The diagnosis of rare genetic diseases is often challenging due to the complexity of the genetic underpinnings of these conditions and the limited availability of diagnostic tools. Machine learning (ML) algorithms have the potential to improve the accuracy and speed of diagnosis by analyzing large amounts of genomic data and identifying complex multiallelic patterns that may be associated with specific diseases. In this systematic review, we aimed to identify the methodological trends and the ML application areas in rare genetic diseases. We performed a systematic review of the literature following the PRISMA guidelines to search studies that used ML approaches to enhance the diagnosis of rare genetic diseases. Studies that used DNA-based sequencing data and a variety of ML algorithms were included, summarized, and analyzed using bibliometric methods, visualization tools, and a feature co-occurrence analysis. Our search identified 22 studies that met the inclusion criteria. We found that exome sequencing was the most frequently used sequencing technology (59%), and rare neoplastic diseases were the most prevalent disease scenario (59%). In rare neoplasms, the most frequent applications of ML models were the differential diagnosis or stratification of patients (38.5%) and the identification of somatic mutations (30.8%). In other rare diseases, the most frequent goals were the prioritization of rare variants or genes (55.5%) and the identification of biallelic or digenic inheritance (33.3%). The most employed method was the random forest algorithm (54.5%). In addition, the features of the datasets needed for training these algorithms were distinctive depending on the goal pursued, including the mutational load in each gene for the differential diagnosis of patients, or the combination of genotype features and sequence-derived features (such as GC-content) for the identification of somatic mutations. ML algorithms based on sequencing data are mainly used for the diagnosis of rare neoplastic diseases, with random forest being the most common approach. We identified key features in the datasets used for training these ML models according to the objective pursued. These features can support the development of future ML models in the diagnosis of rare genetic diseases.

Hydroxytyrosol (HT), the main representative of polyphenols of olive oil, has been described as one of the most powerful natural antioxidants, also showing anti-inflammatory, antimicrobial, cardioprotective and anticancer activity in different type of cancers, but has been little studied in hematological neoplasms. The objective of this work was to evaluate the anticancer potential of HT in acute human leukemia T cells (Jurkat and HL60) and the anti-inflammatory potential in murine macrophages (Raw264.7). For this, cytotoxicity tests were performed for HT, showing IC₅₀ values, at 24 h, for Jurkat, HL60 and Raw264.7 cells, of 27.3 µg·mL⁻¹, 109.8 µg·mL⁻¹ and 45.7 µg·mL⁻¹, respectively. At the same time, HT caused cell arrest in G₀/G₁ phase in both Jurkat and HL60 cells by increasing G₀/G₁ phase and significantly decreasing S phase. Apoptosis and cell cycle assays revealed an antiproliferative effect of HT, decreasing the percentage of dividing cells and increasing apoptosis. Furthermore, HT inhibited the PI3K signaling pathway and, consequently, the MAPK pathway was activated. Inflammation tests revealed that HT acts as an anti-inflammatory agent, reducing NO levels in Raw264.7 cells previously stimulated by lipopolysaccharide (LPS). These processes were confirmed by the changes in the expression of the main markers of inflammation and cancer. In conclusion, HT has an anticancer and anti-inflammatory effect in the cell lines studied, which were Raw264.7, Jurkat, and HL60, and could be used as a natural drug in the treatment of liquid cancers, leukemias, myelomas and lymphomas.

Natural products have a significant role in the development of new drugs, being relevant the pentacyclic triterpenes extracted from Olea europaea L. Anticancer effect of uvaol, a natural triterpene, has been scarcely studied. The aim of this study was to understand the anticancer mechanism of uvaol in the HepG2 cell line. Cytotoxicity results showed a selectivity effect of uvaol with higher influence in HepG2 than WRL68 cells used as control. Our results show that uvaol has a clear and selective anticancer activity in HepG2 cells supported by a significant anti-migratory capacity and a significant increase in the expression of HSP-60. Furthermore, the administration of this triterpene induces cell arrest in the G₀/G₁ phase, as well as an increase in the rate of cell apoptosis. These results are supported by a decrease in the expression of the anti-apoptotic protein Bcl2, an increase in the expression of the pro-apoptotic protein Bax, together with a down-regulation of the AKT/PI3K signaling pathway. A reduction in reactive oxygen species (ROS) levels in HepG2 cells was also observed. Altogether, results showed anti-proliferative and pro-apoptotic effect of uvaol on hepatocellular carcinoma, constituting an interesting challenge in the development of new treatments against this type of cancer.

Meniere disease (MD) is a chronic inner ear disorder with significant heritability. This study compares the burden of rare high‐ and moderate‐impact coding variants in an MD cohort to determine whether genetic burden in sporadic MD (SMD) overlaps familial MD (FMD), potentially revealing hidden inheritance in SMD. Exome sequencing identified rare variants in unrelated FMD ( N = 93) and SMD ( N = 287) patients. Gene Burden Analysis (GBA) was performed, and candidate genes were prioritized using the number of variant carriers, inner‐ear expression, and hearing/balance‐related phenotypic annotations. FMD patients showed higher accumulation of missense and loss‐of‐function variants than SMD, especially in genes linked to auditory and vestibular function. GBA identified 269 enriched genes in SMD, with 31 annotated for inner ear phenotypes, while FMD had 432 with 51 pinpointed. Sporadic and FMD overlapped in 28.1% of enriched genes, with ADGRV1 , MEGF8 , and MYO7A most commonly shared. Auditory brainstem responses from knockout mouse models supported hearing loss of three novel MD candidate genes ( NIN , CCDC88C , and ANKRD24 ), consistent with patient hearing profiles. In conclusion, SMD and FMD have a divergent genetic architecture. The enrichment of missense variants in stria vascularis and hair cell stereocilia genes supports distinct pathogenic mechanisms and a multiallelic‐recessive inheritance pattern in MD.

Meniere disease is a complex inner ear disorder with significant familial aggregation. A differential prevalence of familial MD (FMD) has been reported, being 9–10% in Europeans compared to 6% in East Asians. A broad genetic heterogeneity in FMD has been described, OTOG being the most common mutated gene, with a compound heterozygous recessive inheritance. We hypothesize that an OTOG-related founder effect may explain the higher prevalence of FMD in the European population. Therefore, the present study aimed to compare the allele frequency (AF) and distribution of OTOG rare variants across different populations. For this purpose, the coding regions with high constraint (low density of rare variants) were retrieved in the OTOG coding sequence in Non-Finnish European (NFE).. Missense variants (AF < 0.01) were selected from a 100 FMD patient cohort, and their population AF was annotated using gnomAD v2.1. A linkage analysis was performed, and odds ratios were calculated to compare AF between NFE and other populations. Thirteen rare missense variants were observed in 13 FMD patients, with 2 variants (rs61978648 and rs61736002) shared by 5 individuals and another variant (rs117315845) shared by two individuals. The results confirm the observed enrichment of OTOG rare missense variants in FMD. Furthermore, eight variants were enriched in the NFE population, and six of them were in constrained regions. Structural modeling predicts five missense variants that could alter the otogelin stability. We conclude that several variants reported in FMD are in constraint regions, and they may have a founder effect and explain the burden of FMD in the European population.