UMF

Lung squamous cell carcinoma therapeutic targets using systems-level machine learning based on single-cell rna-sequencing

Screenshot 2024 03 29 at 15.03.32

Contract no: 760066/23.05.2023

Code: 83/15.11.2022

Project title: LUNG SQUAMOUS CELL CARCINOMA THERAPEUTIC TARGETS USING SYSTEMS-LEVEL MACHINE LEARNING BASED ON SINGLE-CELL RNA-SEQUENCING

Budget: 7.637.115,98 RON (PNNR 7.000.000 RON plus 637.115,98 RON VAT).

Duration of the project: 36 months (between 01.07.2023-30.06.2026)

Project Director: Prof.Dr. ANDREAS BENDER, Cambridge University, UK

The implementation place: Centrul de Cercetări pentru Genomică Funcţională, Biomedicină şi Medicină Translaţională al Universitatatii de Medicină și Farmacie “Iuliu Hațieganu” Cluj-Napoca

Summary

In the context of emerging high throughput technologies and the generation of big data, artificial intelligence (AI) and related technologies are beginning to be used also in health care. Single-cell RNA sequencing (scRNA-seq) is one of the newest techniques in molecular biology. Data generated can be analyzed using complex computational and statistical methods to unravel the tumor complexity in cellular subpopulations and the dynamic cellular processes that occur. Investigating the tumor microenvironment (TME) and the immune cell within the tumor and their interaction is crucial in understanding the tumor development and progression. Lung squamous cell carcinoma (LUSC) represents one of the most consistent threats worldwide, and more than 80% of patients with LUSC have no therapeutic options. For LUSC understanding, the current project is developed to generate data regarding transcriptomics profiling of LUSC tumors and their TME using scRNA-seq, exploit using AI and bioinformatics methods new targetable molecules and the corresponding therapeutic compound and validate these findings and the accuracy of the machine learning algorithm in vivo experiments to advance drug discovery for LUSC patients. Through the proposed results, the project will contribute to innovation in oncology and the rapid analysis of the tumor and TME cellular subpopulation profiling in LUSC patients. The project focuses on AI using ML algorithms, one of the newest improvements in health innovation. We will use AI for both the clustering of cellular tumor components and TME and the prediction of precision models for therapy based on the cellular subpopulations of the tumors.

General aim

Development of a targeted approach for precision medicine in LUSC patients using AI and ML algorithms based on scRNAseq data and its validation in PDX models.

Specific Objectives

SO1. Development of a prospective integrated LUSC biorepository of 120 fresh frozen tumor tissues/normal adjacent tissuesstage III and IV and associated blood samples (360 samples – blood, serum plasma).

SO2. Characterization of tumor and its TME cells’ subpopulations, constitution and clustering using scRNA-Seq analysis.

SO3. Development of LUSC/TME experimental design: PDX orthotopic models based on the patients biopsy to be further used for drug discovery and in vivo validation.

SO4. ML-based models trained on scRNA-seq data and clusterisation of the cellular subpopulations to identify drug targets for LUSC/TME.

SO5. Validation of predicted drug combinations and drug targets using the models developed in SO3.

 

„PNRR. Finanțat de Uniunea Europeană – UrmătoareaGenerațieUE”

“Conținutul acestui material nu reprezintă în mod obligatoriu poziția oficială a Uniunii Europene sau a Guvernului României“

https://mfe.gov.ro/pnrr/ ; https://www.facebook.com/PNRROficial