Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the pojo-accessibility domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/doctoral/public_html/wp-includes/functions.php on line 6121
ICDSUPL4-H027 – University of Life Sciences in Lublin

ICDSUPL4-H027

Volume: 4, 2025
4th International PhD Student’s Conference at the University of Life Sciences in Lublin, Poland:
ENVIRONMENT – PLANT – ANIMAL – PRODUCT

Abstract number: H027

DOI: https://doi.org/10.24326/ICDSUPL4.H027

Published online: 9 April 2025

ICDSUPL, 4, H027 (2025)


From genome to AI algorithm: mutations identified inpatients diagnosed with retinitis pigmentosa (RP)

Katarzyna Ognik1, Ewelina Cholewińska1*, Karolina Różaniecka1, Przemysław Sołek1, Ewelina Witkowska3, Agata Pietras2, Beata Gajda-Deryło2, Robert Rejdak2, Katarzyna Nowomiejska2

1 Department of Biochemistry and Toxicology, University of Life Sciences in Lublin, Akademicka 13, 20-950 Lublin, Poland

2 Chair and Department of General and Paediatric Ophthalmology, Medical University of Lublin, Chmielna 1, 20-079 Lublin, Poland

3 Rare Diseases Laboratory, UCML Genetics Laboratory, University Clinical Center of the Medical University of Warsaw, Banacha 1A, 02-097 Warszawa, Poland

* Corresponding author: ewelina.cholewińskal@up.lublin.pl

Abstract

The study aimed to determine mutations that determine the occurrence of a rare disease Retinitis pigmentosa (RP) among the Polish population and develop an AI algorithm to rapidly diagnose and monitor disease progression.
A total of 203 patients with ophthalmologically diagnosed RP symptoms were included in the study (102 women (50.25%) and 101 men (49.75%)). The blood samples were collected from patients, and the next DNA was isolated. These DNA were subjected to whole exome sequencing (WES), which was performed in the German CeGaT laboratory according to the ExomeXtra® protocol on the Illumina NovaSeq 6000 sequencer. The sequencing results were subjected to bioinformatic analysis to determine the mutations associated with RP and the pathogenicity of the detected variants.
The studies did not reveal any mutations or DNA copy number changes associated with RP in 40 patients (19.70%). In two patients (0.99%), DNA copy number changes (CNV) associated with RP were detected, and their include, respectively, a loss encompassing coding exons 7 to 19 of RPGR (Xp11.4, loss (0 copies), ~ 110.5 kb) and a heterozygous deletion encompassing exons 1-6 of the PRPF31 gene (19q13.42, deletion (1 copy), 13.9 kb). In 161 patients (79.31%), pathogenic, probably pathogenic, or uncertain significance variants associated with RP were detected. These pathogenic, probably pathogenic, or uncertain significance variants were most frequently observed in the ABCA4 (in thirty-two patients) and USH2A (in twenty-eight patients) genes. In the ABCA4 gene, thirty-two pathogenic, probably pathogenic, or uncertain variants associated with RP phenotypes were detected, and in the USH2A gene, thirty such variants were detected. Genes quite frequently affected by mutational changes also included RPGR (fourteen variants, fifteen patients), CDHR1 (two variants, thirteen patients), PROM1 (seven variants, nine patients), EYS (thirteen variants, eight patients), RHO (four variants, seven patients), NR2E3 (four variants, six patients), PRPF31 (four variants, six patients), RP1 (three variants, five patients) and PDE6B (five variants, four patients). Pathogenic, probably pathogenic or uncertain significance variants associated with RP were observed less frequently (in three or less patients) in the CNGA1, IMPG2, RP1L1, AGBL5, ALPK1, BBS5, BEST1, IFT140, MERTK, MYOC, NRL, PRPF3, PRPF8, PRPH2, ADAMTSL4, ADGRV1, AHI1, CEP290, CFAP410, CHM, CLN3, CRB1, FLVCR1, GNAT1, GUCY2D, HK1, IMPDH1, LCA5, MFRP, MT-ATP6, PCDH15, RBP3, RDH12, RLBP1, RP2, RPE65, SAG, SNRNP200, TOPORS, TRNT1, TUBB4B, USH1C and USH1G genes.
These results allow the conclusion that the most common cause of RP in the Polish population is mutations occurring in the ABCA4 and USH2A genes responsible for the disease Retinitis pigmentosa 19 phenotype (ABCA4) and Retinitis pigmentosa 39 phenotype (USH2A). These results will enable the selection of genes for the design of an original genetic panel, which is aimed at increasing the availability of RP diagnostics for patients.

The research was carried out within the Lublin Digital Union (LUC) and funded by the Ministry of Education and Science (actually Ministry of Science and Higher Education) in Poland, Grant No. MEiN/2023/DPI/2196.

Keywords: artificial intelligence, next-generation sequencing, mutation, retinitis pigmentosa


How to cite

K. Ognik, E. Cholewińska, K. Różaniecka, P. Sołek, E. Witkowska, A. Pietras, B. Gajda-Deryło, R. Rejdak, K. Nowomiejska, 2025. From genome to AI algorithm: mutations identified inpatients diagnosed with retinitis pigmentosa (RP). In: 4th International PhD Student’s Conference at the University of Life Sciences in Lublin, Poland: Environment – Plant – Animal – Product. https://doi.org/10.24326/ICDSUPL4.H027

Skip to content