Impact of IFT variants in renal ciliopathies using AI-based tools

Variants in IFT genes are a frequent cause of renal ciliopathies, such as nephronophthisis (NPH) and autosomal dominant polycystic kidney disease (PKD). Furthermore, recent data from P5-Imagine indicates the presence of modifier alleles in IFTA genes in the context of NPHP1-associated NPH. We will study how these variants affect the structure and function of the IFT complex using deep-learning algorithms. (1) The severity of mutations will be assessed through Alpha missense, and their impact on structure and interactions will be examined using Alphafold modeling (coll. P4-UHEI) as well as through biochemical approaches (coll. P3-AU). (2) The most relevant alleles will be stably expressed as tagged forms in kidney cell lines invalidated for the respective IFTA subunit by CRISPR-Cas9. Their ability to rescue the phenotype associated with NPHP1 (cilia defects, transcriptomic profiling, etc) will also be investigated in NPHP1-invalidated cells. The impact on ciliogenesis and ciliary composition will be examined using an AI-based image analysis system (AP5-Medetia) and proximity labeling (coll. P1-RUMC), respectively. (3) In parallel, additional causative and modifier variants will be sought in ciliopathy cohorts from internal databases (> 2000) and existing ones. The genetic and molecular profiles will be linked to clinical phenotypes and disease progression using AI methodology such as patient similarity network (PSN) integration, will use PSN framework to integrate diverse data types and to identify biological features characteristic of disease with the aim for clinical risk factor assessment. 

Fellow profile: Master degree in Life Sciences, Biomedical science, Biology, or related field. This project is very suitable for students with a keen interest in molecular biology who are motivated to develop AI/ML-based image analysis and data integration.