Prediction of Parkinson's disease pathogenic variants using hybrid Machine learning systems and radiomic features.

PURPOSE: In Parkinson's disease (PD), 5-10% of cases are of genetic origin with mutations identified in several genes such as leucine-rich repeat kinase 2 (LRRK2) and glucocerebrosidase (GBA). We aim to predict these two gene mutations using hybrid machine learning systems (HMLS), via imaging and non-imaging data, with the long-term goal to predict conversion to active disease. METHODS: We studied 264 and 129 patients with known LRRK2 and GBA mutations status from PPMI database. Each dataset includes 513 features such as clinical features (CFs), conventional imaging features (CIFs) and radiomic features (RFs) extracted from DAT-SPECT images. Features, normalized by Z-score, were univariately analyzed for statistical significance by the t-test and chi-square test, adjusted by Benjamini-Hochberg correction. Multiple HMLSs, including 11 features extraction (FEA) or 10 features selection algorithms (FSA) linked with 21 classifiers were utilized. We also employed Ensemble Voting (EV) to classify the genes. RESULTS: For prediction of LRRK2 mutation status, a number of HMLSs resulted in accuracies of 0.98 ± 0.02 and 1.00 in 5-fold cross-validation (80% out of total data points) and external testing (remaining 20%), respectively. For predicting GBA mutation status, multiple HMLSs resulted in high accuracies of 0.90 ± 0.08 and 0.96 in 5-fold cross-validation and external testing, respectively. We additionally showed that SPECT-based RFs added value to the specific prediction of of GBA mutation status. CONCLUSION: We demonstrated that combining medical information with SPECT-based imaging features, and optimal utilization of HMLS can produce excellent prediction of the mutations status in PD patients.

A Novel ARMC5 Germline Variant in Primary Macronodular Adrenal Hyperplasia Using Whole-Exome Sequencing.

Background: Primary macronodular adrenocortical hyperplasia (PMAH) is a rare form of adrenal Cushing's syndrome with incomplete penetrance which may be sporadic or autosomal dominant. The inactivation of the ARMC5 gene, a potential tumor suppressor gene, is one of the associated causes of PMAH. This study aimed to identify the variant responsible for Iranian familial PMAH. Methods: The proband, a 44-year-old woman, was directed to whole-exome sequencing (WES) of the blood sample to discover a germline variant. In addition, the identified causative variant was confirmed and segregated in other and available unaffected family members. Results: The novel germline heterozygous missense variant, c.2105C>A in the ARMC5 gene, was found, and the same germline variant as the proband was confirmed in two affected sisters. This variant was detected in the brother of the proband with an asymptomatic condition and this considered because of incomplete penetrance and age-dependent appearance. The function of the ARMC5 protein would be damaged by the identified variant, according to in silico and computer analyses that followed. Conclusion: The new germline ARMC5 variation (c.2105C>A, (p. Ala702Glu)) was interpreted as a likely pathogenic variant based on ACMG and Sherloc standards. PMAH may be diagnosed early using genetic testing that shows inherited autosomal dominant mutations in the ARMC5 gene.

Extracellular matrix protein 1 gene (ECM1) mutations in nine Iranian families with lipoid proteinosis.

BACKGROUND & OBJECTIVES: Lipoid proteinosis (LP) is an autosomal recessive disease. Clinical characteristics of this disease are hoarse voice, scarring of the skin, brain calcifications, and eyelid papules (moniliform blepharosis). Mutations in the ECM1 gene on 1q21.2 are responsible for this disease. This study was conducted to investigate the mutation spectrum of ECM1 gene in nine Iranian families having at least one LP patient diagnosed clinically. METHODS: The entire ECM1 gene was screened using PCR and direct sequencing in nine Iranian families with 12 suspected LP patients who were referred to the clinic, along with their parents and siblings. Thirty healthy individuals were included as controls. RESULTS: In only one patient a homozygous G>A transition at nucleotide c.806 in exon 7 was detected. A G>A substitution at nucleotide 1243 in exon 8 that changes glycine (GGT) to serine (AGT) was observed in most of our patients. Furthermore, in one patient there was a change in the sequence of intron 8, the A>T transition in nucleotide 4307. In addition, in two cases (one patient and one healthy mother with affected child) there was a C (4249) deletion in intron 8. INTERPRETATION & CONCLUSIONS: Our results indicate that although mutation in ECM1gene is responsible for lipoid proteinosis, it is likely that this is not the only gene causing this disease and probably other genes may be involved in the pathogenesis of the LP disease.

MDR1 gene polymorphisms: possible association with its expression and clinicopathology characteristics in colorectal cancer patients.

AIM: Over-expression of some genes, such as MDR1, can increase the level of chemotherapy drug afflux and limit the effectiveness of treatment. We aimed to investigate the effect of MDR1 polymorphisms on its expression level and related characteristics in Iranian colorectal cancer patients. METHODS: Tumor, normal mucosal tissue and blood samples from CRC patients and blood samples from healthy controls (n=60) were obtained for genotyping and measuring the expression level of MDR1. RESULTS: The expression of the MDR1 gene showed a significant increase in cancerous regions compared to adjacent normal tissue. Furthermore, the GG2677 genotype was correlated with highest while the AT 2677 genotype was associated with the lowest levels of expression. In addition only the G2677T/A polymorphism showed association with histological grade of colorectal tumors. CONCLUSION: Our study once more emphasizes effects of MDR1 SNPs which may indirectly impact on response to drugs.