Statistical component model to identify associations between chemicals and toxicological effects

August 10, 2017
Statistical component model to identify associations between chemicals and toxicological effects
The component model describes statistical links between chemicals and the effect of their molecular toxins. Credit: Juuso Parkkinen, Aalto University

The joint Aalto University, Karolinska Institute and Institute for Molecular Medicine Finland (FIMM) study included over 1,300 known pharmaceutical molecules, on which there is a wealth of measurement data available.

'The study uses systematic data-driven analysis to combine toxicity measurements taken on cell lines with gene expression responses describing gene activation. Toxicity includes growth inhibitory and cell killing effects. The method developed in the study makes it possible to more accurately predict the toxicity of new molecules because it makes use of advanced statistical methods and much bigger datasets than before,' explains Juuso Parkkinen, who completed his doctoral dissertation at Aalto University.

At present, is primarily measured by means of animal testing. Thanks to this new method, can be partly replaced in the future by a combination of cell line testing and statistical modelling. This would also result in considerable cost savings for pharmaceutical development.

'The new prediction can be applied to new pharmaceutical molecules and other chemicals currently in product development to eliminate possible toxic ,' adds Parkkinen.

Advances in statistical machine learning and methods have risen to play a crucial role in many application areas in addition to medical research.

'Juuso Parkkinen is an excellent example of the usefulness of Aalto University's artificial intelligence research and doctoral studies: He wrote his dissertation on medicinal applications in my research group and then transferred to Reaktor to apply data science to a wide range of business needs,' praises Parkkinen's dissertation adviser, Professor Samuel Kaski.

Explore further: Novel method to detect toxic effects of chemicals could reduce need for animal testing

More information: Pekka Kohonen et al. A transcriptomics data-driven gene space accurately predicts liver cytopathology and drug-induced liver injury, Nature Communications (2017). DOI: 10.1038/ncomms15932

Related Stories

Novel method to detect toxic effects of chemicals could reduce need for animal testing

April 24, 2017
Traditional toxicological investigations performed on animals (in vivo) are expensive, time-consuming and may cause animal suffering. But research from Umeå University demonstrates that a neuronal cell model, derived from ...

Researchers create deep learning algorithm that could boost drug development

April 3, 2017
Artificially intelligent algorithms can learn to identify amazingly subtle information, enabling them to distinguish between people in photos or to screen medical images as well as a doctor. But in most cases their ability ...

Evaluating low-dose toxicity from endocrine active chemicals

July 18, 2017
A new report by the National Academies of Sciences, Engineering, and Medicine proposes a strategy that the U.S. Environmental Protection Agency (EPA) should use to evaluate the evidence of adverse human health effects from ...

Recommended for you

Make way for hemoglobin

August 18, 2017
Every cell in the body, whether skin or muscle or brain, starts out as a generic cell that acquires its unique characteristics after undergoing a process of specialization. Nowhere is this process more dramatic than it is ...

Two-step process leads to cell immortalization and cancer

August 17, 2017
A mutation that helps make cells immortal is critical to the development of a tumor, but new research at the University of California, Berkeley suggests that becoming immortal is a more complicated process than originally ...

Female mouse embryos actively remove male reproductive systems

August 17, 2017
A protein called COUP-TFII determines whether a mouse embryo develops a male reproductive tract, according to researchers at the National Institutes of Health and their colleagues at Baylor College of Medicine, Houston. The ...

New Pathology Atlas maps genes in cancer to accelerate progress in personalized medicine

August 17, 2017
A new Pathology Atlas is launched today with an analysis of all human genes in all major cancers showing the consequence of their corresponding protein levels for overall patient survival. The difference in expression patterns ...

New technique overcomes genetic cause of infertility

August 17, 2017
Scientists have created healthy offspring from genetically infertile male mice, offering a potential new approach to tackling a common genetic cause of human infertility.

Inhibiting a protein found to reduce progression of Alzheimer's and ALS in mice

August 17, 2017
(Medical Xpress)—A team of researchers with Genetech Inc. and universities in Hamburg and San Francisco has found that inhibiting the creation of a protein leads to a reduction in the progression of Alzheimer's disease ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.