ABSTRACT
Continued advances in variant effect prediction are necessary to demonstrate the ability of machine learning methods to accurately determine the clinical impact of variants of unknown significance (VUS). Towards this goal, the ARSA Critical Assessment of Genome Interpretation (CAGI) challenge was designed to characterize progress by utilizing 219 experimentally assayed missense VUS in the Arylsulfatase A (ARSA) gene to assess the performance of community-submitted predictions of variant functional effects. The challenge involved 15 teams, and evaluated additional predictions from established and recently released models. Notably, a model developed by participants of a genetics and coding bootcamp, trained with standard machine-learning tools in Python, demonstrated superior performance among submissions. Furthermore, the study observed that state-of-the-art deep learning methods provided small but statistically significant improvement in predictive performance compared to less elaborate techniques. These findings underscore the utility of variant effect prediction, and the potential for models trained with modest resources to accurately classify VUS in genetic and clinical research.
ABSTRACT
Newborn screening for severe combined immunodeficiency (SCID) has not only accelerated diagnosis and improved treatment for affected infants, but also led to identification of novel genes required for human T cell development. A male proband had SCID newborn screening showing very low T cell receptor excision circles (TRECs), a biomarker for thymic output of nascent T cells. He had persistent profound T lymphopenia, but normal numbers of B and natural killer (NK) cells. Despite an allogeneic hematopoietic stem cell transplant from his brother, he failed to develop normal T cells. Targeted resequencing excluded known SCID genes; however, whole exome sequencing (WES) of the proband and parents revealed a maternally inherited X-linked missense mutation in MED14 (MED14V763A), a component of the mediator complex. Morpholino (MO)-mediated loss of MED14 function attenuated T cell development in zebrafish. Moreover, this arrest was rescued by ectopic expression of cDNA encoding the wild type human MED14 ortholog, but not by MED14V763A , suggesting that the variant impaired MED14 function. Modeling of the equivalent mutation in mouse (Med14V769A) did not disrupt T cell development at baseline. However, repopulation of peripheral T cells upon competitive bone marrow transplantation was compromised, consistent with the incomplete T cell reconstitution experienced by the proband upon transplantation with bone marrow from his healthy male sibling, who was found to have the same MED14V763A variant. Suspecting that the variable phenotypic expression between the siblings was influenced by further mutation(s), we sought to identify genetic variants present only in the affected proband. Indeed, WES revealed a mutation in the L1 cell adhesion molecule (L1CAMQ498H); however, introducing that mutation in vivo in mice did not disrupt T cell development. Consequently, immunodeficiency in the proband may depend upon additional, unidentified gene variants.
Subject(s)
Lymphopenia , Severe Combined Immunodeficiency , Animals , Humans , Infant , Infant, Newborn , Lymphopenia/genetics , Male , Mice , Neonatal Screening , Severe Combined Immunodeficiency/diagnosis , Severe Combined Immunodeficiency/genetics , Severe Combined Immunodeficiency/therapy , T-Lymphocytes , ZebrafishABSTRACT
Genetics play a key role in venous thromboembolism (VTE) risk, however established risk factors in European populations do not translate to individuals of African descent because of the differences in allele frequencies between populations. As part of the fifth iteration of the Critical Assessment of Genome Interpretation, participants were asked to predict VTE status in exome data from African American subjects. Participants were provided with 103 unlabeled exomes from patients treated with warfarin for non-VTE causes or VTE and asked to predict which disease each subject had been treated for. Given the lack of training data, many participants opted to use unsupervised machine learning methods, clustering the exomes by variation in genes known to be associated with VTE. The best performing method using only VTE related genes achieved an area under the ROC curve of 0.65. Here, we discuss the range of methods used in the prediction of VTE from sequence data and explore some of the difficulties of conducting a challenge with known confounders. In addition, we show that an existing genetic risk score for VTE that was developed in European subjects works well in African Americans.
Subject(s)
Exome Sequencing/methods , Venous Thromboembolism/genetics , Warfarin/administration & dosage , Cluster Analysis , Computational Biology/methods , Congresses as Topic , Female , Genetic Predisposition to Disease , Humans , Male , ROC Curve , Unsupervised Machine Learning , Venous Thromboembolism/drug therapy , Warfarin/therapeutic useABSTRACT
BACKGROUND: Severe combined immunodeficiency (SCID) is characterized by arrested T-lymphocyte production and by B-lymphocyte dysfunction, which result in life-threatening infections. Early diagnosis of SCID through population-based screening of newborns can aid clinical management and help improve outcomes; it also permits the identification of previously unknown factors that are essential for lymphocyte development in humans. METHODS: SCID was detected in a newborn before the onset of infections by means of screening of T-cell-receptor excision circles, a biomarker for thymic output. On confirmation of the condition, the affected infant was treated with allogeneic hematopoietic stem-cell transplantation. Exome sequencing in the patient and parents was followed by functional analysis of a prioritized candidate gene with the use of human hematopoietic stem cells and zebrafish embryos. RESULTS: The infant had "leaky" SCID (i.e., a form of SCID in which a minimal degree of immune function is preserved), as well as craniofacial and dermal abnormalities and the absence of a corpus callosum; his immune deficit was fully corrected by hematopoietic stem-cell transplantation. Exome sequencing revealed a heterozygous de novo missense mutation, p.N441K, in BCL11B. The resulting BCL11B protein had dominant negative activity, which abrogated the ability of wild-type BCL11B to bind DNA, thereby arresting development of the T-cell lineage and disrupting hematopoietic stem-cell migration; this revealed a previously unknown function of BCL11B. The patient's abnormalities, when recapitulated in bcl11ba-deficient zebrafish, were reversed by ectopic expression of functionally intact human BCL11B but not mutant human BCL11B. CONCLUSIONS: Newborn screening facilitated the identification and treatment of a previously unknown cause of human SCID. Coupling exome sequencing with an evaluation of candidate genes in human hematopoietic stem cells and in zebrafish revealed that a constitutional BCL11B mutation caused human multisystem anomalies with SCID and also revealed a prethymic role for BCL11B in hematopoietic progenitors. (Funded by the National Institutes of Health and others.).
Subject(s)
Abnormalities, Multiple/genetics , Hematopoietic Stem Cells/physiology , Mutation, Missense , Repressor Proteins/genetics , Severe Combined Immunodeficiency/genetics , Tumor Suppressor Proteins/genetics , Animals , Brain/diagnostic imaging , Cell Movement , Disease Models, Animal , Gene Expression Regulation , Hematopoietic Stem Cell Transplantation , Hematopoietic Stem Cells/metabolism , Humans , In Vitro Techniques , Infant, Newborn , Magnetic Resonance Imaging , Male , Neonatal Screening/methods , Receptors, Antigen, T-Cell , Repressor Proteins/deficiency , Repressor Proteins/metabolism , Tumor Suppressor Proteins/deficiency , Tumor Suppressor Proteins/metabolism , Zebrafish/growth & developmentABSTRACT
PURPOSE: Severe combined immunodeficiency (SCID) is characterized by failure of T lymphocyte development and absent or very low T cell receptor excision circles (TRECs), DNA byproducts of T cell maturation. Newborn screening for TRECs to identify SCID is now performed in several states using PCR of DNA from universally collected dried blood spots (DBS). In addition to infants with typical SCID, TREC screening identifies infants with T lymphocytopenia who appear healthy and in whom a SCID diagnosis cannot be confirmed. Deep sequencing was employed to find causes of T lymphocytopenia in such infants. METHODS: Whole exome sequencing and analysis were performed in infants and their parents. Upon finding deleterious mutations in the ataxia telangiectasia mutated (ATM) gene, we confirmed the diagnosis of ataxia telangiectasia (AT) in two infants and then tested archival newborn DBS of additional AT patients for TREC copy number. RESULTS: Exome sequencing and analysis led to 2 unsuspected gene diagnoses of AT. Of 13 older AT patients for whom newborn DBS had been stored, 7 samples tested positive for SCID under the criteria of California's newborn screening program. AT children with low neonatal TRECs had low CD4 T cell counts subsequently detected (R = 0.64). CONCLUSIONS: T lymphocytopenia in newborns can be a feature of AT, as revealed by TREC screening and exome sequencing. Although there is no current cure for the progressive neurological impairment of AT, early detection permits avoidance of infectious complications, while providing information for families regarding reproductive recurrence risks and increased cancer risks in patients and carriers.
Subject(s)
Ataxia Telangiectasia/diagnosis , Neonatal Screening , Severe Combined Immunodeficiency/diagnosis , Amino Acid Sequence , Ataxia Telangiectasia/complications , Ataxia Telangiectasia/genetics , Ataxia Telangiectasia Mutated Proteins , Base Sequence , Cell Cycle Proteins/genetics , Child , Child, Preschool , DNA-Binding Proteins/genetics , Exome , Female , Humans , Infant , Infant, Newborn , Lymphopenia/genetics , Male , Mutation , Phenotype , Polymorphism, Single Nucleotide , Protein Serine-Threonine Kinases/genetics , Severe Combined Immunodeficiency/complications , Severe Combined Immunodeficiency/genetics , Tumor Suppressor Proteins/geneticsABSTRACT
Enzyme activation by monovalent cations is widely documented in plants and the animal world. In type II enzymes, activation entails two steps: binding of the monovalent cation to its allosteric site and transduction of this event into enhanced catalytic activity. The effect has exquisite specificity for either Na(+) or K(+), the most abundant cations present in physiological environments. Enzymes requiring K(+) such as kinases and molecular chaperones are not activated as well or at all by the larger cation Cs(+) or the smaller cations Na(+) and Li(+). Enzymes requiring Na(+) such as ß-galactosidase and clotting proteases are not activated as well by Li(+), or the larger cations K(+), Rb(+), and Cs(+). Efforts to switch specificity between Na(+) and K(+) in this large class of enzymes and completely redesign the mechanism of allosteric transduction leading to enhanced catalytic activity have so far been unsuccessful. Here we show how mutagenesis of two loops defining the Na(+) binding site of thrombin, a Na(+)-activated clotting protease, generates a construct that is most active in the presence of K(+) toward synthetic and physiological substrates. The effect is the result of a higher binding affinity and more efficient allosteric transduction of binding into enhanced catalytic activity for K(+) compared to Na(+), which represents a complete reversal of the properties of wild type. In addition, the construct features altered specificity toward physiological substrates resulting in a significant anticoagulant profile. The findings are relevant to all Na(+)-activated proteases involved in blood coagulation and the complement system.