Limits...
eTOXlab, an open source modeling framework for implementing predictive models in production environments.

Carrió P, López O, Sanz F, Pastor M - J Cheminform (2015)

Bottom Line: The particular eTOXlab architecture as a self-contained, portable prediction engine allows building models with confidential information within corporate facilities, which can be safely exported and used for prediction without disclosing the structures of the training series.The technologies used by eTOXlab (web services, VM, object-oriented programming) provide an elegant solution to common practical issues; the system can be installed easily in heterogeneous environments and integrates well with other software.Moreover, the system provides a simple and safe solution for building models with confidential structures that can be shared without disclosing sensitive information.

View Article: PubMed Central - PubMed

Affiliation: Research Programme on Biomedical Informatics (GRIB), Department of Experimental and Health Sciences, Universitat Pompeu Fabra, IMIM (Hospital del Mar Medical Research Institute), Dr. Aiguader 88, E-08003 Barcelona, Spain.

ABSTRACT

Background: Computational models based in Quantitative-Structure Activity Relationship (QSAR) methodologies are widely used tools for predicting the biological properties of new compounds. In many instances, such models are used as a routine in the industry (e.g. food, cosmetic or pharmaceutical industry) for the early assessment of the biological properties of new compounds. However, most of the tools currently available for developing QSAR models are not well suited for supporting the whole QSAR model life cycle in production environments.

Results: We have developed eTOXlab; an open source modeling framework designed to be used at the core of a self-contained virtual machine that can be easily deployed in production environments, providing predictions as web services. eTOXlab consists on a collection of object-oriented Python modules with methods mapping common tasks of standard modeling workflows. This framework allows building and validating QSAR models as well as predicting the properties of new compounds using either a command line interface or a graphic user interface (GUI). Simple models can be easily generated by setting a few parameters, while more complex models can be implemented by overriding pieces of the original source code. eTOXlab benefits from the object-oriented capabilities of Python for providing high flexibility: any model implemented using eTOXlab inherits the features implemented in the parent model, like common tools and services or the automatic exposure of the models as prediction web services. The particular eTOXlab architecture as a self-contained, portable prediction engine allows building models with confidential information within corporate facilities, which can be safely exported and used for prediction without disclosing the structures of the training series.

Conclusions: The software presented here provides full support to the specific needs of users that want to develop, use and maintain predictive models in corporate environments. The technologies used by eTOXlab (web services, VM, object-oriented programming) provide an elegant solution to common practical issues; the system can be installed easily in heterogeneous environments and integrates well with other software. Moreover, the system provides a simple and safe solution for building models with confidential structures that can be shared without disclosing sensitive information.

No MeSH data available.


Related in: MedlinePlus

Schema of the main eTOXlab workflows: prediction (right hand side) and building (left hand side), indicating the input and output, and themodelmethods called. Notice that both workflows use the same normalize and extract methods.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4358905&req=5

Fig3: Schema of the main eTOXlab workflows: prediction (right hand side) and building (left hand side), indicating the input and output, and themodelmethods called. Notice that both workflows use the same normalize and extract methods.

Mentions: eTOXlab implements building and prediction workflows that define the order and the calls to be made to the methods of the model class (Table 1), as represented in Figure 3. For building a model, the first step of the building workflow consist in normalizing the structures of the training series (normalize method), these structures are then used to compute the numerical description of their structures and to obtain the biological annotations present in the original file (extract method). With these, a QSAR model is built and validated (build method). The net result of this process is a predictive model, which is stored internally at the server. For carrying out predictions, the first step of the prediction workflow is to normalize the input structure and to compute the molecular descriptors exactly as it was done for the compounds of the training series. In eTOXlab this requirement is guaranteed because the very same methods (normalize and extract) are applied. The molecular descriptors together with the stored models are then used for producing the prediction (predict method). These pre-defined building and prediction workflows, like any other method of the model class, can be also overridden allowing the user to implement models that use completely different workflows.Figure 3


eTOXlab, an open source modeling framework for implementing predictive models in production environments.

Carrió P, López O, Sanz F, Pastor M - J Cheminform (2015)

Schema of the main eTOXlab workflows: prediction (right hand side) and building (left hand side), indicating the input and output, and themodelmethods called. Notice that both workflows use the same normalize and extract methods.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4358905&req=5

Fig3: Schema of the main eTOXlab workflows: prediction (right hand side) and building (left hand side), indicating the input and output, and themodelmethods called. Notice that both workflows use the same normalize and extract methods.
Mentions: eTOXlab implements building and prediction workflows that define the order and the calls to be made to the methods of the model class (Table 1), as represented in Figure 3. For building a model, the first step of the building workflow consist in normalizing the structures of the training series (normalize method), these structures are then used to compute the numerical description of their structures and to obtain the biological annotations present in the original file (extract method). With these, a QSAR model is built and validated (build method). The net result of this process is a predictive model, which is stored internally at the server. For carrying out predictions, the first step of the prediction workflow is to normalize the input structure and to compute the molecular descriptors exactly as it was done for the compounds of the training series. In eTOXlab this requirement is guaranteed because the very same methods (normalize and extract) are applied. The molecular descriptors together with the stored models are then used for producing the prediction (predict method). These pre-defined building and prediction workflows, like any other method of the model class, can be also overridden allowing the user to implement models that use completely different workflows.Figure 3

Bottom Line: The particular eTOXlab architecture as a self-contained, portable prediction engine allows building models with confidential information within corporate facilities, which can be safely exported and used for prediction without disclosing the structures of the training series.The technologies used by eTOXlab (web services, VM, object-oriented programming) provide an elegant solution to common practical issues; the system can be installed easily in heterogeneous environments and integrates well with other software.Moreover, the system provides a simple and safe solution for building models with confidential structures that can be shared without disclosing sensitive information.

View Article: PubMed Central - PubMed

Affiliation: Research Programme on Biomedical Informatics (GRIB), Department of Experimental and Health Sciences, Universitat Pompeu Fabra, IMIM (Hospital del Mar Medical Research Institute), Dr. Aiguader 88, E-08003 Barcelona, Spain.

ABSTRACT

Background: Computational models based in Quantitative-Structure Activity Relationship (QSAR) methodologies are widely used tools for predicting the biological properties of new compounds. In many instances, such models are used as a routine in the industry (e.g. food, cosmetic or pharmaceutical industry) for the early assessment of the biological properties of new compounds. However, most of the tools currently available for developing QSAR models are not well suited for supporting the whole QSAR model life cycle in production environments.

Results: We have developed eTOXlab; an open source modeling framework designed to be used at the core of a self-contained virtual machine that can be easily deployed in production environments, providing predictions as web services. eTOXlab consists on a collection of object-oriented Python modules with methods mapping common tasks of standard modeling workflows. This framework allows building and validating QSAR models as well as predicting the properties of new compounds using either a command line interface or a graphic user interface (GUI). Simple models can be easily generated by setting a few parameters, while more complex models can be implemented by overriding pieces of the original source code. eTOXlab benefits from the object-oriented capabilities of Python for providing high flexibility: any model implemented using eTOXlab inherits the features implemented in the parent model, like common tools and services or the automatic exposure of the models as prediction web services. The particular eTOXlab architecture as a self-contained, portable prediction engine allows building models with confidential information within corporate facilities, which can be safely exported and used for prediction without disclosing the structures of the training series.

Conclusions: The software presented here provides full support to the specific needs of users that want to develop, use and maintain predictive models in corporate environments. The technologies used by eTOXlab (web services, VM, object-oriented programming) provide an elegant solution to common practical issues; the system can be installed easily in heterogeneous environments and integrates well with other software. Moreover, the system provides a simple and safe solution for building models with confidential structures that can be shared without disclosing sensitive information.

No MeSH data available.


Related in: MedlinePlus