predict two specific endpoints in continental freshwater for ecotoxicological and human impacts and derived characterization factors that were missing for more than a hundred chemicals in USEtox® is presented.
Toward regulatory acceptance and improving the prediction confidence of in silico approaches: a case study of genotoxicity
TLDR
It appears that there is still large room for improvement of genotoxicity prediction methods, and availability of well-curated high-quality databases, covering a broader chemical space, is one of the most important needs.
QSAR Models for Human Carcinogenicity: An Assessment Based on Oral and Inhalation Slope Factors
Carcinogenicity is a crucial endpoint for the safety assessment of chemicals and products. During the last few decades, the development of quantitative structure–activity relationship ((Q)SAR) models
ToxRead: A tool to assist in read across and its use to assess mutagenicity of chemicals£
TLDR
This paper discusses how to improve and standardize read across activity using ad hoc visualization and data search methods which use similarity measures and fragment search to organize in a chart a picture of all the relevant information that the expert needs to make an assessment.
...
...

References

SHOWING 1-10 OF 15 REFERENCES
Using toxicological evidence from QSAR models in practice.
TLDR
The article demonstrates both the use of QSAR models as tools to reduce or replace in vivo testing, and the need for scientific expertise and rigor in their use.
The acceptance of in silico models for REACH: Requirements, barriers, and perspectives
TLDR
Some of the issues and challenges involved in the acceptance of quantitative structure-activity relationships (QSAR) models for regulatory purposes are outlined.
Automatic knowledge extraction from chemical structures: the case of mutagenicity prediction
TLDR
This work proposes a new structure–activity relationship (SAR) approach to mine molecular fragments that act as structural alerts for biological activity, and has been tested on the mutagenicity endpoint, showing marked prediction skills and bringing to the surface much of the knowledge already collected in the literature as well as new evidence.
Assessment and validation of the CAESAR predictive model for bioconcentration factor (BCF) in fish
TLDR
The CAESAR model for BCF is useful for regulatory purposes because it is robust, reliable and predictive and has a well-defined applicability domain, as required by REACH.
Validation of models
TLDR
Which statistical techniques can be used to validate simulation models, depending on which real-life data are available, are shown.
Methods and Experimental Techniques in Computer Engineering
TLDR
This book critically presents the role of scientific method in computing from a unitary conceptual and methodological perspective by addressing specific case studies at the intersection between computing and science.
SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules
TLDR
This chapter discusses the construction of Benzenoid and Coronoid Hydrocarbons through the stages of enumeration, classification, and topological properties in a number of computers used for this purpose.
Molecular descriptors for chemoinformatics
TLDR
This book presents a meta-modelling framework for QSAR/QSPR Modeling using Greek alphabets, selected from 450 journals and covering the period from the beginning of molecular descriptor research until the year 2008.
...
...