Wdrożenia

IT tools

QSAR Lab’s research, development, and implementation activity focuses on developing a set of computer tools that enable a comprehensive assessment of the risks posed by new materials (including nanomaterials) to the natural environment and human health and life. Try the tools developed by our company.

TRY NOW!

QSAR Models for Predicting Nanoparticle Toxicity Alerts and Behavior

This is a unique online application, supported by machine learning (ML) algorithms, that enables the prediction of genotoxicity and mutagenicity alerts for TiO2 and SiO2 nanoparticles. In addition to information on potential toxicity, the application also provides data on the level of uncertainty with which the results should be treated – an innovation in QSAR models.

  Regulatory relevant endpoints & tests

   Reliable & accurate data aligned with EFSA recommendations

  Reducing time-consuming and costly experiments

  Simple and intuitive user-friendly interface

TRY NOW!

NAMs Database - all methods for hazard characterization in one place

NAMs.network is the first database of regulatory-relevant NAMs for assessing the safety of nanomaterials and chemicals. It is a comprehensive, easily accessible repository that collects all of the NAMs under EU and US regulations in one place, allowing you to extract state-of-the-art knowledge on different NAMs.

   Recently proposed & promising NAMs

  NAMs currently under validation or adaptation

  Already accepted & legally approved NAMs

Bioinformatics service supporting the design of molecular diagnostic tests

A unique web-based bioinformatics tool and service, powered by machine learning (ML) and artificial intelligence (AI), to help design and develop new molecular diagnostic tests for emerging or established diseases such as COVID-19. An innovative, experimentally validated algorithm optimizes virtual high-throughput screening (vHTS) and molecular docking of virtual peptide libraries consisting of all possible combinations of amino acid (AA) sequences for a given peptide length (4-12 AA).

    Library of over 25 billions peptide structures

  Molecular docking using force field

   Reduction of cost, time and computational power

TRY NOW

Model predicting BMD(L) values of multi-wall carbon nanotubes (MWCNT) in the context of AOP 173

TRY NOW

Model predicting the toxicity of nanoparticles towards the CHO-K1 cell line using SAPNet

Want to know more?