Jaqpot is a computational platform for in silico modelling of chemical compounds, that provides both access to its services both over a User Interface (GUI) and an Application Programming Interface (API). It is a cloud-ready application that uses the benefits of Java, R and Python, having incorporated functionality by various established and open-source machine learning and data analysis toolkits, while algorithms in any programming algorithm can be added to Jaqpot. A new version of the UI and API is in preparation and will be released within 2019 (Jaqpot 5).

The UI is a user-friendly path for non-developers to explore its functionality, while the API provides developers with great power to enhance existing 3rd-party apps, tools, Graphical User Interfaces (GUIs), and Jupyter notebooks by integrating integrate Jaqpot modelling and analysis services into them.

At the same time, third parties can easily contribute and integrate their services into the Jaqpot infrastructure provided that they make them API compliant. Thus, Jaqpot's architecture paves the way to the creation of a modeling ecosystem where independent systems contribute and collaborate while maintaining their autonomy, provided that they adhere to the API.

Jaqpot was originally developed by NTUA during the FP7 OpenTox project according to the OpenTox APIs and considerably extended in the H2020 eNanoMapper project to include additional modelling functionalities, some of them addressing the special requirements emerging from the complex and multi-perspective characterisation of NMs. The Jaqpot API has been integrated in the ongoing H2020 OpenRiskNet project as a component of the overall e-infrastructure, with extensions to address additional modelling and analysis requirements and use cases, such as biokinetics and dose-response modelling. The OpenRiskNet infrastructure will live on through the NanoCommons project. https://app.jaqpot.org/

Jaqpot Quattro (JQ) is a web application for predictive model development, validation, testing and calculating model predictions. The JQ user interface (http://www.jaqpot.org/) had its first beta release in April 2016. It enables non modelling-proficient users to have easy access to all JQ tools and applications, but also to a repository of validated models. Second release coming soon! The Application Programming Interface (API) adheres to the the REST architectural constraints, is an extension of the original OpenTox API and has been documentated using swagger: http://jaqpot.org:8080/jaqpot/swagger/

A Jaqpot Docker image is available at https://hub.docker.com/r/jaqpot/jaqpot-core/ that guarantees reproducibility of results and full compatibility at all times.

A number of API compatible web services that implement major machine learning, and statistical algorithms used for preprocessing, regression, classification, clustering and model validation and for defining the domain of applicability. An indicative but not exhaustive list of methods include: multivariable linear regression, Lasso, Elastic net, hierarchical clustering, bi-clustering, ID3 decision tree, partial least squares, partial least squares with Variable Importance in Projection (VIP) variable selection, radial basis function neural networks, support vector machines. The Jaqpot Protocol of Data Interchange (JPDI) allows developers of modelling algorithms to integrate their implementations in the framework, using the OpenTox algorithms ontology. JQ provides full integration with  the R and Python languages and the WEKA machine learning software, so any algorithm written in these languages can be included in the system:

http://app.jaqpot.org:8080/jaqpot/services/algorithm/ocpu-lm
http://app.jaqpot.org:8080/jaqpot/services/algorithm/pmml
http://app.jaqpot.org:8080/jaqpot/services/algorithm/ocpu-glmnet
http://app.jaqpot.org:8080/jaqpot/services/algorithm/ocpu-clustering
http://app.jaqpot.org:8080/jaqpot/services/algorithm/ocpu-go
http://app.jaqpot.org:8080/jaqpot/services/algorithm/weka-mlr
http://app.jaqpot.org:8080/jaqpot/services/algorithm/weka-svm
http://app.jaqpot.org:8080/jaqpot/services/algorithm/weka-pls
http://app.jaqpot.org:8080/jaqpot/services/algorithm/weka-rbf
http://app.jaqpot.org:8080/jaqpot/services/algorithm/scaling
http://app.jaqpot.org:8080/jaqpot/services/algorithm/standarization
http://app.jaqpot.org:8080/jaqpot/services/algorithm/leverage
http://app.jaqpot.org:8080/jaqpot/services/algorithm/python-lm
http://app.jaqpot.org:8080/jaqpot/services/algorithm/python-pls-vip
http://app.jaqpot.org:8080/jaqpot/services/algorithm/python-id3-mci
http://app.jaqpot.org:8080/jaqpot/services/algorithm/python-lasso

NanoImage, part of the Jaqpot Platform, offers tools for analysis of electron microscopy images, allowing the user to derive descriptors for the materials directly from the images, offering distinct advantage over manual procedures, in terms of speed and ability to represent the whole sample. It is not up to the microscope operator to capture measurements that express the frequency of occurrence of materials with certain dimensions/shapes or the presence of materials with outlier dimensions/shapes. https://github.com/enanomapper/imageAnalysis, Prototype: https://app.jaqpot.org/nanoImage/

ExpDesign is an R package that performs optimal experimental design. Full factorial design and the D-optimal, A-optimal and I-optimal experimental design algorithms are included. Link: https://github.com/enanomapper/ExpDesign

RRegrs is an R package for computer aided model selection and easy-to-use model comparison. It automates the estimation of the best regression model by using certain cross validation schemes and by searching over many different algorithms and tuning the parameters in each algorithm. Other resampling procedures are also included to minimize the variability errors, such as data splitting, repeated cross-validation, Y-randomization. Additionally normalization and filtering options are included. (Collaboration with University of Maastricht). Link: https://github.com/enanomapper/RRegrs

IntPROAST R package for training dose-response models based on the PROAST software. The model can identify the dose of a substance that is expected to result in a pre-specified level of effect (benchmark response, BMR).

PBPK models A user application for creating and simulating PBPK models and for calculating optimal continuous dosing strategies based on the Model Predictive Control (MPC) methodology. Link: http://147.102.82.32:8088/

MyDosage is a mobile friendly web application that helps doctors personalize the dosage of drugs for their patients. Personal data is used as input along with the different input requirements that each drug algorithm requires. Reports are exported in the form of graphs and values. Link: http://147.102.86.129:8080/my-dosage/#/

toxFlow is a web-application developed for enrichment analysis of omics data and toxicity prediction. A sequential analysis workflow is suggested where users can filter omics data using enrichment scores and incorporate their findings into a correlation-based read-across technique for predicting a toxicity index based on its analogs. Either embedded or in-house gene signature libraries can be used for enrichment analysis. Visualization options are offered to interactively explore correlation patterns in the data, whereas results can be exported for further analysis. Link: toxflow.jaqpot.org