Nicolas Arning
Machine Learner Multi-omics and Imaging @Bayer
Signup · Get unlimited contacts
WORK HISTORY
Machine Learner Multi-omics and Imaging @Bayer
Monheim, DE
I work on applying machine learning models to high throughput transcription data at Bayer. For this mean I have developed an RNAseq processing pipeline in nextflow that runs on cloud servers which handles read processing up to differential expression analysis. I work in close collaboration with lab scientist and other machine learning researchers at Bayer.
EDUCATION
University of Oxford
Dphil
University of Münster
Master of Science - MS
The University of British Columbia
Master of Science - MS
The University of Sheffield
Bachelor of Science - BS
University of Münster
Bachelor of Science - BS
ABOUT NICOLAS ARNING
I am a data scientist with a passion for leveraging machine learning, deep learning, bioinformatics and multi-omics integration to create a holistic biological understanding from the wealth of omics data. In my current role at Bayer, I have expanded my focus from transcriptomic data to a broader spectrum of Omics technologies and imaging data, directly supporting our pipeline. My work centers on integrating transcriptomic data with cell painting images additional to protein-ligand matching to investigate biological responses to our compounds which narrows the near infinite space of chemical possibilities. I collaborate closely with lab scientists to design experiments and curate data from the ground up—handling processing, cleaning, initial analysis, multi-modal data integration, and reporting. Using this high-quality data, I develop machine learning and deep learning models to uncover novel insights into the mechanism of action of our chemistry. Additionally, I am the sub-project lead for active learning at Bayer with focus on multi-omics, I lead the Bioinformatics cross-team, coordinate the \"Target/Mode of Action\" cluster within the Data Science hub, and oversee the multi-omics data creation process, which has generated over multi-modal data points. Prior to this, I worked as a scientist in data analysis and machine learning at Bayer, where I focused on massively multiplexed transcriptomic data. I implemented and maintained a processing pipeline using Python, R, and Bash in a Nextflow-AWS cloud environment, while also building machine learning models to extract meaningful insights from large-scale transcriptomic datasets. Before joining Bayer, I was a health data scientist at the Big Data Institute at the University of Oxford, applying Bayesian model averaging to analyze COVID-19 risk factors using UK Biobank data. I hold a PhD from the University of Oxford, where I applied machine learning in genomics, working with eukaryotic, viral, and bacterial DNA, as well as heterogeneous data from UK Biobank. My research has been published in leading journals, including Nature, Nature Ecology & Evolution, and The New England Journal of Medicine. During my PhD, I founded and led the DTC Coding Dojo, a peer support network for bioinformatics challenges. I have also taught and supervised undergraduate and postgraduate students in bioinformatics. I am a full-stack omics data scientist taking care of all in silico steps between designing experiments to building AI models to create actionable insights. Website: nicolas-arning.com
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.