Upon recognizing the importance of providing biomedical and behavioral researchers with algorithms, tools, and computational facilities that accelerate scientific discoveries, the NIH sponsored the creation of several National Centers for...]]>
The emergence of the field of biomedical computing captured the attention of the leadership of the NIH toward the end of the 1990s. NIH Director Harold Varmus named a working group of the Advisory Committee to the Director
Genome-wide association studies (GWAS) require high specificity and large numbers of subjects to identify genotype–phenotype correlations accurately. The aim of this study was to identify type 2 diabetes (T2D) cases and controls for a GWAS, using data captured through routine clinical care across five institutions using different electronic medical record (EMR) systems.
An algorithm was developed to identify T2D cases and controls based on a combination of diagnoses, medications, and laboratory results. The performance of the algorithm was validated at three of the five participating institutions compared against clinician review. A GWAS was subsequently performed using cases and controls identified by the algorithm, with samples pooled across all five institutions.
The algorithm achieved 98% and 100% positive predictive values for the identification of diabetic cases and controls, respectively, as compared against clinician review. By standardizing and applying the algorithm across institutions, 3353 cases and 3352 controls were identified. Subsequent GWAS using data from five institutions replicated the TCF7L2 gene variant (rs7903146) previously associated with T2D.
By applying stringent criteria to EMR data collected through routine clinical care, cases and controls for a GWAS were identified that subsequently replicated a known genetic variant. The use of standard terminologies to define data elements enabled pooling of subjects and data across five different institutions to achieve the robust numbers required for GWAS.
An algorithm using commonly available data from five different EMR can accurately identify T2D cases and controls for genetic study across multiple institutions.
To evaluate data fragmentation across healthcare centers with regard to the accuracy of a high-throughput clinical phenotyping (HTCP) algorithm developed to differentiate (1) patients with type 2 diabetes mellitus (T2DM) and (2) patients with no diabetes.
This population-based study identified all Olmsted County, Minnesota residents in 2007. We used provider-linked electronic medical record data from the two healthcare centers that provide >95% of all care to County residents (ie, Olmsted Medical Center and Mayo Clinic in Rochester, Minnesota, USA). Subjects were limited to residents with one or more encounter January 1, 2006 through December 31, 2007 at both healthcare centers. DM-relevant data on diagnoses, laboratory results, and medication from both centers were obtained during this period. The algorithm was first executed using data from both centers (ie, the gold standard) and then from Mayo Clinic alone. Positive predictive values and false-negative rates were calculated, and the McNemar test was used to compare categorization when data from the Mayo Clinic alone were used with the gold standard. Age and sex were compared between true-positive and false-negative subjects with T2DM. Statistical significance was accepted as p<0.05.
With data from both medical centers, 765 subjects with T2DM (4256 non-DM subjects) were identified. When single-center data were used, 252 T2DM subjects (1573 non-DM subjects) were missed; an additional false-positive 27 T2DM subjects (215 non-DM subjects) were identified. The positive predictive values and false-negative rates were 95.0% (513/540) and 32.9% (252/765), respectively, for T2DM subjects and 92.6% (2683/2898) and 37.0% (1573/4256), respectively, for non-DM subjects. Age and sex distribution differed between true-positive (mean age 62.1; 45% female) and false-negative (mean age 65.0; 56.0% female) T2DM subjects.
The findings show that application of an HTCP algorithm using data from a single medical center contributes to misclassification. These findings should be considered carefully by researchers when developing and executing HTCP algorithms.
There is increasing interest in using electronic health records (EHRs) to identify subjects for genomic association studies, due in part to the availability of large amounts of clinical data and the expected cost efficiencies of subject identification. We describe the construction and validation of an EHR-based algorithm to identify subjects with age-related cataracts.
We used a multi-modal strategy consisting of structured database querying, natural language processing on free-text documents, and optical character recognition on scanned clinical images to identify cataract subjects and related cataract attributes. Extensive validation on 3657 subjects compared the multi-modal results to manual chart review. The algorithm was also implemented at participating
An EHR-based cataract phenotyping algorithm was successfully developed and validated, resulting in positive predictive values (PPVs) >95%. The multi-modal approach increased the identification of cataract subject attributes by a factor of three compared to single-mode approaches while maintaining high PPV. Components of the cataract algorithm were successfully deployed at three other institutions with similar accuracy.
A multi-modal strategy incorporating optical character recognition and natural language processing may increase the number of cases identified while maintaining similar PPVs. Such algorithms, however, require that the needed information be embedded within clinical documents.
We have demonstrated that algorithms to identify and characterize cataracts can be developed utilizing data collected via the EHR. These algorithms provide a high level of accuracy even when implemented across multiple EHRs and institutional boundaries.
Current techniques for knowledge-based Word Sense Disambiguation (WSD) of ambiguous biomedical terms rely on relations in the Unified Medical Language System Metathesaurus but do not take into account the domain of the target documents. The authors' goal is to improve these methods by using information about the topic of the document in which the ambiguous term appears.
The authors proposed and implemented several methods to extract lists of key terms associated with Medical Subject Heading terms. These key terms are used to represent the document topic in a knowledge-based WSD system. They are applied both alone and in combination with local context.
A standard measure of accuracy was calculated over the set of target words in the widely used National Library of Medicine WSD dataset.
The authors report a significant improvement when combining those key terms with local context, showing that domain information improves the results of a WSD system based on the Unified Medical Language System Metathesaurus alone. The best results were obtained using key terms obtained by relevance feedback and weighted by inverse document frequency.
A complex disease is generally caused by the mutation of multiple genes or by the dysfunction of multiple biological processes. Systematic identification of causal disease genes and module biomarkers can provide insights into the mechanisms underlying complex diseases, and help develop efficient therapies or effective drugs.
In this paper, we present a novel approach to predict disease genes and identify dysfunctional networks or modules, based on the analysis of differential interactions between disease and control samples, in contrast to the analysis of differential gene or protein expressions widely adopted in existing methods.
As an example, we applied our method to the study of three-stage microarray data for gastric cancer. We identified network modules or module biomarkers that include a set of genes related to gastric cancer, implying the predictive power of our method. The results on holdout validation data sets show that our identified module can serve as an effective module biomarker for accurately detecting or diagnosing gastric cancer, thereby validating the efficiency of our method.
We proposed a new approach to detect module biomarkers for diseases, and the results on gastric cancer demonstrated that the differential interactions are useful to detect dysfunctional modules in the molecular interaction network, which in turn can be used as robust module biomarkers.
The relationship between diseases and their causative genes can be complex, especially in the case of polygenic diseases. Further exacerbating the challenges in their study is that many genes may be causally related to multiple diseases. This study explored the relationship between diseases through the adaptation of an approach pioneered in the context of information retrieval: vector space models.
A vector space model approach was developed that bridges gene disease knowledge inferred across three knowledge bases: Online Mendelian Inheritance in Man, GenBank, and Medline. The approach was then used to identify potentially related diseases for two target diseases: Alzheimer disease and Prader-Willi Syndrome.
In the case of both Alzheimer Disease and Prader-Willi Syndrome, a set of plausible diseases were identified that may warrant further exploration.
This study furthers seminal work by Swanson, et al. that demonstrated the potential for mining literature for putative correlations. Using a vector space modeling approach, information from both biomedical literature and genomic resources (like GenBank) can be combined towards identification of putative correlations of interest. To this end, the relevance of the predicted diseases of interest in this study using the vector space modeling approach were validated based on supporting literature.
The results of this study suggest that a vector space model approach may be a useful means to identify potential relationships between complex diseases, and thereby enable the coordination of gene-based findings across multiple complex diseases.
Renal transplantation has dramatically improved the survival rate of hemodialysis patients. However, with a growing proportion of marginal organs and improved immunosuppression, it is necessary to verify that the established allocation system, mostly based on human leukocyte antigen matching, still meets today's needs. The authors turn to machine-learning techniques to predict, from donor–recipient data, the estimated glomerular filtration rate (eGFR) of the recipient 1 year after transplantation.
The patient's eGFR was predicted using donor–recipient characteristics available at the time of transplantation. Donors' data were obtained from Eurotransplant's database, while recipients' details were retrieved from Charité Campus Virchow-Klinikum's database. A total of 707 renal transplantations from cadaveric donors were included.
Two separate datasets were created, taking features with <10% missing values for one and <50% missing values for the other. Four established regressors were run on both datasets, with and without feature selection.
The authors obtained a Pearson correlation coefficient between predicted and real eGFR (COR) of 0.48. The best model for the dataset was a Gaussian support vector machine with recursive feature elimination on the more inclusive dataset. All results are available at http://transplant.molgen.mpg.de/.
For now, missing values in the data must be predicted and filled in. The performance is not as high as hoped, but the dataset seems to be the main cause.
Predicting the outcome is possible with the dataset at hand (COR=0.48). Valuable features include age and creatinine levels of the donor, as well as sex and weight of the recipient.
Predictive models that generate individualized estimates for medically relevant outcomes are playing increasing roles in clinical care and translational research. However, current methods for calibrating these estimates lose valuable information. Our goal is to develop a new calibration method to conserve as much information as possible, and would compare favorably to existing methods in terms of important performance measures: discrimination and calibration.
We propose an adaptive technique that utilizes individualized confidence intervals (CIs) to calibrate predictions. We evaluate this new method, adaptive calibration of predictions (ACP), in artificial and real-world medical classification problems, in terms of areas under the ROC curves, the Hosmer-Lemeshow goodness-of-fit test, mean squared error, and computational complexity.
ACP compared favorably to other calibration methods such as binning, Platt scaling, and isotonic regression. In several experiments, binning, isotonic regression, and Platt scaling failed to improve the calibration of a logistic regression model, whereas ACP consistently improved the calibration while maintaining the same discrimination or even improving it in some experiments. In addition, the ACP algorithm is not computationally expensive.
The calculation of CIs for individual predictions may be cumbersome for certain predictive models. ACP is not completely parameter-free: the length of the CI employed may affect its results.
ACP can generate estimates that may be more suitable for individualized predictions than estimates that are calibrated using existing methods. Further studies are necessary to explore the limitations of ACP.
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.
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.
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.
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.
We demonstrate a genome-wide method for the integration of many studies of gene expression of phenotypically similar disease processes, a method of multiplex meta-analysis. We use immune dysfunction as an example disease process.
We use a heterogeneous collection of datasets across human and mice samples from a range of tissues and different forms of immunodeficiency. We developed a method integrating Tibshirani's modified t-test (SAM) is used to interrogate differential expression within a study and Fisher's method for omnibus meta-analysis to identify differentially expressed genes across studies. The ability of this overall gene expression profile to prioritize disease associated genes is evaluated by comparing against the results of a recent genome wide association study for common variable immunodeficiency (CVID).
Our approach is able to prioritize genes associated with immunodeficiency in general (area under the ROC curve = 0.713) and CVID in particular (area under the ROC curve = 0.643).
This approach may be used to investigate a larger range of failures of the immune system. Our method may be extended to other disease processes, using RNA levels to prioritize genes likely to contain disease associated DNA variants.
Since publication of the human genome in 2003, geneticists have been interested in risk variant associations to resolve the etiology of traits and complex diseases. The International HapMap Consortium undertook an effort to catalog all common variation across the genome (variants with a minor allele frequency (MAF) of at least 5% in one or more ethnic groups). HapMap along with advances in genotyping technology led to genome-wide association studies which have identified common variants associated with many traits and diseases. In 2008 the 1000 Genomes Project aimed to sequence 2500 individuals and identify rare variants and 99% of variants with a MAF of <1%.
To determine whether the 1000 Genomes Project includes all the variants in HapMap, we examined the overlap between single nucleotide polymorphisms (SNPs) genotyped in the two resources using merged phase II/III HapMap data and low coverage pilot data from 1000 Genomes.
Comparison of the two data sets showed that approximately 72% of HapMap SNPs were also found in 1000 Genomes Project pilot data. After filtering out HapMap variants with a MAF of <5% (separately for each population), 99% of HapMap SNPs were found in 1000 Genomes data.
Not all variants cataloged in HapMap are also cataloged in 1000 Genomes. This could affect decisions about which resource to use for SNP queries, rare variant validation, or imputation. Both the HapMap and 1000 Genomes Project databases are useful resources for human genetics, but it is important to understand the assumptions made and filtering strategies employed by these projects.
Thousands of complex-disease single-nucleotide polymorphisms (SNPs) have been discovered in genome-wide association studies (GWAS). However, these intragenic SNPs have not been collectively mined to unveil the genetic architecture between complex clinical traits. The authors hypothesize that biological annotations of host genes of trait-associated SNPs may reveal the biomolecular modularity across complex-disease traits and offer insights for drug repositioning.
Trait-to-polymorphism (SNPs) associations confirmed in GWAS were used. A novel method to quantify trait–trait similarity anchored in Gene Ontology annotations of human proteins and information theory was developed. The results were then validated with the shortest paths of physical protein interactions between biologically similar traits.
A network was constructed consisting of 280 significant intertrait similarities among 177 disease traits, which covered 1438 well-validated disease-associated SNPs. Thirty-nine percent of intertrait connections were confirmed by curators, and the following additional studies demonstrated the validity of a proportion of the remainder. On a phenotypic trait level, higher Gene Ontology similarity between proteins correlated with smaller ‘shortest distance’ in protein interaction networks of complexly inherited diseases (Spearman p<2.2x10–16). Further, ‘cancer traits’ were similar to one another, as were ‘metabolic syndrome traits’ (Fisher's exact test p=0.001 and 3.5x10–7, respectively).
An imputed disease network by information-anchored functional similarity from GWAS trait-associated SNPs is reported. It is also demonstrated that small shortest paths of protein interactions correlate with complex-disease function. Taken together, these findings provide the framework for investigating drug targets with unbiased functional biomolecular networks rather than worn-out single-gene and subjective canonical pathway approaches.
Although trait-associated genes identified as complex versus single-gene inheritance differ substantially in odds ratio, the authors nonetheless posit that their mechanistic concordance can reveal fundamental properties of the genetic architecture, allowing the automated interpretation of unique polymorphisms within a personal genome.
An analytical method, SPADE-gen, spanning three biological scales was developed to demonstrate the mechanistic concordance between Mendelian and complex inheritance of Alzheimer's disease (AD) genes: biological functions (BP), protein interaction modeling, and protein domain implicated in the disease-associated polymorphism.
Among Gene Ontology (GO) biological processes (BP) enriched at a false detection rate <5% in 15 AD genes of Mendelian inheritance (Online Mendelian Inheritance in Man) and independently in those of complex inheritance (25 host genes of intragenic AD single-nucleotide polymorphisms confirmed in genome-wide association studies), 16 overlapped (empirical p=0.007) and 45 were similar (empirical p<0.009; information theory). SPAN network modeling extended the canonical pathway of AD (KEGG) with 26 new protein interactions (empirical p<0.0001).
The study prioritized new AD-associated biological mechanisms and focused the analysis on previously unreported interactions associated with the biological processes of polymorphisms that affect specific protein domains within characterized AD genes and their direct interactors using (1) concordant GO-BP and (2) domain interactions within STRING protein–protein interactions corresponding to the genomic location of the AD polymorphism (eg, EPHA1, APOE, and CD2AP).
These results are in line with unique-event polymorphism theory, indicating how disease-associated polymorphisms of Mendelian or complex inheritance relate genetically to those observed as ‘unique personal variants’. They also provide insight for identifying novel targets, for repositioning drugs, and for personal therapeutics.
Morphologic variations of disease are often linked to underlying molecular events and patient outcome, suggesting that quantitative morphometric analysis may provide further insight into disease mechanisms. In this paper a methodology for the subclassification of disease is developed using image analysis techniques. Morphologic signatures that represent patient-specific tumor morphology are derived from the analysis of hundreds of millions of cells in digitized whole slide images. Clustering these signatures aggregates tumors into groups with cohesive morphologic characteristics. This methodology is demonstrated with an analysis of glioblastoma, using data from The Cancer Genome Atlas to identify a prognostically significant morphology-driven subclassification, in which clusters are correlated with transcriptional, genetic, and epigenetic events.
Methodology was applied to 162 glioblastomas from The Cancer Genome Atlas to identify morphology-driven clusters and their clinical and molecular correlates. Signatures of patient-specific tumor morphology were generated from analysis of 200 million cells in 462 whole slide images. Morphology-driven clusters were interrogated for associations with patient outcome, response to therapy, molecular classifications, and genetic alterations. An additional layer of deep, genome-wide analysis identified characteristic transcriptional, epigenetic, and copy number variation events.
Analysis of glioblastoma identified three prognostically significant patient clusters (median survival 15.3, 10.7, and 13.0 months, log rank p=1.4e-3). Clustering results were validated in a separate dataset. Clusters were characterized by molecular events in nuclear compartment signaling including developmental and cell cycle checkpoint pathways. This analysis demonstrates the potential of high-throughput morphometrics for the subclassification of disease, establishing an approach that complements genomics.
We completed the roll-out of our rebranding effort with a new logo and a web site that has greatly increased functionality, a modern look, and...]]>