Sbir phase I: computational platform to infer putative causative pathways of pathology using spatial omics data

This $255,994 Project Grant from the National Science Foundation's Engineering program (CFDA 47.041) will fund Sygnamap Inc. to develop a computational platform using spatial omics data to infer putative causative pathways of kidney disease. The platform will leverage mass spectrometry imaging and artificial intelligence/machine learning approaches to correlate and optimize the localization of molecules with pathologic features. This will identify key biochemical pathways that drive disease development. Converting semi-quantitative mass spectrometry output to rigorous quantitative results will enable the identification of pathways driving disease. The anticipated technical results include technologies that can infer disease causation at a spatial level, with the broader impacts of improving clinical outcomes and quality of life for those with kidney disease through enabling personalized treatments. The period of performance is February 15, 2022 through January 31, 2023.

Abstract

The broader impact of this small business innovation research (SBIR) phase I project will be to improve clinical outcomes and quality of life for kidney disease. This technology will help identify biomarkers and enable new personalized treatments to improve efficacy and reduce harmful side effects. The innovation will leverage new enhancements in visualizing molecules in biological samples and will improve scientific understanding of complex diseases. The proposed project will leverage the power of the emerging field of spatial omics to build a novel computational platform. Multi-omics technology at a spatial level is changing our understanding of complex conditions, such as cancer and metabolic diseases. These technologies are important to better understand heterogeneity of normal organ structure and changes during the development of complex chronic metabolic diseases and cancers. Mass spectrometry-based platforms have led multi-omic spatial applications, but quantifying the output of mass spectrometry imaging remains a challenge. The research objectives are to correlate and optimize localization of molecules with pathologic features and identify key biochemical pathways that drive disease development. The methods will include computational pathology, mass spectrometry imaging, and artificial intelligence/ machine learning approaches. The anticipated technical results will be development of technologies that convert semi-quantitative output to rigorous, quantitative results for identification of pathways driving disease development. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.