At next week’s Bio IT World conference and expo (Boston, May 15-17), Elsevier will be giving four talks on the implications of AI and machine learning on life science research, a statistical analysis of concordance between animal toxicities and human adverse events, strategies for increasing data sharing and the latest technologies being used to integrate multiple data sources.
If you plan on attending, please be sure to join us in these sessions:
AI, Machine Learning and Big Data for life sciences; the good the bad and the ugly (BioInformatics Track)
Frederik van den Broek, Ph.D., Consultant, R&D Solutions, Elsevier
Wednesday, May 16 at 12:40 pm
Many believe that Artificial Intelligence has the potential to revolutionize life sciences and healthcare. However, there are significant pitfalls in the application of AI and Big Data. This talk will present an overview of best and worst practices in applying AI and Machine learning to life sciences to facilitate successful use of these techniques in today’s competitive drug discovery environment.
CO-PRESENTATION: How well do toxicology studies predict clinical safety outcome – A translational safety big data analysis (Clinical Research & Translational Informatics Track)
Thomas Steger-Hartmann, Investigational Toxicology, Bayer AG
Matthew Clark, PhD, Scientific Services, R&D Solutions, Elsevier
Wednesday, May 16 at 2:25 pm
We present the results of a statistical analysis of concordance between animal toxicities and human adverse events based on data available for 3290 compounds from the database Pharmapendium. Our work will provide answers to the implication of an observation in an animal for human risk and more specifically to the question whether concordance, i.e. the translatability of an observation from animal to human, is dependent on the animal species.
Setting a Course for FAIRness in Scientific Research (FAIR Data for Genomics Applications Track)
Helena Deus, PhD, Director, Disruptive Technologies, Elsevier
Thursday, May 17 at 10:40 am
About 73% of researchers agree that sharing data is important. However, as many as 34% of researchers admit to not share their data at all, and many believe that there is no credit attached to sharing data. As scientific biomedical data increases in both size and complexity, the lack of incentives and training needed to properly share experimental results is likely responsible for widening this gap. Learn about some of the strategies being used to close the gap, with a special emphasis on genomic information and sharing sequencing results.
Zen and the Art of Data Science Maintenance 12:50pm (Pharmaceutical R&D Informatics Track)
Jabe Wilson, Ph.D., Consulting Director, Text and Data Analytics, Elsevier
Thursday, May 17 at 12:50 pm
You want insights from your Data: Use historic data for predictive modeling, power virtualized R&D for data sharing, and, mine real world data to understand patients and markets. Is this an Art or a Science? Learn how you can use current technologies to integrate multiple data sources into a semantic infrastructure, enabling delivery of data for machine learning processes.