Shaza Ahmed

Artificial Intelligence and machine learning are increasingly used to interrogate complex biological data. This systematic review evaluates their application to multi-omics for the molecular characterization of hematological malignancies, an area with unmet clinical need. We searched PubMed, Embase, Institute of Electrical and Electronics Engineers Xplore, and Web of Science from January 2015 to December 2024. Two reviewers screened records, extracted data, and used a modified appraisal emphasizing explainability, performance, reproducibility, and ethics. From 2847 records, 89 studies met inclusion criteria. Studies focused on acute myeloid leukemia (34), acute lymphoblastic leukemia (23), and multiple myeloma (18). Other hematological diseases were less frequently studied. Methods included Support Vector Machines, Random Forests, and deep learning (28, 25, and 24 studies). Multi-omics integration was reported in 23 studies. External validation occurred in 31 studies, and explainability in 19. The median diagnostic area under the curve was 0.87 (interquartile range 0.81 to 0.94); deep learning reached 0.91 but offered the least explainability. Artificial Intelligence and machine learning show promise for molecular characterization, yet gaps in validation, interpretability, and standardization remain. Priorities include external validation, interpretable modeling, harmonized evaluation, and standardized reporting with shared benchmarks to enable safe, reproducible clinical translation.

Background: The P53 protein has an essential role in several cellular processes, including DNA repair, apoptosis, and cell cycle arrest. The pathophysiology of many cancer types has frequently been linked to polymorphisms in theTP53locus. Over 200 single nucleotide polymorphisms (SNPs) have been identified in TP53. However, Pro72Arg (rs1042522) at codon 72, shows contradictory results in terms of cancer risk. In this study, we aimed to determine if the Pro72Arg (rs1042522) SNP in theTP53gene would be linked to breast cancer (BC) risk among Egyptian patients.Materials and Methods: Genomic DNA was extracted from blood samples of 100 healthy volunteers and 100 breast cancer patients (50 familial and 50 non-familial).TP53Genotyping was performed using tetra-primer amplification refractory mutation (Tetra-ARMS) PCR. Data were analyzed using SNPstat software.Results: The prevalence ofTP53(Pro72Arg) rs1042522 genotypes carrying the high-risk allele [Pro/Arg (CG) and Arg/Arg (GG)] were significantly higher in BC patients compared to healthy volunteers and were associated with BC susceptibility (OR 0.2; [95% CI 0.11–0.38];P = 0.0001). However, there was no statistical significant difference in the prevalence ofTP53(Pro72Arg) rs1042522 genotypes carrying the high-risk allele between familial and non-familial BC patients. In addition, there was no association between the prevalence ofTP53(Pro72Arg) rs1042522 genotypes carrying the high-risk allele and BC patients’ clinical and pathological characteristics including tumor size, tumor grade, lymph node status, presence of lymphovascular invasion, expression of ER, PR and Her-2 in both of familial and non-familial BC patients.Conclusions: TP53(Pro72Arg) rs1042522 is more prevalent among BC patients but not associated with disease progression.

Introduction: Breast cancer (BC) is a multifactorial disease, that is attributed to non-familial factors such as environmental or genetic factors that play a vital role in the development of the disease. BRCA1/2 mutations represent a high risk of breast cancer. The current study focused on exploring the relationship between the presence of BRCA1/2 mutations and some clinicopathological characteristics which might impact the pathogenesis of BC disease. Material and Methods: Genomic DNA samples were obtained from 19 fresh tissues using Gene JET Extraction Kit (Thermo Scientific/US, Canada), and 29 FFPE using QIAamp DNA FFPE Tissue Kit (Qiagen, Valencia, USA) obtained from pretreatment BC patients. Library preparation was performed using Devyser BRCA NGS kit (DEVYSER, Stockholm, Sweden), according to the manufacturer's instructions. The reagent kit V2, 500 Cycles PE, on the Illumina MiSeq System (Illumina, San Diego, CA, USA). The BRCA1 and BRCA2 genes reference were: NM_007300 and NM_000059, respectively. Variants were called using freebayes (1.1.0.46) and annotated using ANNOVAR(version2019Oct24). All samples were subjected for detection of Human Mammary Tumor Virus (HMTV) and Human Papillomavirus (HPV) DNAs using qualitative PCR assay. Result: The study identified 40 and 54 different BRCA1 and BRCA2 mutations, mostly in the form of frameshift and stop codon mutations. Regarding, BRCA1, 14 pathogenic mutations were detected, exon10 and exon 9 showed to be the most affected exons representing (c.C1612T (25%) and c.C1471T(22.9%), respectively. For BRCA2, only five pathogenic mutations were identified, exon 11 and exon 14 showed to be the most affected exons (cT4001A(6.25%) and c.7231delA(4.16%), respectively. Regarding relation between BRCA1/2 genes mutations and clinicopathological parameters, BRCA1 and BRCA2 carriers were younger than non-carriers though not significant (p=0.440). Regarding the tumor characteristics, BRCA1/2 carriers had large tumor size (p=0.091), high tumor grade compared to non-carriers but without significance (P=0.098). Micro-classifications positivity (60%) was also more frequently among BRCA1/2 carrier than non-carrier (p= 0.082). Regarding detection of HMTV and HPV, BRCA1/2 mutation carriers has a skew towards negative results (P=<0.001 and 0.004, respectively). Conclusion: Our data suggest that BRCA1/2 mutations might contribute to the pathogenesis among both familial and non-familial Egyptian breast cancer patients, but we need more sample size to confirm the findings. It also identifies the most affected exons in preparation for establishing a diagnostic tool like HRM for genetic counseling, which will help when selecting treatment modalities for BC patients. STDF Acknowledgment: This project was supported financially by the Science and Technology Development Fund (STDF), Egypt, Grant No.22944 Citation Format: Samah A. Loutfy, Nasra F. Abdel Fattah, Ahmed B. Barakat, Omar R. Alfarouk, Tarek M. Hashem, Ahmed M. Osman, Shimaa A. Metwally, Maha A. Abo-Shadi, Amany M. Helal, Shaza A. Habib, Ahmed A. El Sherif, Abdel Wahab El Ghareeb, Mohamed M. Mouneer, Manar M. Moneer, Marwa A. Abdel-Wahed, Mona A. Salem, Asmaa M. M. M. Salama, Fatma S. Hafez, Sara H. Agwa, Hesham Elghazaly, Manal M. El-Mahdy, Mark J. Dunning, Sherif F. El-Khamisy. BRCA1 and BRCA2 mutations and its clinical relevance among egyptian breast cancer women [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2512.