A review of genetic variant databases and machine learning tools for predicting the pathogenicity of breast cancer.

Studies continue to uncover contributing risk factors for breast cancer (BC) development including genetic variants. Advances in machine learning and big data generated from genetic sequencing can now be used for predicting BC pathogenicity. However, it is unclear which tool developed for pathogenicity prediction is most suited for predicting the impact and pathogenicity of variant effects. A significant challenge is to determine the most suitable data source for each tool since different tools can yield different prediction results with different data inputs. To this end, this work reviews genetic variant databases and tools used specifically for the prediction of BC pathogenicity. We provide a description of existing genetic variants databases and, where appropriate, the diseases for which they have been established. Through example, we illustrate how they can be used for prediction of BC pathogenicity and discuss their associated advantages and disadvantages. We conclude that the tools that are specialized by training on multiple diverse datasets from different databases for the same disease have enhanced accuracy and specificity and are thereby more helpful to the clinicians in predicting and diagnosing BC as early as possible.

Bi-allelic null variant in matrix metalloproteinase-15, causes congenital cardiac defect, cholestasis jaundice, and failure to thrive.

Here, we delineate the phenotype of two siblings with a bi-allelic frameshift variant in MMP15 gene with congenital cardiac defects, cholestasis, and dysmorphism. Genome sequencing analysis revealed a recently reported homozygous frameshift variant (c.1058delC, p.Pro353Glnfs*102) in MMP15 gene that co-segregates with the phenotype in the family in a recessive mode of inheritance. Relative quantification of MMP15 mRNA showed evidence of degradation of the mutated transcript, presumably by nonsense mediated decay. Likewise, MMP15: p.Gly231Arg, a concurrently reported homozygous missense variant in another patient exhibiting a similar phenotype, was predicted to disrupt zinc ion binding to the MMP-15 enzyme catalytic domain, which is essential for substrate proteolysis, by structural modeling. Previous animal models and cellular findings suggested that MMP15 plays a crucial role in the formation of endocardial cushions. These findings confirm that MMP15 is an important gene in human development, particularly cardiac, and that its loss of function is likely to cause a severe disorder phenotype.

The pharmacological chaperone N-n-butyl-deoxygalactonojirimycin enhances ß-galactosidase processing and activity in fibroblasts of a patient with infantile GM1-gangliosidosis.

GM1-gangliosidosis, a lysosomal storage disorder, is associated with ~ 161 missense variants in the GLB1 gene. Affected patients present with ß-galactosidase (ß-Gal) deficiency in lysosomes. Loss of function in ER-retained misfolded enzymes with missense variants is often due to subcellular mislocalization. Deoxygalactonojirimycin (DGJ) and its derivatives are pharmaceutical chaperones that directly bind to mutated ß-Gal in the ER promoting its folding and trafficking to lysosomes and thus enhancing its activity. An Emirati child has been diagnosed with infantile GM1-gangliosidosis carrying the reported p.D151Y variant. We show that p.D151Y ß-Gal in patient's fibroblasts retained < 1% residual activity due to impaired processing and trafficking. The amino acid substitution significantly affected the enzyme conformation; however, p.D151Y ß-Gal was amenable for partial rescue in the presence of glycerol or at reduced temperature where activity was enhanced with ~ 2.3 and 7 folds, respectively. The butyl (NB-DGJ) and nonyl (NN-DGJ) derivatives of DGJ chaperoning function were evaluated by measuring their IC50s and ability to stabilize the wild-type ß-Gal against thermal degradation. Although NN-DGJ showed higher affinity to ß-Gal, it did not show a significant enhancement in p.D151Y ß-Gal activity. However, NB-DGJ promoted p.D151Y ß-Gal maturation and enhanced its activity up to ~ 4.5% of control activity within 24 h which was significantly increased to ~ 10% within 6 days. NB-DGJ enhancement effect was sustained over 3 days after washing it out from culture media. We therefore conclude that NB-DGJ might be a promising therapeutic chemical chaperone in infantile GM1 amenable variants and therefore warrants further analysis for its clinical applications.

Biallelic loss of function variants in PPP1R21 cause a neurodevelopmental syndrome with impaired endocytic function.

Next-generation sequencing (NGS) has been instrumental in solving the genetic basis of rare inherited diseases, especially neurodevelopmental syndromes. However, functional workup is essential for precise phenotype definition and to understand the underlying disease mechanisms. Using whole exome (WES) and whole genome sequencing (WGS) in four independent families with hypotonia, neurodevelopmental delay, facial dysmorphism, loss of white matter, and thinning of the corpus callosum, we identified four previously unreported homozygous truncating PPP1R21 alleles: c.347delT p.(Ile116Lysfs*25), c.2170_2171insGGTA p.(Ile724Argfs*8), c.1607dupT p.(Leu536Phefs*7), c.2063delA p.(Lys688Serfs*26) and found that PPP1R21 was absent in fibroblasts of an affected individual, supporting the allele's loss of function effect. PPP1R21 function had not been studied except that a large scale affinity proteomics approach suggested an interaction with PIBF1 defective in Joubert syndrome. Our co-immunoprecipitation studies did not confirm this but in contrast defined the localization of PPP1R21 to the early endosome. Consistent with the subcellular expression pattern and the clinical phenotype exhibiting features of storage diseases, we found patient fibroblasts exhibited a delay in clearance of transferrin-488 while uptake was normal. In summary, we delineate a novel neurodevelopmental syndrome caused by biallelic PPP1R21 loss of function variants, and suggest a role of PPP1R21 within the endosomal sorting process or endosome maturation pathway.

Novel founder intronic variant in SLC39A14 in two families causing Manganism and potential treatment strategies.

Congenital disorders of manganese metabolism are rare occurrences in children, and medical management of these disorders is complex and challenging. Homozygous exonic mutations in the manganese transporter SLC39A14 have recently been associated with a pediatric-onset neurodegenerative disorder characterized by brain manganese accumulation and clinical signs of manganese neurotoxicity, including parkinsonism-dystonia. We performed whole exome sequencing on DNA samples from two unrelated female children from the United Arab Emirates with progressive movement disorder and brain mineralization, identified a novel homozygous intronic mutation in SLC39A14 in both children, and demonstrated that the mutation leads to aberrant splicing. Both children had consistently elevated serum manganese levels and were diagnosed with SLC39A14-associated manganism. Over a four-year period, we utilized a multidisciplinary management approach for Patient 1 combining decreased manganese dietary intake and chelation with symptomatic management of dystonia. Our treatment strategy appeared to slow disease progression, but did not lead to a cure or reversal of already established deficits. Clinicians should consider testing for noncoding mutations in the diagnosis of congenital disorders of manganese metabolism and utilizing multidisciplinary approaches in the management of these disorders.

Clinical and molecular spectrum of thymidine kinase 2-related mtDNA maintenance defect.

Mitochondrial DNA maintenance (mtDNA) defects have a wide range of causes, each with a set of phenotypes that overlap with many other neurological or muscular diseases. Clinicians face the challenge of narrowing down a long list of differential diagnosis when encountered with non-specific neuromuscular symptoms. Biallelic pathogenic variants in the Thymidine Kinase 2 (TK2) gene cause a myopathic form of mitochondrial DNA maintenance defect. Since the first description in 2001, there have been 71 patients reported with 42 unique pathogenic variants. Here we are reporting 11 new cases with 5 novel pathogenic variants. We describe and analyze a total of 82 cases with 47 unique TK2 pathogenic variants in effort to formulate a comprehensive molecular and clinical spectrum of TK2-related mtDNA maintenance disorders.

Homozygous variants in pyrroline-5-carboxylate reductase 2 (PYCR2) in patients with progressive microcephaly and hypomyelinating leukodystrophy.

Pyrroline-5-carboxylate reductase 2, encoded by PYCR2, is one of the three homologous enzymes that catalyze the last step of proline synthesis. Homozygous variants in PYCR2 have been reported in patients from multiple consanguineous families with hypomyelinating leukodystrophy 10 (HLD10) (MIM: 616420). Here, we report five additional patients from three families with homozygous nonsense or missense variants in PYCR2, identified through clinical exome sequencing. All patients presented with postnatally acquired microcephaly, moderate to profound global developmental delay, and failure to thrive. Brain MRI in these patients showed thin corpus callosum, delayed myelination, and generalized white-matter volume loss. Additional phenotypes that were less consistent among patients included seizures or seizure-like movements, spasticity and ataxic gait, recurrent vomiting, cortical blindness, dysmorphic features, joint contractures, and irritability. Exome sequencing identified homozygous variants in PYCR2 in the proband from each family: c.28C>T (p.(Glu10Ter)), c.796C>T (p.(Arg266Ter)), and c.577G>A (p.(Val193Met)). Subsequent targeted analyses demonstrated co-segregation of the disease with the variant in the family. Despite the metabolic role of PYCR2, routine serum metabolic test in these patients were normal. To further understand the disease etiology and functions of PYCR2, small molecule metabolomics profiling was performed in plasma from three severely affected patients. No significant changes were identified in proline biosynthesis pathway or related metabolites. Studying the clinical features and the metabolic profiles of the PYCR2-deficient patients provides a more comprehensive picture for this newly identified disorder and facilitates further research on the gene function and disease etiology. © 2016 Wiley Periodicals, Inc.

Clinical, morphological, biochemical, imaging and outcome parameters in 21 individuals with mitochondrial maintenance defect related to FBXL4 mutations.

FBXL4 deficiency is a recently described disorder of mitochondrial maintenance associated with a loss of mitochondrial DNA in cells. To date, the genetic diagnosis of FBXL4 deficiency has been established in 28 individuals. This paper retrospectively reviews proxy-reported clinical and biochemical findings and evaluates brain imaging, morphological and genetic data in 21 of those patients. Neonatal/early-onset severe lactic acidosis, muscular hypotonia, feeding problems and failure to thrive is the characteristic pattern at first presentation. Facial dysmorphic features are present in 67% of cases. Seven children died (mean age 37 months); 11 children were alive (mean age at follow-up 46 months), three children were lost to follow-up. All survivors developed severe psychomotor retardation. Brain imaging was non-specific in neonates but a later-onset, rapidly progressive brain atrophy was noted. Elevated blood lactate and metabolic acidosis were observed in all individuals; creatine kinase was elevated in 45% of measurements. Diagnostic workup in patient tissues and cells revealed a severe combined respiratory chain defect with a general decrease of enzymes associated with mitochondrial energy metabolism and a relative depletion of mitochondrial DNA content. Mutations were detected throughout the FBXL4 gene albeit with no clear delineation of a genotype-phenotype correlation. Treatment with "mitochondrial medications" did not prove effective. In conclusion, a clinical pattern of early-onset encephalopathy, persistent lactic acidosis, profound muscular hypotonia and typical facial dysmorphism should prompt initiation of molecular genetic analysis of FBXL4. Establishment of the diagnosis permits genetic counselling, prevents patients undergoing unhelpful diagnostic procedures and allows for accurate prognosis.

Diagnosis and treatment of late-onset Pompe disease in the Middle East and North Africa region: consensus recommendations from an expert group.

BACKGROUND: Pompe disease is a rare autosomal recessive disorder caused by a deficiency of the lysosomal enzyme alpha-glucosidase responsible for degrading glycogen. Late-onset Pompe disease has a complex multisystem phenotype characterized by a range of symptoms. METHODS: An expert panel from the Middle East and North Africa (MENA) region met to create consensus-based guidelines for the diagnosis and treatment of late-onset Pompe disease for the MENA region, where the relative prevalence of Pompe disease is thought to be high but there is a lack of awareness and diagnostic facilities. RESULTS: These guidelines set out practical recommendations and include algorithms for the diagnosis and treatment of late-onset Pompe disease. They detail the ideal diagnostic workup, indicate the patients in whom enzyme replacement therapy should be initiated, and provide guidance on appropriate patient monitoring. CONCLUSIONS: These guidelines will serve to increase awareness of the condition, optimize patient diagnosis and treatment, reduce disease burden, and improve patient outcomes.

Transaldolase deficiency caused by the homozygous p.R192C mutation of the TALDO1 gene in four Emirati patients with considerable phenotypic variability.

UNLABELLED: Transaldolase deficiency is a heterogeneous disorder of carbohydrate metabolism characterized clinically by dysmorphic features, cutis laxa, hepatosplenomegaly, hepatic fibrosis, pancytopenia, renal and cardiac abnormalities, and urinary excretion of polyols. This report describes four Emirati patients with transaldolase deficiency caused by the homozygous p.R192C missense mutation in TALDO1 displaying wide phenotypic variability. The patients had variable clinical presentations including hepatosplenomegaly, pancytopenia, liver failure, proteinuria, hydrops fetalis, cardiomyopathy, and skin manifestations (e.g., dryness, cutis laxa, ichthyosis, telangiectasias, and hemangiomas). Biochemical analyses including urinary concentration of polyols were consistent with transaldolase deficiency. The mutation p.R192C was previously identified in an Arab patient, suggesting a founder effect in Arab populations. CONCLUSION: The above findings support the premise that biallelic mutations in TALDO1 are responsible for transaldolase deficiency and confirm the broad phenotypic variability of this condition, even with the same genotype.

Diagnostic exome sequencing to elucidate the genetic basis of likely recessive disorders in consanguineous families.

Rare, atypical, and undiagnosed autosomal-recessive disorders frequently occur in the offspring of consanguineous couples. Current routine diagnostic genetic tests fail to establish a diagnosis in many cases. We employed exome sequencing to identify the underlying molecular defects in patients with unresolved but putatively autosomal-recessive disorders in consanguineous families and postulated that the pathogenic variants would reside within homozygous regions. Fifty consanguineous families participated in the study, with a wide spectrum of clinical phenotypes suggestive of autosomal-recessive inheritance, but with no definitive molecular diagnosis. DNA samples from the patient(s), unaffected sibling(s), and the parents were genotyped with a 720K SNP array. Exome sequencing and array CGH (comparative genomic hybridization) were then performed on one affected individual per family. High-confidence pathogenic variants were found in homozygosity in known disease-causing genes in 18 families (36%) (one by array CGH and 17 by exome sequencing), accounting for the clinical phenotype in whole or in part. In the remainder of the families, no causative variant in a known pathogenic gene was identified. Our study shows that exome sequencing, in addition to being a powerful diagnostic tool, promises to rapidly expand our knowledge of rare genetic Mendelian disorders and can be used to establish more detailed causative links between mutant genotypes and clinical phenotypes.

Exploring the efficacy and safety of Ambroxol in Gaucher disease: an overview of clinical studies.

Gaucher disease (GD) is mainly caused by glucocerebrosidase (GCase) enzyme deficiency due to genetic variations in the GBA1 gene leading to the toxic accumulation of sphingolipids in various organs, which causes symptoms such as anemia, thrombocytopenia, hepatosplenomegaly, and neurological manifestations. GD is clinically classified into the non-neuronopathic type 1, and the acute and chronic neuronopathic forms, types 2 and 3, respectively. In addition to the current approved GD medications, the repurposing of Ambroxol (ABX) has emerged as a prospective enzyme enhancement therapy option showing its potential to enhance mutated GCase activity and reduce glucosylceramide accumulation in GD-affected tissues of different GBA1 genotypes. The variability in response to ABX varies across different variants, highlighting the diversity in patients' therapeutic outcomes. Its oral availability and safety profile make it an attractive option, particularly for patients with neurological manifestations. Clinical trials are essential to explore further ABX's potential as a therapeutic medication for GD to encourage pharmaceutical companies' investment in its development. This review highlights the potential of ABX as a pharmacological chaperone therapy for GD and stresses the importance of addressing response variability in clinical studies to improve the management of this rare and complex disorder.

A founder mutation in CA5A causing intrafamilial and interfamilial phenotypic variability in a cohort of 18 patients with carbonic anhydrase VA deficiency.

Carbonic anhydrase VA (CA-VA) deficiency is a rare cause of hyperammonemia caused by biallelic mutations in CA5A. Most patients present with hyperammonemic encephalopathy in early infancy to early childhood, and patients usually have no further recurrence of hyperammonemia with a favorable outcome. This retrospective cohort study reports 18 patients with CA-VA deficiency caused by homozygosity for a founder mutation, c.59G>A p.(Trp20*) in CA5A. The reported patients show significant intrafamilial and interfamilial variability, and display atypical clinical features. Two adult patients were asymptomatic, 7/18 patients had recurrent hyperammonemia, 7/18 patients developed variable degree of developmental delay, 9/11 patients had hyperCKemia, and 7/18 patients had failure to thrive. Microcephaly was seen in three patients and one patient developed a metabolic stroke. The same variant had been reported already in a single South Asian patient presenting with neonatal hyperammonemic encephalopathy and subsequent development of seizures and developmental delay. This report highlights the limitations of current understanding of the pathomechanisms involved in this disorder, and calls for further evaluation of the possible role of genetic modifiers in this condition.

Spectrum of genetic variants in bilateral sensorineural hearing loss.

Background: Hearing loss (HL) is an impairment of auditory function with identified genetic forms that can be syndromic (30%) or non-syndromic (70%). HL is genetically heterogeneous, with more than 1,000 variants across 150 causative genes identified to date. The genetic diagnostic rate varies significantly depending on the population being tested. Countries with a considerably high rate of consanguinity provide a unique resource for studying rare forms of recessive HL. In this study, we identified genetic variants associated with bilateral sensorineural HL (SNHL) using whole-exome sequencing (WES) in 11 families residing in the United Arab Emirates (UAE). Results: We established the molecular diagnosis in six probands, with six different pathogenic or likely pathogenic variants in the genes MYO15A, SLC26A4, and GJB2. One novel nonsense variant, MYO15A:p.Tyr1962Ter*, was identified in a homozygous state in one family, which has not been reported in any public database. SLC26A4 and GJB2 were found to be the most frequently associated genes in this study. In addition, six variants of uncertain significance (VUS) were detected in five probands in the genes CDH23, COL11A1, ADGRV1, NLRP3, and GDF6. In total, 12 variants were observed in eight genes. Among these variants, eight missense variants (66.7%), three nonsense variants (25.0%), and one frameshift (8.3%) were identified. The overall diagnostic rate of this study was 54.5%. Approximately 45.5% of the patients in this study came from consanguineous families. Conclusion: Understanding the genetic basis of HL provides insight for the clinical diagnosis of hearing impairment cases through the utilization of next-generation sequencing (NGS). Our findings contribute to the knowledge of the heterogeneous genetic profile of HL, especially in a population with a high rate of consanguineous marriage in the Arab population.

Novel compound heterozygous variants (c.971delA/c.542C > T) in SLC1A4 causes spastic tetraplegia, thin corpus callosum, and progressive microcephaly: a case report and mutational analysis.

Spastic tetraplegia, thin corpus callosum, and progressive microcephaly (SPATCCM) are linked to SLC1A4 genetic variants since the first reported case in 2015. SLC1A4 encodes for the neutral amino acid transporter ASCT1 which is involved in the transportation of serine between astrocytes and neurons. Although most of the reported cases are of Ashkenazi Jewish ancestry, SPATCCM has also been reported in Irish, Italian, Czech, Palestinian, and Pakistani ethnicities. Herein, we report two Pakistani male siblings from a non-consanguineous marriage presented with global developmental delay associated with spastic quadriplegia, microcephaly, and infantile spasm. Since infancy, both siblings suffered from microcephaly with brain MRI demonstrating generalized atrophy of the frontal, temporal, and parietal lobes with a prominence of the subarachnoid spaces, widening of the Sylvian fissures, and enlargement of the ventricular system not compatible with the chronological age of both patients associated with thinning of the corpus callosum. Whole-exome sequencing of both affected brothers revealed novel compound heterozygous variants in the SLC1A4 gene (NM_003038) segregating from their parents. The maternal c.971delA (p.N324Tfs*29) deletion variant disturbs the transcript reading frame leading to the generation of a premature stop codon and its subsequent degradation by nonsense-mediated mRNA decay as detected through expression analysis. The paternal c.542C > T (p.S181F) missense variant was predicted deleterious via multiple in silico prediction tools as the amino acid substitution is speculated to affect the overall ASCT1 structural confirmation due to the loss of an H-bond at the core of the protein at this position which might affect its function as concluded from the simulation analysis. The presented cases expand the genetic and clinical spectrum of ASCT1 deficiency and support the importance of including SLC1A4 gene screening in infants with unexplained global neurodevelopmental delay regardless of ethnicity.

Case report: Birk-Landau-Perez syndrome linked to the SLC30A9 gene-identification of additional cases and expansion of the phenotypic spectrum.

Birk-Landau-Perez syndrome (BILAPES) is an autosomal recessive cerebro-renal syndrome associated with genetic defects in the SLC30A9 gene, initially reported in 2017 in six individuals belonging to a large Bedouin kindred. The SLC30A9 gene encodes a putative mitochondrial zinc transporter with ubiquitous expression, the highest found in the brain, kidney, and skeletal muscle. Since the first report, only one additional affected patient has been described, but there were some inconsistencies, such as hearing loss, failure to thrive, and neuroimaging findings between the clinical presentation of the disease in the Bedouin family and the second patient. Here, we present two more patients from a consanguineous Middle Eastern family with features of chronic kidney disease, neurodevelopmental regression, ataxia, hearing loss, and eye abnormalities, which were largely consistent with BILAPES. Whole-exome sequencing detected a homozygous in-frame deletion c.1049_1051delCAG (p.Ala350del) in the SLC30A9 gene, which was the same variant detected in the patients from the primary literature report and the variant segregated with disease in the family. However, in the patients described here, brain MRI showed cerebellar atrophy, which was not a cardinal feature of the syndrome from the primary report. Our findings provide further evidence for SLC30A9-associated BILAPES and contribute to defining the clinical spectrum.

Interaction of Glutathione with MMACHC Arginine-Rich Pocket Variants Associated with Cobalamin C Disease: Insights from Molecular Modeling.

Methylmalonic aciduria and homocystinuria type C protein (MMACHC) is required by the body to metabolize cobalamin (Cbl). Due to its complex structure and cofactor forms, Cbl passes through an extensive series of absorptive and processing steps before being delivered to mitochondrial methyl malonyl-CoA mutase and cytosolic methionine synthase. Depending on the cofactor attached, MMACHC performs either flavin-dependent reductive decyanation or glutathione (GSH)-dependent dealkylation. The alkyl groups of Cbl have to be removed in the presence of GSH to produce intermediates that can later be converted into active cofactor forms. Pathogenic mutations in the GSH binding site, such as R161Q, R161G, R206P, R206W, and R206Q, have been reported to cause Cbl diseases. The impact of these variations on MMACHC's structure and how it affects GSH and Cbl binding at the molecular level is poorly understood. To better understand the molecular basis of this interaction, mutant structures involving the MMACHC-MeCbl-GSH complex were generated using in silico site-directed point mutations and explored using molecular dynamics (MD) simulations. The results revealed that mutations in the key arginine residues disrupt GSH binding by breaking the interactions and reducing the free energy of binding of GSH. Specifically, variations at position 206 appeared to produce weaker GSH binding. The lowered binding affinity for GSH in the variant structures could impact metabolic pathways involving Cbl and its trafficking.

Expanding the clinical spectrum of cytosolic phosphoenolpyruvate carboxykinase deficiency: novel PCK1 variants in four Arabian Gulf families.

BACKGROUND: In metabolic stress, the cytosolic phosphoenolpyruvate carboxykinase (PEPCK-C) enzyme is involved in energy production through the gluconeogenesis pathway. PEPCK-C deficiency is a rare childhood-onset autosomal recessive metabolic disease caused by PCK1 genetic defects. Previous studies showed a broad clinical spectrum ranging from asymptomatic to recurrent hypoglycemia with/without lactic acidosis, encephalopathy, seizures, and liver failure. RESULTS: In this article, we discuss the occurrence of PEPCK-C deficiency in four families from the United Arab Emirates and Oman. All patients presented with unexplained hypoglycemia as a common feature. Two out of the seven patients presented with episodes of encephalopathy that resulted in seizures and neuroregression leading to global developmental delay and one patient had a neonatal presentation. Observed biochemical abnormalities include elevated lactate, transaminases, and tricarboxylic acid cycle metabolites in most patients. Elevated creatine kinase was documented in two patients. Whole exome sequencing revealed two novel (c.574T > C, and c.1268 C > T) and a previously reported splice site (c.961 + 1G > A) PCK1 variant in the affected families. CONCLUSION: Patients become vulnerable during intercurrent illness; thus, prevention and prompt reversal of a catabolic state are crucial to avoid irreversible brain damage. This report will help to expand the clinical understanding of this rare disease and recommends screening for PEPCK-C deficiency in unexplained hypoglycemia.

A review of SARS-CoV-2 drug repurposing: databases and machine learning models.

The emergence of Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2) posed a serious worldwide threat and emphasized the urgency to find efficient solutions to combat the spread of the virus. Drug repurposing has attracted more attention than traditional approaches due to its potential for a time- and cost-effective discovery of new applications for the existing FDA-approved drugs. Given the reported success of machine learning (ML) in virtual drug screening, it is warranted as a promising approach to identify potential SARS-CoV-2 inhibitors. The implementation of ML in drug repurposing requires the presence of reliable digital databases for the extraction of the data of interest. Numerous databases archive research data from studies so that it can be used for different purposes. This article reviews two aspects: the frequently used databases in ML-based drug repurposing studies for SARS-CoV-2, and the recent ML models that have been developed for the prospective prediction of potential inhibitors against the new virus. Both types of ML models, Deep Learning models and conventional ML models, are reviewed in terms of introduction, methodology, and its recent applications in the prospective predictions of SARS-CoV-2 inhibitors. Furthermore, the features and limitations of the databases are provided to guide researchers in choosing suitable databases according to their research interests.

Artificial intelligence and database for NGS-based diagnosis in rare disease.

Rare diseases (RDs) are rare complex genetic diseases affecting a conservative estimate of 300 million people worldwide. Recent Next-Generation Sequencing (NGS) studies are unraveling the underlying genetic heterogeneity of this group of diseases. NGS-based methods used in RDs studies have improved the diagnosis and management of RDs. Concomitantly, a suite of bioinformatics tools has been developed to sort through big data generated by NGS to understand RDs better. However, there are concerns regarding the lack of consistency among different methods, primarily linked to factors such as the lack of uniformity in input and output formats, the absence of a standardized measure for predictive accuracy, and the regularity of updates to the annotation database. Today, artificial intelligence (AI), particularly deep learning, is widely used in a variety of biological contexts, changing the healthcare system. AI has demonstrated promising capabilities in boosting variant calling precision, refining variant prediction, and enhancing the user-friendliness of electronic health record (EHR) systems in NGS-based diagnostics. This paper reviews the state of the art of AI in NGS-based genetics, and its future directions and challenges. It also compare several rare disease databases.