Accurate variant classification is critical for genetic diagnosis. Variants without clear classification, known as “variants of uncertain significance” (VUS), pose a significant diagnostic challenge. This study examines AlphaMissense performance in variant classification, specifically for VUS. A systematic comparison between AlphaMissense predictions and predictions based on curated evidence according to the ACMG/AMP classification guidelines was conducted for 5845 missense variants in 59 genes associated with representative Mendelian disorders. A framework for quantifying and modeling VUS pathogenicity was used to facilitate comparison. Manual reviewing classified 5845 variants as 4085 VUS, 1576 pathogenic/likely pathogenic, and 184 benign/likely benign. Pathogenicity predictions based on AlphaMissense and ACMG guidelines were concordant for 1887 variants (1352 pathogenic, 132 benign, and 403 VUS/ambiguous). The sensitivity and specificity of AlphaMissense predictions for pathogenicity were 92% and 78%. Moreover, the quantification of VUS evidence and heatmaps weakly correlated with the AlphaMissense score. For VUS without computational evidence, incorporating AlphaMissense changed the VUS quantification for 878 variants, while 56 were reclassified as likely pathogenic. When AlphaMissense replaced existing computational evidence for all VUS, 1709 variants changed quantified criteria while 63 were reclassified as likely pathogenic. Our research suggests that the augmentation of AlphaMissense with empirical evidence may improve performance by incorporating a quantitative framework to aid in VUS classification.

Introduction: Classification of genetic variants has significant implications for clinical management. Artificial Intelligence (AI) has the potential to transform classification of genetic variants, such as AlphaMissense, which incorporates structure-function relationships and allele frequencies across large datasets of genetic variants. While this represents a promising new tool, the performance of AlphaMissense has only been compared to known pathogenic and benign variants. Therefore, the discriminatory power for variants of unknown significance (VUS) has yet to be determined. We have performed a comparison of these predictions with variants associated with inherited myeloid neoplasms: 1) to assess the accuracy of these models against VUS; 2) to enhance classification of unpublished VUS by leveraging published information about other variants; and 3) to map the predicted classification onto protein structures to examine spatial patterns. Methods: For 83 genes associated with inherited myeloid diseases, a systematic literature review for missense variants was performed using the Mastermind Genomic Intelligence Platform and ClinVar. We used Alphamissense to characterize VUS missense variants according to predicted pathogenicity scores as pathogenic, ambiguous, or benign. Known pathogenic (n=1594) and benign (n=501) variants served as controls to evaluate the accuracy of the system. AlphaFold2 structures were visualized for structure-function rendering of reclassified VUS and known pathogenic variants to compare and identify discernible patterns of spatial distribution. Results: This variant dataset comprised 1594 pathogenic, 501 benign, and 46676 VUS missense variants. Among VUS, AlphaMissense reclassified a majority of VUS missense mutations and established that the system was 88% accurate in predicting pathogenicity. A higher percentage of variants was classified as pathogenic among tumor suppressor genes e.g. DDX41 and RUNX1 (57.1% and 40.5%) compared to the oncogenes, GATA1 and GATA2 (25.7% and 34.9%). Furthermore, 3D models revealed a majority of variants reclassified to pathogenic were located in regions with defined tertiary structure clustered with known pathogenic variants, while benign variants were located at peripheral positions lacking definite structure. Conclusions: These results demonstrate the discriminatory power of AlphaMissense for VUS pathogenicity prediction for both loss-of-function and gain-of-function disease mechanisms. This work may also have implications for rare or challenging somatic cancer variants and variants in rare diseases. Finally, incorporating information available from empirical and clinical studies for disease-causing variants offers the possibility of significantly enhancing the predictive power of these models. Citation Format: Amina Kurtovic-Kozaric, Asja Campara, Melissa Jahibasic, Amar Mujkic, Adnan Fojnica, Mark J. Kiel. Assessment of AlphaMissense and structure-function predictions demonstrates efficient reclassification of genetic variants of unknown pathogenicity in inherited myeloid neoplasms [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2267.

Background PLA2G6 associated neurodegeneration (PLAN) comprises three diseases with overlapping features: infantile neuroaxonal dystrophy (INAD), atypical neuroaxonal dystrophy (atypical NAD), and PLA2G6 related dystonia parkinsonism. INAD is an early onset disease characterized by progressive loss of vision, muscular control, and mental skills. The prevalence of PLA2G6 associated diseases has not been previously calculated. Methods To provide the most accurate prevalence estimate, we utilized two independent approaches: database-based approach which included collecting variants from ClinVar, Human Gene Mutation Database (HGMD) and high confidence predicted loss-of-function (pLoF) from gnomAD (Rare Genomes Project Genetic Prevalence Estimator; GeniE), and literature based approach which gathered variants through Mastermind Genomic Search Engine (Genomenon, Inc). Genetic prevalence of PLAN was calculated based on allele frequencies from gnomAD, assuming Hardy Weinberg equilibrium. Results In the PLA2G6 gene, our analysis found 122 pathogenic, 82 VUS, and 15 variants with conflicting interpretations (pathogenic vs VUS) between two approaches. Allele frequency was available for 58 pathogenic, 42 VUS, and 15 conflicting variants in gnomAD database. If pathogenic and VUS variants are included, the overall genetic prevalence was estimated to be 1 in 220,322 pregnancies, with the highest genetic prevalence in African/African-American populations at 1 in 86,012 pregnancies. Similarly, the highest carrier frequencies observed were in African/African American and Asian populations. Conclusion Our estimates highlight the significant underdiagnosis of PLA2G6 associated neurodegeneration and underscores the need for increased awareness and diagnostic efforts. Furthermore, our study revealed a higher carrier frequency of PLA2G6 variants in African and Asian populations, stressing the importance of expanded genetic sequencing in non European populations to ensure accurate and comprehensive diagnosis. Future research should focus on confirming our findings and implementing expanded sequencing strategies to facilitate maximal and accurate diagnosis, particularly in non European populations.

Bosnia and Herzegovina is among ten countries in the world with the highest mortality rate due to COVID-19 infection. Lack of lockdown, open borders, high mortality rate, no herd immunity, no vaccination plan, and strong domestic anti-vaccination movement present serious COVID-19 concerns in Bosnia and Herzegovina. In such circumstances, we set out to study if the population is willing to receive the vaccine. A cross-sectional study was conducted among 10,471 adults in Bosnia and Herzegovina to assess the attitude of participants toward COVID-19 vaccination. Using a logistic regression model, we assessed the associations of sociodemographic characteristics with vaccine rejection, reasons for vaccine hesitancy, preferred vaccine manufacturer, and information sources. Surprisingly, only 25.7% of respondents indicated they would like to get a COVID-19 vaccine, while 74.3% of respondents were either hesitant or completely rejected vaccination. The vaccine acceptance increased with increasing age, education, and income level. Major motivation of pro-vaccination behaviour was intention to achieve collective immunity (30.1%), while the leading incentive for vaccine refusal was deficiency of clinical data (30.2%). The Pfizer-BioNTech vaccine is shown to be eightfold more preferred vaccine compared to the other manufacturers. For the first time, vaccine acceptance among health care professionals has been reported, where only 39.4% of healthcare professionals expressed willingness to get vaccinated. With the high share of the population unwilling to vaccinate, governmental impotence in securing the vaccines supplies, combined with the lack of any lockdown measures suggests that Bosnia and Herzegovina is unlikely to put COVID-19 pandemic under control in near future.