Digital Methods in Life Sciences: Using digitisation to create value from data in applied life sciences

The vision of developping integrated intelligence for diagnostics and therapeutics with the development of computational and machine learning algorithms and implementation of databases for knowledge representation and discovery in the life sciences.

Clinical, Laboratory and Multi-Omics Data to Leverage Machine Learning for Personalized Diagnostics
Prof. Dr. Enkelejda Miho, Group leader Laboratory of Artificial Intelligence in Health, FHNW School of Life Sciences

The early and accurate diagnosis of disea-ses is imperative for the inhibition disease progression and the identification of appropriate therapeutics. The precise diagnosis of autoimmune diseases is notoriously challenging due to nonspecific symptoms. Clinical decision support software (CDSS) tools support clinicians
to assign patients to a disease category. We developed the Personalis platform, a CDSS aimed to demultiplex complex autoimmune diseases. We applied machine learning models to medical datasets such as clinical, laboratory and multi-omics data. Neural networks, support vector machines and random forests predict autoimmune diseases with more than 95% prediction accuracy and prediction accuracy increases when clinical values are integrated with additional laboratory results, such as cytokine concentration, and genetics, immunomics and metabolomics data.

Single-Cell Full-Length Isoform Sequencing of patient-derived organoid cells in clear cell Renal Cell Carcinoma
Dr. Abdullah Kahraman, Group leader Data Science in Life Sciences, FHNW School of Life Sciences

Clear cell Renal Cell Carcinoma (ccRCC) is a heterogenous, lethal, and aggressive cancer that arises in kidney tubules. Late-stage ccRCC patients tend to be resistant to various chemotherapies. Their 5-year survival rate is less than 10%. Therefore, identifying new drug targets and predictive biomarkers is urgently needed. To get a more reliable overview of full-length transcripts in ccRCC and search for patho-genic and druggable splicing events, we have utilized single-cell long-read sequencing in four patient-derived ccRCC organoids. Our results and analyses are revealing novel transcripts and differences in transcript expression on single cell resolution. We hope that our approach will provide new diagnostic and predictive biomarker candidates and give ccRCC patients new hope for novel precision medicine treatments against their detrimental disease.

The event is followed by an apéro.