He has a strong scientific background in the field of chem/bio/nanoinformatics, modelling, simulation, and medicinal & materials chemistry. His scientific work has been published in over 90 original research articles and reviews in international peer-reviewed journals. According to Google Scholar, his h-index is 30. He successfully coordinated applied drug discovery projects and based on the results 3 patents were filed. He has successfully led the efforts on the development and implementation of state-of-the-art information technology systems (database, web services, custom made scientific software development) in NovaMechanics Ltd for solving Cheminformatics, Bioinformatics, Nanoinformatics, Modelling, Simulation and Big Data analysis problems. He has supervised all the R&D activities and the product development of the company (Isalos Analytics Platform, Enalos+ KNIME nodes, Enalos Cloud Platform, Enalos Suite etc). As a Director at NovaMechanics Ltd, he has led several efforts for the development of computational infrastructures of scientific and technological excellence at a national and European level that have contributed decisively to the support of new scientists. He participates as a PI with NovaMechanics in 29 multi-partner & international cooperation Research Projects. Currently he is the Coordinator of the materials informatics projects NanoSolveIT (H2020 project, budget €6M, 24 partners) and CompSafeNano (Marie Curie RISE, budget €1,7M, 22 partners)
OpenTox Summer School 2022
Applications and Exercises in Image Analysis and Chem/Nano informatics Applications using Enalos Tools
Dimitra Danai Varsou, Panayiotis Kolokathis, Panayiotis Lagarias, Nikolaos Cheimarios, Konstantinos D. Papavasileiou, Anastasios Papadiamantis , Andreas Tsoumanis, Antreas Afantitis
Drug discovery and nanomaterials, complex and advance materials design require extensive experimental time and resources. These can be facilitated through the use of in silico workflows for the analysis of large datasets of chemicals and materials along with corresponding properties/activities, as well as the retrieval and virtual screening of more structures in an effort to identify new structures with desired properties or activity. This is a computationally demanding task, since it requires the combination of different tools and workflows and can be facilitated by NovaMechanics tools that require minimal to none coding experience
NovaMechanics is a nano-, bio- and cheminformatics R&D company, automating the data analysis and exploitation process through powerful and user-friendly tools. These facilitate a variety of important tasks to construct workflows that simplify the handling, processing, and modelling of nano/chem informatics data and provide time and cost-efficient solutions, reproducible and easier to maintain.
Enalos toolbox including more than 50 processing modules, the Enalos+ & Enalos Asclepios KNIME nodes, available through the open source KNIME platform, will be presented for users interested in the nanoinformatics and cheminformatics analysis of chemical and biological data. The Enalos+ & Enalos Asclepios KNIME nodes provide a broad range of important functionalities including data mining and retrieval from large available databases and tools for robust and predictive model development and validation. Enalos Nodes are available through KNIME as add-ins and offer valuable tools for extracting useful information and analyzing experimental and virtual screening results in a chem- or nano- informatics framework.
In addition, the Enalos Cloud Platform http://www.enaloscloud.novamechanics.com/ hosting data-driven, machine learning & artificial intelligence models and tools will be presented. Among the available tools, Nanomaterials occupational exposure & lung exposure dose simulation tools will be presented. In addition, the NanoXtract Tool will be specifically demonstrated. NanoXtract is an image analysis online tool for the calculation of image descriptors based on Transmission Electron Microscopy (TEM) images of nanomaterials.
Full documentation of all tools, tutorials, and exercises will be given to the participants.
OpenTox 2022 Virtual Conference
Isalos Analytics and Enalos Cloud Platform: A Machine Learning / Artificial Intelligence Zero Code Platform for Cheminformatics & NanoInformatics
The growing trend of employing machine learning and data analysis methods in various disciplines and sectors that are not strongly associated to informatics (e.g., marketing, social sciences), requires the use of algorithms by individuals or professionals who in many cases lack deep programming skills. Thus, there is a need to access and utilize these techniques through easy-to-use, and intuitive environments, which at the same time offer access to powerful computing tools without the need for code development. The Isalos Predictive Analytics Platform addresses these needs, as it offers a plethora of ready-to-use, well-known machine learning methods without the need of any coding skills. These methods can be implemented through a user-friendly and easy-to-learn graphical interface. In this work we present and discuss, with the aid of case studies, the main features of the Isalos platform to facilitate data analysis and modelling. Current needs in both drug and material design render the development of robust and reliable in silico models inevitable. Models and tools developed can greatly underpin the efforts for assessing the risk of chemical compounds and (engineered) nanomaterials, reducing the time and resources spend in experimental activities. However, while several predictive models have been built for assessing the toxic side-effects of small molecules and ENMs, these remain unexploited by the wider community as the developed predictive models have not been properly disseminated. All models developed should be integrated within a simple and user- friendly environment to reach all interested users and facilitate decisions making. Enalos Cloud Platform (http://www.enaloscloud.novamechanics.com/), supported by Isalos Analytics Platform algorithms and nanoPharos database https://db.nanopharos.eu/Queries/Datasets.zul?datasetID=1) , addresses exactly this need for a user friendly interface that can produce in few steps toxicity predictions and property calculations for chemical structures or ENMs through web-services. The integrated models are built on reliable well known open source algorithms as well as proprietary software (e.g., Enalos+ nodes).
Predictions are performed shortly after data input and are accompanied always by an indication of their
reliability based on the results of the fully validated models running in the background. The produced results can be downloaded for further analysis and exploration contributing in this way -depending on the type of the background model- in the understanding of activity mechanisms and read-across similarities. Enalos Cloud Platform hosts at the time of writing 25 predictive models released as web services that can contribute to different aspects of material design and development, drug discovery, virtual screening of chemical substances, nanosafety and safe-by-design (nano)materials. The platform is an easy-to-use portal where web-services are arranged by categories of use (cheminformatics, nanoinformatics, image analysis, exposure and biokinetics models) and projects so that users can quickly explore and choose the tool of their preference. Finally, the web-services’ interface is carefully designed with the aim of being simple and user friendly, to also allow users without any informatics background to easily use the models and benefit from the
produced predictions and results.
ACKNOWLEDGMENT
This work was funded by the EU H2020 research and innovation projects NanoSolveIT (Grant Agreement No. 814572), SABYDOMA (Grant Agreement No. 862296), Scenarios (Grant Agreement No. 101037509), DIAGONAL (Grant Agreement No. 953152), RiskGONE (Grant Agreement No. 814425), CY-Biobank (Grant Agreement nº 857122), and the EU H2020 research infrastructure NanoCommons programme (Grant Agreement No. 731032).