ABSTRACT
Acute pericarditis is defined as inflammation of the pericardium and occurs in approximately 4.4% of patients who present to the emergency department for nonischemic chest pain, with a higher prevalence in men. Although there are numerous etiologies of pericarditis, most episodes are idiopathic and the cause is presumed to be viral. Diagnosis of pericarditis requires at least two of the following criteria: new or worsening pericardial effusion, characteristic pleuritic chest pain, pericardial friction rub, or electrocardiographic changes, including new, widespread ST elevations or PR depressions. Pericardial friction rubs are highly specific but transient, and they have been reported in 18% to 84% of patients with acute pericarditis. Classic electrocardiographic findings include PR-segment depressions; diffuse, concave, upward ST-segment elevations without reciprocal changes; and T-wave inversions. Transthoracic echocardiography should be performed in all patients with acute pericarditis to characterize the size of effusions and evaluate for complications. Nonsteroidal anti-inflammatory drugs are the first-line treatment option. Glucocorticoids should be reserved for patients with contraindications to first-line therapy and those who are pregnant beyond 20 weeks' gestation or have other systemic inflammatory conditions. Colchicine should be used in combination with first- or second-line treatments to reduce the risk of recurrence. Patients with a higher risk of complications should be admitted to the hospital for further workup and treatment.
Subject(s)
Anti-Inflammatory Agents, Non-Steroidal , Electrocardiography , Pericarditis , Humans , Pericarditis/diagnosis , Pericarditis/physiopathology , Pericarditis/therapy , Acute Disease , Anti-Inflammatory Agents, Non-Steroidal/therapeutic use , Colchicine/therapeutic use , Echocardiography , Female , Pericardial Effusion/diagnosis , Pericardial Effusion/therapy , Pericardial Effusion/etiology , Chest Pain/etiology , Chest Pain/diagnosis , Male , Glucocorticoids/therapeutic useABSTRACT
This study aimed to enhance performance, identify additional predictors, and improve the interpretability of biopsychosocial machine learning models for low back pain (LBP). Using survey data from a 6-year nationwide study involving 17,609 adults aged ≥50 years (Korea National Health and Nutrition Examination Survey), we explored 119 factors to detect LBP in individuals who reported experiencing LBP for at least 30 days within the previous 3 months. Our primary model, model 1, employed eXtreme Gradient Boosting (XGBoost) and selected primary factors (PFs) based on their feature importance scores. To extend this, we introduced additional factors, such as lumbar X-ray findings, physical activity, sitting time, and nutrient intake levels, which were available only during specific survey periods, into models 2 to 4. Model performance was evaluated using the area under the curve, with predicted probabilities explained by SHapley Additive exPlanations. Eleven PFs were identified, and model 1 exhibited an enhanced area under the curve .8 (.77-.84, 95% confidence interval). The factors had varying impacts across individuals, underscoring the need for personalized assessment. Hip and knee joint pain were the most significant PFs. High levels of physical activity were found to have a negative association with LBP, whereas a high intake of omega-6 was found to have a positive association. Notably, we identified factor clusters, including hip joint pain and female sex, potentially linked to osteoarthritis. In summary, this study successfully developed effective XGBoost models for LBP detection, thereby providing valuable insight into LBP-related factors. Comprehensive LBP management, particularly in women with osteoarthritis, is crucial given the presence of multiple factors. PERSPECTIVE: This article introduces XGBoost models designed to detect LBP and explores the multifactorial aspects of LBP through the application of SHapley Additive exPlanations and network analysis on the 4 developed models. The utilization of this analytical system has the potential to aid in devising personalized management strategies to address LBP.
Subject(s)
Low Back Pain , Machine Learning , Humans , Low Back Pain/diagnosis , Female , Male , Middle Aged , Aged , Exercise/physiology , Nutrition SurveysABSTRACT
OBJECTIVE: We applied natural language processing and inference methods to extract social determinants of health (SDoH) information from clinical notes of patients with chronic low back pain (cLBP) to enhance future analyses of the associations between SDoH disparities and cLBP outcomes. MATERIALS AND METHODS: Clinical notes for patients with cLBP were annotated for 7 SDoH domains, as well as depression, anxiety, and pain scores, resulting in 626 notes with at least one annotated entity for 364 patients. We used a 2-tier taxonomy with these 10 first-level classes (domains) and 52 second-level classes. We developed and validated named entity recognition (NER) systems based on both rule-based and machine learning approaches and validated an entailment model. RESULTS: Annotators achieved a high interrater agreement (Cohen's kappa of 95.3% at document level). A rule-based system (cTAKES), RoBERTa NER, and a hybrid model (combining rules and logistic regression) achieved performance of F1 = 47.1%, 84.4%, and 80.3%, respectively, for first-level classes. DISCUSSION: While the hybrid model had a lower F1 performance, it matched or outperformed RoBERTa NER model in terms of recall and had lower computational requirements. Applying an untuned RoBERTa entailment model, we detected many challenging wordings missed by NER systems. Still, the entailment model may be sensitive to hypothesis wording. CONCLUSION: This study developed a corpus of annotated clinical notes covering a broad spectrum of SDoH classes. This corpus provides a basis for training machine learning models and serves as a benchmark for predictive models for NER for SDoH and knowledge extraction from clinical texts.
Subject(s)
Low Back Pain , Humans , Social Determinants of Health , Natural Language Processing , Machine LearningABSTRACT
Asthma affects more than 25 million people in the United States, and 62% of adults with asthma do not have adequately controlled symptoms. Asthma severity and level of control should be assessed at diagnosis and evaluated at subsequent visits using validated tools such as the Asthma Control Test or the asthma APGAR (activities, persistent, triggers, asthma medications, response to therapy) tools. Short-acting beta2 agonists are preferred asthma reliever medications. Controller medications consist of inhaled corticosteroids, long-acting beta2 agonists, long-acting muscarinic antagonists, and leukotriene receptor antagonists. Treatment typically begins with inhaled corticosteroids, and additional medications or dosage increases should be added in a stepwise fashion according to guideline-directed therapy recommendations from the National Asthma Education and Prevention Program or the Global Initiative for Asthma when symptoms are inadequately controlled. Single maintenance and reliever therapy combines an inhaled corticosteroid and long-acting beta2 agonist for controller and reliever treatments. This therapy is preferred for adults and adolescents because of its effectiveness in reducing severe exacerbations. Subcutaneous immunotherapy may be considered for those five years and older with mild to moderate allergic asthma; however, sublingual immunotherapy is not recommended. Patients with severe uncontrolled asthma despite appropriate treatment should be reassessed and considered for specialty referral. Biologic agents may be considered for patients with severe allergic and eosinophilic asthma.
Subject(s)
Anti-Asthmatic Agents , Asthma , Adult , Adolescent , Humans , Asthma/diagnosis , Asthma/drug therapy , Adrenal Cortex Hormones/therapeutic use , Administration, Inhalation , Muscarinic Antagonists/therapeutic use , Drug Therapy, CombinationABSTRACT
PURPOSE: To identify independent risk factors, including the Risk Assessment and Prediction Tool (RAPT) score, associated with extended length of stay (eLOS) and non-home discharge following elective multi-level instrumented spine fusion operations for diagnosis of adult spinal deformity (ASD) and lumbar degenerative pathology. METHODS: Adults who underwent multi-level ([Formula: see text] segments) instrumented spine fusions for ASD and lumbar degenerative pathology at a single institution (2016-2021) were reviewed. Presence of a pre-operative RAPT score was used as an inclusion criterion. Excluded were patients who underwent non-elective operations, revisions, operations for trauma, malignancy, and/or infections. Outcomes were eLOS (> 7 days) and discharge location (home vs. non-home). Predictor variables included demographics, comorbidities, operative information, Surgical Invasiveness Index (SII), and RAPT score. Fisher's exact test was used for univariate analysis, and significant variables were implemented in multivariate binary logistic regression, with generation of 95% percent confidence intervals (CI), odds ratios (OR), and p-values. RESULTS: Included for analysis were 355 patients. Post-operatively, 36.6% (n = 130) had eLOS and 53.2% (n = 189) had a non-home discharge. Risk factors significant for a non-home discharge were older age (> 70 years), SII > 36, pre-op RAPT < 10, DMII, diagnosis of depression or anxiety, and eLOS. Risk factors significant for an eLOS were SII > 20, RAPT < 6, and an ASA score of 3. CONCLUSION: The RAPT score and SII were most important significant predictors of eLOS and non-home discharges following multi-level instrumented fusions for lumbar spinal pathology and deformity. Preoperative optimization of the RAPT's individual components may provide a useful strategy for decreasing LOS and modifying discharge disposition.
Subject(s)
Patient Discharge , Spine , Humans , Adult , Length of Stay , Risk Factors , Risk AssessmentABSTRACT
STUDY DESIGN: A retrospective study at a single academic institution. OBJECTIVE: The purpose of this study is to utilize machine learning to predict hospital length of stay (LOS) and discharge disposition following adult elective spine surgery, and to compare performance metrics of machine learning models to the American College of Surgeon's National Surgical Quality Improvement Program's (ACS NSQIP) prediction calculator. SUMMARY OF BACKGROUND DATA: A total of 3678 adult patients undergoing elective spine surgery between 2014 and 2019, acquired from the electronic health record. METHODS: Patients were divided into three stratified cohorts: cervical degenerative, lumbar degenerative, and adult spinal deformity groups. Predictive variables included demographics, body mass index, surgical region, surgical invasiveness, surgical approach, and comorbidities. Regression, classification trees, and least absolute shrinkage and selection operator (LASSO) were used to build predictive models. Validation of the models was conducted on 16% of patients (N=587), using area under the receiver operator curve (AUROC), sensitivity, specificity, and correlation. Patient data were manually entered into the ACS NSQIP online risk calculator to compare performance. Outcome variables were discharge disposition (home vs. rehabilitation) and LOS (days). RESULTS: Of 3678 patients analyzed, 51.4% were male (n=1890) and 48.6% were female (n=1788). The average LOS was 3.66 days. In all, 78% were discharged home and 22% discharged to rehabilitation. Compared with NSQIP (Pearson R2 =0.16), the predictions of poisson regression ( R2 =0.29) and LASSO ( R2 =0.29) models were significantly more correlated with observed LOS ( P =0.025 and 0.004, respectively). Of the models generated to predict discharge location, logistic regression yielded an AUROC of 0.79, which was statistically equivalent to the AUROC of 0.75 for NSQIP ( P =0.135). CONCLUSION: The predictive models developed in this study can enable accurate preoperative estimation of LOS and risk of rehabilitation discharge for adult patients undergoing elective spine surgery. The demonstrated models exhibited better performance than NSQIP for prediction of LOS and equivalent performance to NSQIP for prediction of discharge location.
Subject(s)
Postoperative Complications , Quality Improvement , Adult , United States , Humans , Retrospective Studies , Postoperative Complications/surgery , Elective Surgical Procedures , Spine/surgery , Length of Stay , Risk AssessmentABSTRACT
Chronic low back pain (LBP) is a leading cause of disability and opioid prescriptions worldwide, representing a significant medical and socioeconomic problem. Clinical heterogeneity of LBP limits accurate diagnosis and precise treatment planning, culminating in poor patient outcomes. A current priority of LBP research is the development of objective, multidimensional assessment tools that subgroup LBP patients based on neurobiological pain mechanisms, to facilitate matching patients with the optimal therapies. Using unsupervised machine learning on full body biomechanics, including kinematics, dynamics, and muscle forces, captured with a marker-less depth camera, this study identified a forward-leaning sit-to-stand strategy (STS) as a discriminating movement biomarker for LBP subjects. A forward-leaning STS strategy, as opposed to a vertical rise strategy seen in the control participants, is less efficient and results in increased spinal loads. Inefficient STS with the subsequent higher spinal loading may be a biomarker of poor motor control in LBP patients as well as a potential source of the ongoing symptomology.
ABSTRACT
BACKGROUND: In epidemiological studies, finding the best subset of factors is challenging when the number of explanatory variables is large. OBJECTIVE: Our study had two aims. First, we aimed to identify essential depression-associated factors using the extreme gradient boosting (XGBoost) machine learning algorithm from big survey data (the Korea National Health and Nutrition Examination Survey, 2012-2016). Second, we aimed to achieve a comprehensive understanding of multifactorial features in depression using network analysis. METHODS: An XGBoost model was trained and tested to classify "current depression" and "no lifetime depression" for a data set of 120 variables for 12,596 cases. The optimal XGBoost hyperparameters were set by an automated machine learning tool (TPOT), and a high-performance sparse model was obtained by feature selection using the feature importance value of XGBoost. We performed statistical tests on the model and nonmodel factors using survey-weighted multiple logistic regression and drew a correlation network among factors. We also adopted statistical tests for the confounder or interaction effect of selected risk factors when it was suspected on the network. RESULTS: The XGBoost-derived depression model consisted of 18 factors with an area under the weighted receiver operating characteristic curve of 0.86. Two nonmodel factors could be found using the model factors, and the factors were classified into direct (P<.05) and indirect (P≥.05), according to the statistical significance of the association with depression. Perceived stress and asthma were the most remarkable risk factors, and urine specific gravity was a novel protective factor. The depression-factor network showed clusters of socioeconomic status and quality of life factors and suggested that educational level and sex might be predisposing factors. Indirect factors (eg, diabetes, hypercholesterolemia, and smoking) were involved in confounding or interaction effects of direct factors. Triglyceride level was a confounder of hypercholesterolemia and diabetes, smoking had a significant risk in females, and weight gain was associated with depression involving diabetes. CONCLUSIONS: XGBoost and network analysis were useful to discover depression-related factors and their relationships and can be applied to epidemiological studies using big survey data.
Subject(s)
Depression , Quality of Life , Depression/epidemiology , Epidemiologic Studies , Female , Humans , Machine Learning , Nutrition SurveysABSTRACT
OBJECTIVE: Using the newly created University of California (UC) Health Data Warehouse, we present the first study to analyze antihyperglycemic treatment utilization across the five large UC academic health systems (Davis, Irvine, Los Angeles, San Diego, and San Francisco). RESEARCH DESIGN AND METHODS: This retrospective analysis used deidentified electronic health records (EHRs; 2014-2019) including 97,231 patients with type 2 diabetes from 1,003 UC-affiliated clinical settings. Significant differences between health systems and individual providers were identified using binomial probabilities with cohort matching. RESULTS: Our analysis reveals statistically different treatment utilization patterns not only between health systems but also among individual providers within health systems. We identified 21 differences among health systems and 29 differences among individual providers within these health systems, with respect to treatment intensifications within existing guidelines on top of either metformin monotherapy or dual therapy with metformin and a sulfonylurea. Next, we identified variation for medications within the same class (e.g., glipizide vs. glyburide among sulfonylureas), with 33 differences among health systems and 86 among individual providers. Finally, we identified 2 health systems and 55 individual providers who more frequently used medications with known cardioprotective benefits for patients with high cardiovascular disease risk, but also 1 health system and 8 providers who prescribed such medications less frequently for these patients. CONCLUSIONS: Our study used cohort-matching techniques to highlight real-world variation in care between health systems and individual providers. This demonstrates the power of EHRs to quantify differences in treatment utilization, a necessary step toward standardizing precision care for large populations.
Subject(s)
Diabetes Mellitus, Type 2 , Metformin , Diabetes Mellitus, Type 2/drug therapy , Humans , Hypoglycemic Agents/therapeutic use , Metformin/therapeutic use , Retrospective Studies , Sulfonylurea Compounds/therapeutic useABSTRACT
There is a great and growing need to ascertain what exactly is the state of a patient, in terms of disease progression, actual care practices, pathology, adverse events, and much more, beyond the paucity of data available in structured medical record data. Ascertaining these harder-to-reach data elements is now critical for the accurate phenotyping of complex traits, detection of adverse outcomes, efficacy of off-label drug use, and longitudinal patient surveillance. Clinical notes often contain the most detailed and relevant digital information about individual patients, the nuances of their diseases, the treatment strategies selected by physicians, and the resulting outcomes. However, notes remain largely unused for research because they contain Protected Health Information (PHI), which is synonymous with individually identifying data. Previous clinical note de-identification approaches have been rigid and still too inaccurate to see any substantial real-world use, primarily because they have been trained with too small medical text corpora. To build a new de-identification tool, we created the largest manually annotated clinical note corpus for PHI and develop a customizable open-source de-identification software called Philter ("Protected Health Information filter"). Here we describe the design and evaluation of Philter, and show how it offers substantial real-world improvements over prior methods.
ABSTRACT
BACKGROUND: Dry eye disease (DED) is a complex disease of the ocular surface, and its associated factors are important for understanding and effectively treating DED. OBJECTIVE: This study aimed to provide an integrative and personalized model of DED by making an explanatory model of DED using as many factors as possible from the Korea National Health and Nutrition Examination Survey (KNHANES) data. METHODS: Using KNHANES data for 2012 (4391 sample cases), a point-based scoring system was created for ranking factors associated with DED and assessing patient-specific DED risk. First, decision trees and lasso were used to classify continuous factors and to select important factors, respectively. Next, a survey-weighted multiple logistic regression was trained using these factors, and points were assigned using the regression coefficients. Finally, network graphs of partial correlations between factors were utilized to study the interrelatedness of DED-associated factors. RESULTS: The point-based model achieved an area under the curve of 0.70 (95% CI 0.61-0.78), and 13 of 78 factors considered were chosen. Important factors included sex (+9 points for women), corneal refractive surgery (+9 points), current depression (+7 points), cataract surgery (+7 points), stress (+6 points), age (54-66 years; +4 points), rhinitis (+4 points), lipid-lowering medication (+4 points), and intake of omega-3 (0.43%-0.65% kcal/day; -4 points). Among these, the age group 54 to 66 years had high centrality in the network, whereas omega-3 had low centrality. CONCLUSIONS: Integrative understanding of DED was possible using the machine learning-based model and network-based factor analysis. This method for finding important risk factors and identifying patient-specific risk could be applied to other multifactorial diseases.
ABSTRACT
The fight against cancer is hindered by its highly heterogeneous nature. Genome-wide sequencing studies have shown that individual malignancies contain many mutations that range from those commonly found in tumor genomes to rare somatic variants present only in a small fraction of lesions. Such rare somatic variants dominate the landscape of genomic mutations in cancer, yet efforts to correlate somatic mutations found in one or few individuals with functional roles have been largely unsuccessful. Traditional methods for identifying somatic variants that drive cancer are 'gene-centric' in that they consider only somatic variants within a particular gene and make no comparison to other similar genes in the same family that may play a similar role in cancer. In this work, we present oncodomain hotspots, a new 'domain-centric' method for identifying clusters of somatic mutations across entire gene families using protein domain models. Our analysis confirms that our approach creates a framework for leveraging structural and functional information encapsulated by protein domains into the analysis of somatic variants in cancer, enabling the assessment of even rare somatic variants by comparison to similar genes. Our results reveal a vast landscape of somatic variants that act at the level of domain families altering pathways known to be involved with cancer such as protein phosphorylation, signaling, gene regulation, and cell metabolism. Due to oncodomain hotspots' unique ability to assess rare variants, we expect our method to become an important tool for the analysis of sequenced tumor genomes, complementing existing methods.
Subject(s)
Computational Biology/methods , Mutation/genetics , Neoplasms/genetics , Oncogene Proteins/genetics , Protein Domains/genetics , Databases, Protein , Epidermal Growth Factor/genetics , Humans , Mitochondrial Proteins/genetics , Models, Molecular , Oncogene Proteins/classification , Protein Binding , ras Proteins/geneticsABSTRACT
In silico methods for detecting functionally relevant genetic variants are important for identifying genetic markers of human inherited disease. Much research has focused on protein-coding variants since coding regions have well-defined physicochemical and functional properties. However, many bioinformatics tools are not applicable to variants outside coding regions. Here, we increase the classification performance of our regulatory single-nucleotide variant predictor (RSVP) for variants that cause regulatory abnormalities from an AUC of 0.90-0.97 by incorporating genomic regions identified by the ENCODE project into RSVP. RSVP is comparable to a recently published tool, Genome-Wide Annotation of Variants (GWAVA); both RSVP and GWAVA perform better on regulatory variants than a traditional variant predictor, combined annotation-dependent depletion (CADD). However, our method outperforms GWAVA on variants located at similar distances to the transcription start site as the positive set (AUC: 0.96) as compared with GWAVA (AUC: 0.71). Much of this disparity is due to RSVP's incorporation of features pertaining to the nearest gene (expression, GO terms, etc.), which are not included in GWAVA. Our findings hold out the promise of a framework for the assessment of all functional regulatory variants, providing a means to predict which rare or de novo variants are of pathogenic significance.
Subject(s)
Computational Biology/methods , Genomics/methods , Polymorphism, Single Nucleotide , Computer Simulation , Genetic Predisposition to Disease , Genome, Human , Humans , Machine LearningABSTRACT
The fight against cancer has been hindered by its highly heterogeneous nature. Recent genome-wide sequencing studies have shown that individual malignancies contain many mutations that range from those commonly found in tumor genomes to rare cancer somatic mutations present only in a small fraction of lesions. For instance, the genome of a colorectal cancer in one patient can have somewhere between 50 to 100 somatic mutations, but might share only 2 or 3 mutated genes with colorectal tumor genomes from other patients. Somatic mutations that are frequently found in tumor genomes often play a significant role in tumor development and are thus classified as cancer driver mutations. However, efforts to correlate somatic mutations found in one or few individual tumor genomes with critical functional roles in tumor development have so far been unsuccessful. In this paper, we analyze cancer somatic mutations from lung and other types of cancer patients using a new approach based on aggregation of mutational data at the protein domain level. Our preliminary analysis confirms that our approach creates a framework for leveraging structural genomics and evolution into the analysis of somatic cancer mutations. We found that by incorporating information about classification of proteins and protein sites we are able to detect novel clusters of cancer somatic mutations.
ABSTRACT
Variations and similarities in our individual genomes are part of our history, our heritage, and our identity. Some human genomic variants are associated with common traits such as hair and eye color, while others are associated with susceptibility to disease or response to drug treatment. Identifying the human variations producing clinically relevant phenotypic changes is critical for providing accurate and personalized diagnosis, prognosis, and treatment for diseases. Furthermore, a better understanding of the molecular underpinning of disease can lead to development of new drug targets for precision medicine. Several resources have been designed for collecting and storing human genomic variations in highly structured, easily accessible databases. Unfortunately, a vast amount of information about these genetic variants and their functional and phenotypic associations is currently buried in the literature, only accessible by manual curation or sophisticated text text-mining technology to extract the relevant information. In addition, the low cost of sequencing technologies coupled with increasing computational power has enabled the development of numerous computational methodologies to predict the pathogenicity of human variants. This review provides a detailed comparison of current human variant resources, including HGMD, OMIM, ClinVar, and UniProt/Swiss-Prot, followed by an overview of the computational methods and techniques used to leverage the available data to predict novel deleterious variants. We expect these resources and tools to become the foundation for understanding the molecular details of genomic variants leading to disease, which in turn will enable the promise of precision medicine.
Subject(s)
Computational Biology/methods , Genetic Predisposition to Disease , Genetic Variation , Genome, Human , Sequence Analysis/methods , HumansABSTRACT
BACKGROUND: The body of disease mutations with known phenotypic relevance continues to increase and is expected to do so even faster with the advent of new experimental techniques such as whole-genome sequencing coupled with disease association studies. However, genomic association studies are limited by the molecular complexity of the phenotype being studied and the population size needed to have adequate statistical power. One way to circumvent this problem, which is critical for the study of rare diseases, is to study the molecular patterns emerging from functional studies of existing disease mutations. Current gene-centric analyses to study mutations in coding regions are limited by their inability to account for the functional modularity of the protein. Previous studies of the functional patterns of known human disease mutations have shown a significant tendency to cluster at protein domain positions, namely position-based domain hotspots of disease mutations. However, the limited number of known disease mutations remains the main factor hindering the advancement of mutation studies at a functional level. In this paper, we address this problem by incorporating mutations known to be disruptive of phenotypes in other species. Focusing on two evolutionarily distant organisms, human and yeast, we describe the first inter-species analysis of mutations of phenotypic relevance at the protein domain level. RESULTS: The results of this analysis reveal that phenotypic mutations from yeast cluster at specific positions on protein domains, a characteristic previously revealed to be displayed by human disease mutations. We found over one hundred domain hotspots in yeast with approximately 50% in the exact same domain position as known human disease mutations. CONCLUSIONS: We describe an analysis using protein domains as a framework for transferring functional information by studying domain hotspots in human and yeast and relating phenotypic changes in yeast to diseases in human. This first-of-a-kind study of phenotypically relevant yeast mutations in relation to human disease mutations demonstrates the utility of a multi-species analysis for advancing the understanding of the relationship between genetic mutations and phenotypic changes at the organismal level.
Subject(s)
Computational Biology/methods , Evolution, Molecular , Genetic Diseases, Inborn/genetics , Mutation/genetics , Phenotype , Humans , Protein Structure, Tertiary/genetics , Species Specificity , YeastsABSTRACT
BACKGROUND: Large-scale tumor sequencing projects are now underway to identify genetic mutations that drive tumor initiation and development. Most studies take a gene-based approach to identifying driver mutations, highlighting genes mutated in a large percentage of tumor samples as those likely to contain driver mutations. However, this gene-based approach usually does not consider the position of the mutation within the gene or the functional context the position of the mutation provides. Here we introduce a novel method for mapping mutations to distinct protein domains, not just individual genes, in which they occur, thus providing the functional context for how the mutation contributes to disease. Furthermore, aggregating mutations from all genes containing a specific protein domain enables the identification of mutations that are rare at the gene level, but that occur frequently within the specified domain. These highly mutated domains potentially reveal disruptions of protein function necessary for cancer development. RESULTS: We mapped somatic mutations from the protein coding regions of 100 colon adenocarcinoma tumor samples to the genes and protein domains in which they occurred, and constructed topographical maps to depict the "mutational landscapes" of gene and domain mutation frequencies. We found significant mutation frequency in a number of genes previously known to be somatically mutated in colon cancer patients including APC, TP53 and KRAS. In addition, we found significant mutation frequency within specific domains located in these genes, as well as within other domains contained in genes having low mutation frequencies. These domain "peaks" were enriched with functions important to cancer development including kinase activity, DNA binding and repair, and signal transduction. CONCLUSIONS: Using our method to create the domain landscapes of mutations in colon cancer, we were able to identify somatic mutations with high potential to drive cancer development. Interestingly, the majority of the genes involved have a low mutation frequency. Therefore, the method shows good potential for identifying rare driver mutations in current, large-scale tumor sequencing projects. In addition, mapping mutations to specific domains provides the necessary functional context for understanding how the mutations contribute to the disease, and may reveal novel or more refined gene and domain target regions for drug development.
Subject(s)
Computational Biology/methods , Neoplasms/genetics , Colonic Neoplasms/genetics , Humans , Mutation/geneticsABSTRACT
BACKGROUND AND OBJECTIVE: With recent breakthroughs in high-throughput sequencing, identifying deleterious mutations is one of the key challenges for personalized medicine. At the gene and protein level, it has proven difficult to determine the impact of previously unknown variants. A statistical method has been developed to assess the significance of disease mutation clusters on protein domains by incorporating domain functional annotations to assist in the functional characterization of novel variants. METHODS: Disease mutations aggregated from multiple databases were mapped to domains, and were classified as either cancer- or non-cancer-related. The statistical method for identifying significantly disease-associated domain positions was applied to both sets of mutations and to randomly generated mutation sets for comparison. To leverage the known function of protein domain regions, the method optionally distributes significant scores to associated functional feature positions. RESULTS: Most disease mutations are localized within protein domains and display a tendency to cluster at individual domain positions. The method identified significant disease mutation hotspots in both the cancer and non-cancer datasets. The domain significance scores (DS-scores) for cancer form a bimodal distribution with hotspots in oncogenes forming a second peak at higher DS-scores than non-cancer, and hotspots in tumor suppressors have scores more similar to non-cancers. In addition, on an independent mutation benchmarking set, the DS-score method identified mutations known to alter protein function with very high precision. CONCLUSION: By aggregating mutations with known disease association at the domain level, the method was able to discover domain positions enriched with multiple occurrences of deleterious mutations while incorporating relevant functional annotations. The method can be incorporated into translational bioinformatics tools to characterize rare and novel variants within large-scale sequencing studies.
Subject(s)
Mutation , Neoplasms/genetics , Protein Structure, Tertiary/genetics , Proteins/genetics , Databases, Protein , Disease/genetics , Humans , Proteins/chemistryABSTRACT
UNLABELLED: Domain mapping of disease mutations (DMDM) is a database in which each disease mutation can be displayed by its gene, protein or domain location. DMDM provides a unique domain-level view where all human coding mutations are mapped on the protein domain. To build DMDM, all human proteins were aligned to a database of conserved protein domains using a Hidden Markov Model-based sequence alignment tool (HMMer). The resulting protein-domain alignments were used to provide a domain location for all available human disease mutations and polymorphisms. The number of disease mutations and polymorphisms in each domain position are displayed alongside other relevant functional information (e.g. the binding and catalytic activity of the site and the conservation of that domain location). DMDM's protein domain view highlights molecular relationships among mutations from different diseases that might not be clearly observed with traditional gene-centric visualization tools. AVAILABILITY: Freely available at http://bioinf.umbc.edu/dmdm.