RESUMEN
Genomics is advancing towards data-driven science. Through the advent of high-throughput data generating technologies in human genomics, we are overwhelmed with the heap of genomic data. To extract knowledge and pattern out of this genomic data, artificial intelligence especially deep learning methods has been instrumental. In the current review, we address development and application of deep learning methods/models in different subarea of human genomics. We assessed over- and under-charted area of genomics by deep learning techniques. Deep learning algorithms underlying the genomic tools have been discussed briefly in later part of this review. Finally, we discussed briefly about the late application of deep learning tools in genomic. Conclusively, this review is timely for biotechnology or genomic scientists in order to guide them why, when and how to use deep learning methods to analyse human genomic data.
Asunto(s)
Aprendizaje Profundo , Inteligencia Artificial , Genoma Humano/genética , Genómica/métodos , Secuenciación de Nucleótidos de Alto Rendimiento , HumanosRESUMEN
Protein phosphorylation is a post-translational modification that enables various cellular activities and plays essential roles in protein interactions. Phosphorylation is an important process for the replication of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). To shed more light on the effects of phosphorylation, we used an ensemble of neural networks to predict potential kinases that might phosphorylate SARS-CoV-2 nonstructural proteins (nsps) and molecular dynamics (MD) simulations to investigate the effects of phosphorylation on nsps structure, which could be a potential inhibitory target to attenuate viral replication. Eight target candidate sites were found as top-ranked phosphorylation sites of SARS-CoV-2. During the process of molecular dynamics (MD) simulation, the root-mean-square deviation (RMSD) analysis was used to measure conformational changes in each nsps. Root-mean-square fluctuation (RMSF) was employed to measure the fluctuation in each residue of 36 systems considered, allowing us to evaluate the most flexible regions. These analysis shows that there are significant structural deviations in the residues namely nsp1 THR 72, nsp2 THR 73, nsp3 SER 64, nsp4 SER 81, nsp4 SER 455, nsp5 SER284, nsp6 THR 238, and nsp16 SER 132. The identified list of residues suggests how phosphorylation affects SARS-CoV-2 nsps function and stability. This research also suggests that kinase inhibitors could be a possible component for evaluating drug binding studies, which are crucial in therapeutic discovery research.
Asunto(s)
COVID-19 , SARS-CoV-2 , Humanos , Simulación de Dinámica Molecular , Proteínas no Estructurales Virales/metabolismo , Fosforilación , Replicación ViralRESUMEN
PURPOSE: Medical artificial intelligence (MAI) is artificial intelligence (AI) applied to the healthcare field. AI can be applied to many different aspects of genetics, such as variant classification. With little or no prior experience in AI coding, we share our experience with variant classification using the Variant Artificial Intelligence Easy Scoring (VARIES), an open-access platform, and the Automatic Machine Learning (AutoML) of the Google Cloud Platform. METHODS: We investigated exome sequencing data from a sample of 1410 individuals. The majority (80%) were used for training and 20% for testing. The user-friendly Google Cloud Platform was used to create the VARIES model, and the TRIPOD checklist to develop and validate the prediction model for the development of the VARIES system. RESULTS: The learning rate of the training dataset reached optimal results at an early stage of iteration, with a loss value near zero in approximately 4 min. For the testing dataset, the results for F1 (micro average) was 0.64, F1 (macro average) 0.34, micro-average area under the curve AUC (one-over-rest) 0.81 and the macro-average AUC (one-over-rest) 0.73. The overall performance characteristics of the VARIES model suggest the classifier has a high predictive ability. CONCLUSION: We present a systematic guideline to create a genomic AI prediction tool with high predictive power, using a graphical user interface provided by Google Cloud Platform, with no prior experience in creating the software programs required.
Asunto(s)
Inteligencia Artificial , Aprendizaje Automático , Humanos , Programas InformáticosRESUMEN
The colony stimulating factor 2 receptor subunit beta (CSF2RB) is the common signaling subunit of the cytokine receptors for IL-3, IL-5, and GM-CSF. Several studies have shown that spontaneous and random mutants of CSF2RB can lead to ligand independence in vitro. To date, no report(s) have been shown for the presence of potentially transforming and oncogenic CSF2RB mutation(s) clinically in cancer patients until the first reported case of a leukemia patient in 2016 harboring a germline-activating mutation (R461C). We combined exome sequencing, pathway analyses, and functional assays to identify novel somatic mutations in KAIMRC1 cells and breast tumor specimen. The patient's peripheral blood mononuclear cell (PBMC) exome served as a germline control in the identification of somatic mutations. Here, we report the discovery of a novel potentially transforming and oncogenic somatic mutation (S230I) in the CSF2RB gene of a breast cancer patient and the cell line, KAIMRC1 established from her breast tumor tissue. KAIMRC1 cells are immortalized and shown to survive and proliferate in ligand starvation condition. Immunoblot analysis showed that mutant CSF2RB signals through JAK2/STAT and PI3K/mTOR pathways in ligand starvation conditions. Screening a small molecule kinase inhibitor library revealed potent JAK2 inhibitors against KAIMRC1 cells. We, for the first time, identified a somatic, potentially transforming, and oncogenic CSF2RB mutation (S230I) in breast cancer patients that seem to be an actionable mutation leading to the development of new therapeutics for breast cancer.
Asunto(s)
Neoplasias de la Mama/genética , Subunidad beta Común de los Receptores de Citocinas/metabolismo , Línea Celular Tumoral , Proliferación Celular , Femenino , Mutación de Línea Germinal , HumanosRESUMEN
BACKGROUND: The triple assortment influenza A(H1N1) virus emerged in spring 2009 and disseminated worldwide, including Saudi Arabia. This study was carried out to characterize Saudi influenza isolates in relation to the global strains and to evaluate the potential role of mutated residues in transmission, adaptation, and the pathogenicity of the virus. METHODS: Nasopharyngeal samples (n = 6492) collected between September 2009 to March 2011 from patients with influenza-like illness were screened by PCR for influenza A(H1N1). Phylogenetic and Molecular evolutionary analysis were carried out to place the Saudi strains in relation to the global strains followed by Mutation analysis of surface and internal proteins. RESULTS: Concatenated whole-genome phylogenetic analysis along with hemagglutinin (HA) signature changes, that is, Aspartic Acid (D) at position 187, P83S, S203T, and R223Q confirmed that the Saudi strains belong to the antigenic category of A/California/07/2009. However, phylogenetic analysis revealed unusual strains of A(H1N1) circulating in Saudi Arabia, not belonging to any of known clades, appearing in five distinct groups well supported by group-specific mutations and novel mutation complexes. These cases had characteristic inter- and intragroup substitution patterns while few of their closest matches showed up as sporadic cases the world over. Specific mutation patterns were detected within the functional domains of internal proteins PB2, PB1, PA, NP, NS1, and M2 having a putative role in viral fitness and virulence. Bayesian coalescent MCMC analysis revealed that Saudi strains belonged to cluster 2 of A(H1N1)pdm09 and spread a month later as compared to other strains of this cluster. CONCLUSION: Influenza outbreak in Saudi Arabia during 2009-2011 was caused by atypical strains of influenza A(H1N1)pdm09, probably introduced in this community on multiple occasions. To understand the antigenic significance of these novel point mutations and mutation complexes require functional studies, which will be crucial for risk assessment of emergent strains and defining infection control measures.
Asunto(s)
Brotes de Enfermedades , Evolución Molecular , Subtipo H1N1 del Virus de la Influenza A/genética , Gripe Humana/epidemiología , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Teorema de Bayes , Niño , Preescolar , Femenino , Variación Genética , Genotipo , Humanos , Lactante , Subtipo H1N1 del Virus de la Influenza A/aislamiento & purificación , Gripe Humana/virología , Masculino , Persona de Mediana Edad , Nasofaringe/virología , Filogenia , Mutación Puntual , ARN Viral/genética , Arabia Saudita/epidemiología , Adulto JovenRESUMEN
BACKGROUND: Biotin-thiamine-responsive basal ganglia disease (BTBGD) is an autosomal recessive neurometabolic disorder mostly presented in children. The disorder is described as having subacute encephalopathy with confusion, dystonia, and dysarthria triggered by febrile illness that leads to neuroregression and death if untreated. Using biotin and thiamine at an early stage of the disease can lead to significant improvement. METHODS: BTBGD is a treatable disease if diagnosed at an early age and has been frequently reported in Saudi population. Keeping this in mind, the current study screened 3000 Saudi newborns for the SLC19A3 gene mutations using target sequencing, aiming to determine the carrier frequency in Saudi Population and whether BTBGD is a good candidate to be included in the newborn-screened disorders. RESULTS: Using targeted gene sequencing, DNA from 3000 newborns Saudi was screened for the SLC19A3 gene mutations using standard methods. Screening of the SLC19A3 gene revealed a previously reported heterozygous missense mutation (c.1264A>G (p.Thr422Ala) in six unrelated newborns. No probands having homozygous pathogenic mutations were found in the studied cohort. The variant has been frequently reported previously in homozygous state in Saudi population, making it a hot spot mutation. The current study showed that the carrier frequency of SLC19A3 gene mutation is 1 of 500 in Saudi newborns. CONCLUSION: For the first time in the literature, we determined the carrier frequency of SLC19A3 gene mutation in Saudi population. The estimated prevalence is too rare in Saudi population (at least one in million); therefore, the data are not in favor of including such very rare disorders in newborn screening program at population level. However, a larger cohort is needed for a more accurate estimate.
Asunto(s)
Enfermedades de los Ganglios Basales/diagnóstico , Enfermedades de los Ganglios Basales/epidemiología , Pruebas Genéticas , Proteínas de Transporte de Membrana/genética , Tamizaje Neonatal , Enfermedades de los Ganglios Basales/genética , Estudios de Cohortes , Femenino , Heterocigoto , Humanos , Recién Nacido , Masculino , Proyectos Piloto , Arabia Saudita/epidemiología , Análisis de Secuencia de ADNRESUMEN
AIMS: To investigate the extent of CCR5 polymorphism in the healthy Saudi population. METHOD: A total of 321 healthy Saudi individuals were sequenced using the ion Ampliseq™ Exome kit (Life Technologies, USA) on genomic DNA following manufacturer's protocol. Whole Exome Sequencing (WES) reads were aligned to the human reference genome (hg19 build) with Torrent Suite Software (v5.0.2) and the variants were called using the Torrent Variant Caller plugin (v5.0) and imported into Ion Reporter Server (v5.0) for the annotation. CCR5 coding exons variants were filtered and checked against the NHLBI GO Exome Sequencing Project (NHLBI), NCBI Reference dbSNPs database, 1000 genomes and Exome Aggregation Consortium datasets (ExAC). RESULTS: A total of 475 variants were identified. Table 1 shows polymorphisms/mutations detected within exons that introduced an amino acid change, deletion or copy number variants (CNV). Three mutations are predicted to influence CCR5 function, including the 32bp deletion (Rs333). Four polymorphisms were detected, plus two CNV. CONCLUSIONS: This is the first report on sequencing the full CCR5 gene using NGS in the Saudi population. Here we demonstrate seven polymorphisms/mutations that were reported before. All were detected within very low frequency including the delta 32 mutation. However, we report for the first time copy number variants at two CCR5 gene locations; 45072265 and 38591712.