OBJECTIVE: To evaluate if a single-subject study (S3) design, utilizing paired transcriptome samples from the same patient (eg, "sepsis" vs "recovered"), can replicate transcriptomic signatures from small case-control studies, addressing challenges in patient accrual for rare or sub-stratified diseases. METHODS: We generated a sepsis gene signature (SGS) comprising 300 differentially expressed genes (DEGs; FDR < 5%) from a human sepsis case-control cohort using general linear models (GLMs). Reproducibility of SGS was assessed through three approaches applied to sub-sampled independent datasets: single-subject analyses (N-of-1-MixEnrich), anticipated to perform better; conventional paired-sample GLM analyses; and a traditional case-control GLM analysis. RESULTS: SGS reproducibility in GLM analyses was inconsistent at smaller cohort sizes (∼80% reproducibility; n = 5) but stabilized at cohort sizes >6. Remarkably, the single-subject-study approach consistently reproduced SGS in each of the 18 subjects individually (100% reproducibility; n = 1). DISCUSSION: Conventional GLMs are not designed for single-subject or small cohort analyses due to their dependence on larger samples to mitigate variable dispersion and human heterogeneity. In contrast, S3 methods enhance statistical power by: reducing multiple testing through gene set aggregation, emphasizing concordant changes in pathway activity rather than exact molecular consistency, and exploiting paired samples from the same individual. CONCLUSION: This proof-of-concept demonstrates that S3 designs effectively validate gene expression signatures derived from case-control studies, highlighting their potential in research or clinical trials constrained by small sample sizes. However, further validation and computational simulation are needed to demonstrate scalability to other conditions and sensitivity to validation subject variations from the "average subject" of discovery cohorts.

MOTIVATION: Identifying altered transcripts between very small human cohorts is particularly challenging and is compounded by the low accrual rate of human subjects in rare diseases or sub-stratified common disorders. Yet, single-subject studies (S3) can compare paired transcriptome samples drawn from the same patient under two conditions (e.g. treated versus pre-treatment) and suggest patient-specific responsive biomechanisms based on the overrepresentation of functionally defined gene sets. These improve statistical power by: (i) reducing the total features tested and (ii) relaxing the requirement of within-cohort uniformity at the transcript level. We propose Inter-N-of-1, a novel method, to identify meaningful differences between very small cohorts by using the effect size of 'single-subject-study'-derived responsive biological mechanisms. RESULTS: In each subject, Inter-N-of-1 requires applying previously published S3-type N-of-1-pathways MixEnrich to two paired samples (e.g. diseased versus unaffected tissues) for determining patient-specific enriched genes sets: Odds Ratios (S3-OR) and S3-variance using Gene Ontology Biological Processes. To evaluate small cohorts, we calculated the precision and recall of Inter-N-of-1 and that of a control method (GLM+EGS) when comparing two cohorts of decreasing sizes (from 20 versus 20 to 2 versus 2) in a comprehensive six-parameter simulation and in a proof-of-concept clinical dataset. In simulations, the Inter-N-of-1 median precision and recall are > 90% and >75% in cohorts of 3 versus 3 distinct subjects (regardless of the parameter values), whereas conventional methods outperform Inter-N-of-1 at sample sizes 9 versus 9 and larger. Similar results were obtained in the clinical proof-of-concept dataset. AVAILABILITY AND IMPLEMENTATION: R software is available at Lussierlab.net/BSSD.

BACKGROUND: In this era of data science-driven bioinformatics, machine learning research has focused on feature selection as users want more interpretation and post-hoc analyses for biomarker detection. However, when there are more features (i.e., transcripts) than samples (i.e., mice or human samples) in a study, it poses major statistical challenges in biomarker detection tasks as traditional statistical techniques are underpowered in high dimension. Second and third order interactions of these features pose a substantial combinatoric dimensional challenge. In computational biology, random forest (RF) classifiers are widely used due to their flexibility, powerful performance, their ability to rank features, and their robustness to the "P > > N" high-dimensional limitation that many matrix regression algorithms face. We propose binomialRF, a feature selection technique in RFs that provides an alternative interpretation for features using a correlated binomial distribution and scales efficiently to analyze multiway interactions. RESULTS: In both simulations and validation studies using datasets from the TCGA and UCI repositories, binomialRF showed computational gains (up to 5 to 300 times faster) while maintaining competitive variable precision and recall in identifying biomarkers' main effects and interactions. In two clinical studies, the binomialRF algorithm prioritizes previously-published relevant pathological molecular mechanisms (features) with high classification precision and recall using features alone, as well as with their statistical interactions alone. CONCLUSION: binomialRF extends upon previous methods for identifying interpretable features in RFs and brings them together under a correlated binomial distribution to create an efficient hypothesis testing algorithm that identifies biomarkers' main effects and interactions. Preliminary results in simulations demonstrate computational gains while retaining competitive model selection and classification accuracies. Future work will extend this framework to incorporate ontologies that provide pathway-level feature selection from gene expression input data.

An amendment to this paper has been published and can be accessed via the original article.

The development of computational methods capable of analyzing -omics data at the individual level is critical for the success of precision medicine. Although unprecedented opportunities now exist to gather data on an individual's -omics profile ('personalome'), interpreting and extracting meaningful information from single-subject -omics remain underdeveloped, particularly for quantitative non-sequence measurements, including complete transcriptome or proteome expression and metabolite abundance. Conventional bioinformatics approaches have largely been designed for making population-level inferences about 'average' disease processes; thus, they may not adequately capture and describe individual variability. Novel approaches intended to exploit a variety of -omics data are required for identifying individualized signals for meaningful interpretation. In this review-intended for biomedical researchers, computational biologists and bioinformaticians-we survey emerging computational and translational informatics methods capable of constructing a single subject's 'personalome' for predicting clinical outcomes or therapeutic responses, with an emphasis on methods that provide interpretable readouts. Key points: (i) the single-subject analytics of the transcriptome shows the greatest development to date and, (ii) the methods were all validated in simulations, cross-validations or independent retrospective data sets. This survey uncovers a growing field that offers numerous opportunities for the development of novel validation methods and opens the door for future studies focusing on the interpretation of comprehensive 'personalomes' through the integration of multiple -omics, providing valuable insights into individual patient outcomes and treatments.

OBJECTIVE: To introduce a disease prognosis framework enabled by a robust classification scheme derived from patient-specific transcriptomic response to stimulation. MATERIALS AND METHODS: Within an illustrative case study to predict asthma exacerbation, we designed a stimulation assay that reveals individualized transcriptomic response to human rhinovirus. Gene expression from peripheral blood mononuclear cells was quantified from 23 pediatric asthmatic patients and stimulated in vitro with human rhinovirus. Responses were obtained via the single-subject gene set testing methodology "N-of-1-pathways." The classifier was trained on a related independent training dataset (n = 19). Novel visualizations of personal transcriptomic responses are provided. RESULTS: Of the 23 pediatric asthmatic patients, 12 experienced recurrent exacerbations. Our classifier, using individualized responses and trained on an independent dataset, obtained 74% accuracy (area under the receiver operating curve of 71%; 2-sided P = .039). Conventional classifiers using messenger RNA (mRNA) expression within the viral-exposed samples were unsuccessful (all patients predicted to have recurrent exacerbations; accuracy of 52%). DISCUSSION: Prognosis based on single time point, static mRNA expression alone neglects the importance of dynamic genome-by-environment interplay in phenotypic presentation. Individualized transcriptomic response quantified at the pathway (gene sets) level reveals interpretable signals related to clinical outcomes. CONCLUSION: The proposed framework provides an innovative approach to precision medicine. We show that quantifying personal pathway-level transcriptomic response to a disease-relevant environmental challenge predicts disease progression. This genome-by-environment interaction assay offers a noninvasive opportunity to translate omics data to clinical practice by improving the ability to predict disease exacerbation and increasing the potential to produce more effective treatment decisions.

MOTIVATION: As 'omics' biotechnologies accelerate the capability to contrast a myriad of molecular measurements from a single cell, they also exacerbate current analytical limitations for detecting meaningful single-cell dysregulations. Moreover, mRNA expression alone lacks functional interpretation, limiting opportunities for translation of single-cell transcriptomic insights to precision medicine. Lastly, most single-cell RNA-sequencing analytic approaches are not designed to investigate small populations of cells such as circulating tumor cells shed from solid tumors and isolated from patient blood samples. RESULTS: In response to these characteristics and limitations in current single-cell RNA-sequencing methodology, we introduce an analytic framework that models transcriptome dynamics through the analysis of aggregated cell-cell statistical distances within biomolecular pathways. Cell-cell statistical distances are calculated from pathway mRNA fold changes between two cells. Within an elaborate case study of circulating tumor cells derived from prostate cancer patients, we develop analytic methods of aggregated distances to identify five differentially expressed pathways associated to therapeutic resistance. Our aggregation analyses perform comparably with Gene Set Enrichment Analysis and better than differentially expressed genes followed by gene set enrichment. However, these methods were not designed to inform on differential pathway expression for a single cell. As such, our framework culminates with the novel aggregation method, cell-centric statistics (CCS). CCS quantifies the effect size and significance of differentially expressed pathways for a single cell of interest. Improved rose plots of differentially expressed pathways in each cell highlight the utility of CCS for therapeutic decision-making. AVAILABILITY AND IMPLEMENTATION: http://www.lussierlab.org/publications/CCS/ CONTACT: [email protected] or [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The conventional approach to personalized medicine relies on molecular data analytics across multiple patients. The path to precision medicine lies with molecular data analytics that can discover interpretable single-subject signals (N-of-1). We developed a global framework, N-of-1-pathways, for a mechanistic-anchored approach to single-subject gene expression data analysis. We previously employed a metric that could prioritize the statistical significance of a deregulated pathway in single subjects, however, it lacked in quantitative interpretability (e.g. the equivalent to a gene expression fold-change). RESULTS: In this study, we extend our previous approach with the application of statistical Mahalanobis distance (MD) to quantify personal pathway-level deregulation. We demonstrate that this approach, N-of-1-pathways Paired Samples MD (N-OF-1-PATHWAYS-MD), detects deregulated pathways (empirical simulations), while not inflating false-positive rate using a study with biological replicates. Finally, we establish that N-OF-1-PATHWAYS-MD scores are, biologically significant, clinically relevant and are predictive of breast cancer survival (P < 0.05, n = 80 invasive carcinoma; TCGA RNA-sequences). CONCLUSION: N-of-1-pathways MD provides a practical approach towards precision medicine. The method generates the magnitude and the biological significance of personal deregulated pathways results derived solely from the patient's transcriptome. These pathways offer the opportunities for deriving clinically actionable decisions that have the potential to complement the clinical interpretability of personal polymorphisms obtained from DNA acquired or inherited polymorphisms and mutations. In addition, it offers an opportunity for applicability to diseases in which DNA changes may not be relevant, and thus expand the 'interpretable 'omics' of single subjects (e.g. personalome). AVAILABILITY AND IMPLEMENTATION: http://www.lussierlab.net/publications/N-of-1-pathways.

In the United States, International Classification of Disease Clinical Modification (ICD-9-CM, the ninth revision) diagnosis codes are commonly used to identify patient cohorts and to conduct financial analyses related to disease. In October 2015, the healthcare system of the United States will transition to ICD-10-CM (the tenth revision) diagnosis codes. One challenge posed to clinical researchers and other analysts is conducting diagnosis-related queries across datasets containing both coding schemes. Further, healthcare administrators will manage growth, trends, and strategic planning with these dually-coded datasets. The majority of the ICD-9-CM to ICD-10-CM translations are complex and nonreciprocal, creating convoluted representations and meanings. Similarly, mapping back from ICD-10-CM to ICD-9-CM is equally complex, yet different from mapping forward, as relationships are likewise nonreciprocal. Indeed, 10 of the 21 top clinical categories are complex as 78% of their diagnosis codes are labeled as "convoluted" by our analyses. Analysis and research related to external causes of morbidity, injury, and poisoning will face the greatest challenges due to 41 745 (90%) convolutions and a decrease in the number of codes. We created a web portal tool and translation tables to list all ICD-9-CM diagnosis codes related to the specific input of ICD-10-CM diagnosis codes and their level of complexity: "identity" (reciprocal), "class-to-subclass," "subclass-to-class," "convoluted," or "no mapping." These tools provide guidance on ambiguous and complex translations to reveal where reports or analyses may be challenging to impossible.Web portal: http://www.lussierlab.org/transition-to-ICD9CM/Tables annotated with levels of translation complexity: http://www.lussierlab.org/publications/ICD10to9.

Reporting of hospital adverse events relies on Patient Safety Indicators (PSIs) using International Classification of Diseases, Ninth Edition, Clinical Modification (ICD-9-CM) codes. The US transition to ICD-10-CM in 2015 could result in erroneous comparisons of PSIs. Using the General Equivalent Mappings (GEMs), we compared the accuracy of ICD-9-CM coded PSIs against recommended ICD-10-CM codes from the Centers for Medicaid/Medicare Services (CMS). We further predict their impact in a cohort of 38,644 patients (1,446,581 visits and 399 hospitals). We compared the predicted results to the published PSI related ICD-10-CM diagnosis codes. We provide the first report of substantial hospital safety reporting errors with five direct comparisons from the 23 types of PSIs (transfusion and anesthesia related PSIs). One PSI was excluded from the comparison between code sets due to reorganization, while 15 additional PSIs were inaccurate to a lesser degree due to the complexity of the coding translation. The ICD-10-CM translations proposed by CMS pose impending risks for (1) comparing safety incidents, (2) inflating the number of PSIs, and (3) increasing the variability of calculations attributable to the abundance of coding system translations. Ethical organizations addressing 'data-, process-, and system-focused' improvements could be penalized using the new ICD-10-CM Agency for Healthcare Research and Quality PSIs because of apparent increases in PSIs bearing the same PSI identifier and label, yet calculated differently. Here we investigate which PSIs would reliably transition between ICD-9-CM and ICD-10-CM, and those at risk of under-reporting and over-reporting adverse events while the frequency of these adverse events remain unchanged.

BACKGROUND: Understanding individual patient host-response to viruses is key to designing optimal personalized therapy. Unsurprisingly, in vivo human experimentation to understand individualized dynamic response of the transcriptome to viruses are rarely studied because of the obvious limitations stemming from ethical considerations of the clinical risk. OBJECTIVE: In this rhinovirus study, we first hypothesized that ex vivo human cells response to virus can serve as a proxy for otherwise controversial in vivo human experimentation. We further hypothesized that the N-of-1-pathways framework, previously validated in cancer, can be effective in understanding the more subtle individual transcriptomic response to viral infection. METHOD: N-of-1-pathways computes a significance score for a given list of gene sets at the patient level, using merely the 'omics profiles of two paired samples as input. We extracted the peripheral blood mononuclear cells (PBMC) of four human subjects, aliquoted in two paired samples, one subjected to ex vivo rhinovirus infection. Their dysregulated genes and pathways were then compared to those of 9 human subjects prior and after intranasal inoculation in vivo with rhinovirus. Additionally, we developed the Similarity Venn Diagram, a novel visualization method that goes beyond conventional overlap to show the similarity between two sets of qualitative measures. RESULTS: We evaluated the individual N-of-1-pathways results using two established cohort-based methods: GSEA and enrichment of differentially expressed genes. Similarity Venn Diagrams and individual patient ROC curves illustrate and quantify that the in vivo dysregulation is recapitulated ex vivo both at the gene and pathway level (p-values⩽0.004). CONCLUSION: We established the first evidence that an interpretable dynamic transcriptome metric, conducted as an ex vivo assays for a single subject, has the potential to predict individualized response to infectious disease without the clinical risks otherwise associated to in vivo challenges. These results serve as a foundational work for personalized "virograms".

The causal and interplay mechanisms of Single Nucleotide Polymorphisms (SNPs) associated with complex diseases (complex disease SNPs) investigated in genome-wide association studies (GWAS) at the transcriptional level (mRNA) are poorly understood despite recent advancements such as discoveries reported in the Encyclopedia of DNA Elements (ENCODE) and Genotype-Tissue Expression (GTex). Protein interaction network analyses have successfully improved our understanding of both single gene diseases (Mendelian diseases) and complex diseases. Whether the mRNAs downstream of complex disease genes are central or peripheral in the genetic information flow relating DNA to mRNA remains unclear and may be disease-specific. Using expression Quantitative Trait Loci (eQTL) that provide DNA to mRNA associations and network centrality metrics, we hypothesize that we can unveil the systems properties of information flow between SNPs and the transcriptomes of complex diseases. We compare different conditions such as naïve SNP assignments and stringent linkage disequilibrium (LD) free assignments for transcripts to remove confounders from LD. Additionally, we compare the results from eQTL networks between lymphoblastoid cell lines and liver tissue. Empirical permutation resampling (p<0.001) and theoretic Mann-Whitney U test (p<10(-30)) statistics indicate that mRNAs corresponding to complex disease SNPs via eQTL associations are likely to be regulated by a larger number of SNPs than expected. We name this novel property mRNA hubness in eQTL networks, and further term mRNAs with high hubness as master integrators. mRNA master integrators receive and coordinate the perturbation signals from large numbers of polymorphisms and respond to the personal genetic architecture integratively. This genetic signal integration contrasts with the mechanism underlying some Mendelian diseases, where a genetic polymorphism affecting a single protein hub produces a divergent signal that affects a large number of downstream proteins. Indeed, we verify that this property is independent of the hubness in protein networks for which these mRNAs are transcribed. Our findings provide novel insights into the pleiotropy of mRNAs targeted by complex disease polymorphisms and the architecture of the information flow between the genetic polymorphisms and transcriptomes of complex diseases.

Presents an introductory editorial on the special issue for this issue of the publication which examines the fields of biomedical and health informatics.

Barbara Di Eugenio, Andrew Boyd, Camillo Lugaresi, Abhinaya Balasubramanian, Gail Keenan, Mike Burton, Tamara Goncalves Rezende Macieira, Jianrong Li, Yves Lussier, Yves Lussier. Proceedings of the 8th International Natural Language Generation Conference (INLG). 2014.

UNLABELLED: Collecting data from large studies on high-throughput platforms, such as microarray or next-generation sequencing, typically requires processing samples in batches. There are often systematic but unpredictable biases from batch-to-batch, so proper randomization of biologically relevant traits across batches is crucial for distinguishing true biological differences from experimental artifacts. When a large number of traits are biologically relevant, as is common for clinical studies of patients with varying sex, age, genotype and medical background, proper randomization can be extremely difficult to prepare by hand, especially because traits may affect biological inferences, such as differential expression, in a combinatorial manner. Here we present ARTS (automated randomization of multiple traits for study design), which aids researchers in study design by automatically optimizing batch assignment for any number of samples, any number of traits and any batch size. AVAILABILITY AND IMPLEMENTATION: ARTS is implemented in Perl and is available at github.com/mmaiensc/ARTS. ARTS is also available in the Galaxy Tool Shed, and can be used at the Galaxy installation hosted by the UIC Center for Research Informatics (CRI) at galaxy.cri.uic.edu.

BACKGROUND: The emergence of precision medicine allowed the incorporation of individual molecular data into patient care. Indeed, DNA sequencing predicts somatic mutations in individual patients. However, these genetic features overlook dynamic epigenetic and phenotypic response to therapy. Meanwhile, accurate personal transcriptome interpretation remains an unmet challenge. Further, N-of-1 (single-subject) efficacy trials are increasingly pursued, but are underpowered for molecular marker discovery. METHOD: 'N-of-1-pathways' is a global framework relying on three principles: (i) the statistical universe is a single patient; (ii) significance is derived from geneset/biomodules powered by paired samples from the same patient; and (iii) similarity between genesets/biomodules assesses commonality and differences, within-study and cross-studies. Thus, patient gene-level profiles are transformed into deregulated pathways. From RNA-Seq of 55 lung adenocarcinoma patients, N-of-1-pathways predicts the deregulated pathways of each patient. RESULTS: Cross-patient N-of-1-pathways obtains comparable results with conventional genesets enrichment analysis (GSEA) and differentially expressed gene (DEG) enrichment, validated in three external evaluations. Moreover, heatmap and star plots highlight both individual and shared mechanisms ranging from molecular to organ-systems levels (eg, DNA repair, signaling, immune response). Patients were ranked based on the similarity of their deregulated mechanisms to those of an independent gold standard, generating unsupervised clusters of diametric extreme survival phenotypes (p=0.03). CONCLUSIONS: The N-of-1-pathways framework provides a robust statistical and relevant biological interpretation of individual disease-free survival that is often overlooked in conventional cross-patient studies. It enables mechanism-level classifiers with smaller cohorts as well as N-of-1 studies. SOFTWARE: http://lussierlab.org/publications/N-of-1-pathways.

OBJECTIVE: Applying the science of networks to quantify the discriminatory impact of the ICD-9-CM to ICD-10-CM transition between clinical specialties. MATERIALS AND METHODS: Datasets were the Center for Medicaid and Medicare Services ICD-9-CM to ICD-10-CM mapping files, general equivalence mappings, and statewide Medicaid emergency department billing. Diagnoses were represented as nodes and their mappings as directional relationships. The complex network was synthesized as an aggregate of simpler motifs and tabulation per clinical specialty. RESULTS: We identified five mapping motif categories: identity, class-to-subclass, subclass-to-class, convoluted, and no mapping. Convoluted mappings indicate that multiple ICD-9-CM and ICD-10-CM codes share complex, entangled, and non-reciprocal mappings. The proportions of convoluted diagnoses mappings (36% overall) range from 5% (hematology) to 60% (obstetrics and injuries). In a case study of 24 008 patient visits in 217 emergency departments, 27% of the costs are associated with convoluted diagnoses, with 'abdominal pain' and 'gastroenteritis' accounting for approximately 3.5%. DISCUSSION: Previous qualitative studies report that administrators and clinicians are likely to be challenged in understanding and managing their practice because of the ICD-10-CM transition. We substantiate the complexity of this transition with a thorough quantitative summary per clinical specialty, a case study, and the tools to apply this methodology easily to any clinical practice in the form of a web portal and analytic tables. CONCLUSIONS: Post-transition, successful management of frequent diseases with convoluted mapping network patterns is critical. The http://lussierlab.org/transition-to-ICD10CM web portal provides insight in linking onerous diseases to the ICD-10 transition.

BACKGROUND: While genome-wide association studies (GWAS) of complex traits have revealed thousands of reproducible genetic associations to date, these loci collectively confer very little of the heritability of their respective diseases and, in general, have contributed little to our understanding the underlying disease biology. Physical protein interactions have been utilized to increase our understanding of human Mendelian disease loci but have yet to be fully exploited for complex traits. METHODS: We hypothesized that protein interaction modeling of GWAS findings could highlight important disease-associated loci and unveil the role of their network topology in the genetic architecture of diseases with complex inheritance. RESULTS: Network modeling of proteins associated with the intragenic single nucleotide polymorphisms of the National Human Genome Research Institute catalog of complex trait GWAS revealed that complex trait associated loci are more likely to be hub and bottleneck genes in available, albeit incomplete, networks (OR=1.59, Fisher's exact test p < 2.24 × 10(-12)). Network modeling also prioritized novel type 2 diabetes (T2D) genetic variations from the Finland-USA Investigation of Non-Insulin-Dependent Diabetes Mellitus Genetics and the Wellcome Trust GWAS data, and demonstrated the enrichment of hubs and bottlenecks in prioritized T2D GWAS genes. The potential biological relevance of the T2D hub and bottleneck genes was revealed by their increased number of first degree protein interactions with known T2D genes according to several independent sources (p<0.01, probability of being first interactors of known T2D genes). CONCLUSION: Virtually all common diseases are complex human traits, and thus the topological centrality in protein networks of complex trait genes has implications in genetics, personal genomics, and therapy.

OBJECTIVE: 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. METHODS: 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. RESULTS: 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<2.2×10(-16)). Further, 'cancer traits' were similar to one another, as were 'metabolic syndrome traits' (Fisher's exact test p=0.001 and 3.5×10(-7), respectively). CONCLUSION: 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.

MicroRNAs, small non-coding RNAs, may act as tumor suppressors or oncogenes, and each regulate their own transcription and that of hundreds of genes, often in a tissue-dependent manner. This creates a tightly interwoven network regulating and underlying oncogenesis and cancer biology. Although protein-coding gene signatures and single protein pathway markers have proliferated over the past decade, routine adoption of the former has been hampered by interpretability, reproducibility, and dimensionality, whereas the single molecule-phenotype reductionism of the latter is often overly simplistic to account for complex phenotypes. MicroRNA-derived biomarkers offer a powerful alternative; they have both the flexibility of gene expression signature classifiers and the desirable mechanistic transparency of single protein biomarkers. Furthermore, several advances have recently demonstrated the robust detection of microRNAs from various biofluids, thus providing an additional opportunity for obtaining bioinformatically derived biomarkers to accelerate the identification of individual patients for personalized therapy.

OBJECTIVE: 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. MATERIALS AND METHODS: 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. RESULTS: 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). DISCUSSION: 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). CONCLUSION: 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.

Gene expression signatures that are predictive of therapeutic response or prognosis are increasingly useful in clinical care; however, mechanistic (and intuitive) interpretation of expression arrays remains an unmet challenge. Additionally, there is surprisingly little gene overlap among distinct clinically validated expression signatures. These "causality challenges" hinder the adoption of signatures as compared to functionally well-characterized single gene biomarkers. To increase the utility of multi-gene signatures in survival studies, we developed a novel approach to generate "personal mechanism signatures" of molecular pathways and functions from gene expression arrays. FAIME, the Functional Analysis of Individual Microarray Expression, computes mechanism scores using rank-weighted gene expression of an individual sample. By comparing head and neck squamous cell carcinoma (HNSCC) samples with non-tumor control tissues, the precision and recall of deregulated FAIME-derived mechanisms of pathways and molecular functions are comparable to those produced by conventional cohort-wide methods (e.g. GSEA). The overlap of "Oncogenic FAIME Features of HNSCC" (statistically significant and differentially regulated FAIME-derived genesets representing GO functions or KEGG pathways derived from HNSCC tissue) among three distinct HNSCC datasets (pathways:46%, p<0.001) is more significant than the gene overlap (genes:4%). These Oncogenic FAIME Features of HNSCC can accurately discriminate tumors from control tissues in two additional HNSCC datasets (n = 35 and 91, F-accuracy = 100% and 97%, empirical p<0.001, area under the receiver operating characteristic curves = 99% and 92%), and stratify recurrence-free survival in patients from two independent studies (p = 0.0018 and p = 0.032, log-rank). Previous approaches depending on group assignment of individual samples before selecting features or learning a classifier are limited by design to discrete-class prediction. In contrast, FAIME calculates mechanism profiles for individual patients without requiring group assignment in validation sets. FAIME is more amenable for clinical deployment since it translates the gene-level measurements of each given sample into pathways and molecular function profiles that can be applied to analyze continuous phenotypes in clinical outcome studies (e.g. survival time, tumor volume).

Natural Language Processing (NLP) in the medical field has the potential to dramatically influence the way in which everyday clinical care and medical research is conducted. NLP systems provide access to structured content embedded in raw medical texts, therefore enabling automated processing. There are however, several barriers prohibiting wide spread adoption of NLP technology primarily driven by the complexity and cost. This paper describes an approach and implementation which leverages cloud-based deployment and service-based interfaces to extract, process, synthesize, mine, compare/contrast, explore, and manage medical text data in a flexibly secure and scalable architecture. Through a virtual appliance architecture users are able to discover, deploy and utilize NLP engines on demand without requiring knowledge of the underlying, potentially complex, NLP engine. As highlighted in this paper, the system architecture can scale in several configurations: by increasing the number of instances deployed, the number of NLP engines, and the number of databases.

UNLABELLED: GO-Module is a web-accessible synthesis and visualization tool developed for end-user biologists to greatly simplify the interpretation of prioritized Gene Ontology (GO) terms. GO-Module radically reduces the complexity of raw GO results into compact biomodules in two distinct ways, by (i) constructing biomodules from significant GO terms based on hierarchical knowledge, and (ii) refining the GO terms in each biomodule to contain only true positive results. Altogether, the features (biomodules) of GO-Module outputs are better organized and on average four times smaller than the input GO terms list (P = 0.0005, n = 16). AVAILABILITY: http://lussierlab.org/GO-Module.

OBJECTIVE: Uncovering the dominant molecular deregulation among the multitude of pathways implicated in aggressive prostate cancer is essential to intelligently developing targeted therapies. Paradoxically, published prostate cancer gene expression signatures of poor prognosis share little overlap and thus do not reveal shared mechanisms. The authors hypothesize that, by analyzing gene signatures with quantitative models of protein-protein interactions, key pathways will be elucidated and shown to be shared. DESIGN: The authors statistically prioritized common interactors between established cancer genes and genes from each prostate cancer signature of poor prognosis independently via a previously validated single protein analysis of network (SPAN) methodology. Additionally, they computationally identified pathways among the aggregated interactors across signatures and validated them using a similarity metric and patient survival. MEASUREMENT: Using an information-theoretic metric, the authors assessed the mechanistic similarity of the interactor signature. Its prognostic ability was assessed in an independent cohort of 198 patients with high-Gleason prostate cancer using Kaplan-Meier analysis. RESULTS: Of the 13 prostate cancer signatures that were evaluated, eight interacted significantly with established cancer genes (false discovery rate <5%) and generated a 42-gene interactor signature that showed the highest mechanistic similarity (p<0.0001). Via parameter-free unsupervised classification, the interactor signature dichotomized the independent prostate cancer cohort with a significant survival difference (p=0.009). Interpretation of the network not only recapitulated phosphatidylinositol-3 kinase/NF-κB signaling, but also highlighted less well established relevant pathways such as the Janus kinase 2 cascade. CONCLUSIONS: SPAN methodology provides a robust means of abstracting disparate prostate cancer gene expression signatures into clinically useful, prioritized pathways as well as useful mechanistic pathways.

Nearly a decade since the completion of the first draft of the human genome, the biomedical community is positioned to usher in a new era of scientific inquiry that links fundamental biological insights with clinical knowledge. Accordingly, holistic approaches are needed to develop and assess hypotheses that incorporate genotypic, phenotypic, and environmental knowledge. This perspective presents translational bioinformatics as a discipline that builds on the successes of bioinformatics and health informatics for the study of complex diseases. The early successes of translational bioinformatics are indicative of the potential to achieve the promise of the Human Genome Project for gaining deeper insights to the genetic underpinnings of disease and progress toward the development of a new generation of therapies.

BACKGROUND: Mouse xenograft models, in which human cancer cells are implanted in immune-suppressed mice, have been popular for studying the mechanisms of novel therapeutic targets, tumor progression and metastasis. We hypothesized that we could exploit the interspecies genetic differences in these experiments. Our purpose is to elucidate stromal microenvironment signals from probes on human arrays unintentionally cross-hybridizing with mouse homologous genes in xenograft tumor models. RESULTS: By identifying cross-species hybridizing probes from sequence alignment and cross-species hybridization experiment for the human whole-genome arrays, deregulated stromal genes can be identified and then their biological significance were predicted from enrichment studies. Comparing these results with those found by the laser capture microdissection of stromal cells from tumor specimens resulted in the discovery of significantly enriched stromal biological processes. CONCLUSIONS: Using this method, in addition to their primary endpoints, researchers can leverage xenograft experiments to better characterize the tumor microenvironment without additional costs. The Xhyb probes and R script are available at http://www.lussierlab.org/publications/Stroma.

Characterizing the biomolecular systems' properties underpinning prognosis signatures derived from gene expression profiles remains a key clinical and biological challenge. In breast cancer, while different "poor-prognosis" sets of genes have predicted patient survival outcome equally well in independent cohorts, these prognostic signatures have surprisingly little genetic overlap. We examine 10 such published expression-based signatures that are predictors or distinct breast cancer phenotypes, uncover their mechanistic interconnectivity through a protein-protein interaction network, and introduce a novel cross-"gene expression signature" analysis method using (i) domain knowledge to constrain multiple comparisons in a mechanistically relevant single-gene network interactions and (ii) scale-free permutation re-sampling to statistically control for hubness (SPAN - Single Protein Analysis of Network with constant node degree per protein). At adjusted p-values<5%, 54-genes thus identified have a significantly greater connectivity than those through meticulous permutation re-sampling of the context-constrained network. More importantly, eight of 10 genetically non-overlapping signatures are connected through well-established mechanisms of breast cancer oncogenesis and progression. Gene Ontology enrichment studies demonstrate common markers of cell cycle regulation. Kaplan-Meier analysis of three independent historical gene expression sets confirms this network-signature's inherent ability to identify "poor outcome" in ER(+) patients without the requirement of machine learning. We provide a novel demonstration that genetically distinct prognosis signatures, developed from independent clinical datasets, occupy overlapping prognostic space of breast cancer via shared mechanisms that are mediated by genetically different yet mechanistically comparable interactions among proteins of differentially expressed genes in the signatures. This is the first study employing a networks' approach to aggregate established gene expression signatures in order to develop a phenotype/pathway-based cancer roadmap with the potential for (i) novel drug development applications and for (ii) facilitating the clinical deployment of prognostic gene signatures with improved mechanistic understanding of biological processes and functions associated with gene expression changes. http://www.lussierlab.org/publication/networksignature/.

Due to the large number of putative microRNA gene targets predicted by sequence-alignment databases and the relative low accuracy of such predictions which are conducted independently of biological context by design, systematic experimental identification and validation of every functional microRNA target is currently challenging. Consequently, biological studies have yet to identify, on a genome scale, key regulatory networks perturbed by altered microRNA functions in the context of cancer. In this report, we demonstrate for the first time how phenotypic knowledge of inheritable cancer traits and of risk factor loci can be utilized jointly with gene expression analysis to efficiently prioritize deregulated microRNAs for biological characterization. Using this approach we characterize miR-204 as a tumor suppressor microRNA and uncover previously unknown connections between microRNA regulation, network topology, and expression dynamics. Specifically, we validate 18 gene targets of miR-204 that show elevated mRNA expression and are enriched in biological processes associated with tumor progression in squamous cell carcinoma of the head and neck (HNSCC). We further demonstrate the enrichment of bottleneckness, a key molecular network topology, among miR-204 gene targets. Restoration of miR-204 function in HNSCC cell lines inhibits the expression of its functionally related gene targets, leads to the reduced adhesion, migration and invasion in vitro and attenuates experimental lung metastasis in vivo. As importantly, our investigation also provides experimental evidence linking the function of microRNAs that are located in the cancer-associated genomic regions (CAGRs) to the observed predisposition to human cancers. Specifically, we show miR-204 may serve as a tumor suppressor gene at the 9q21.1-22.3 CAGR locus, a well established risk factor locus in head and neck cancers for which tumor suppressor genes have not been identified. This new strategy that integrates expression profiling, genetics and novel computational biology approaches provides for improved efficiency in characterization and modeling of microRNA functions in cancer as compared to the state of art and is applicable to the investigation of microRNA functions in other biological processes and diseases.

BACKGROUND: To address the limitations of traditional virus and pathogen detection methodologies in clinical diagnosis, scientists have developed high-throughput oligonucleotide microarrays to rapidly identify infectious agents. However, objectively identifying pathogens from the complex hybridization patterns of these massively multiplexed arrays remains challenging. METHODS: In this study, we conceived an automated method based on the hypergeometric distribution for identifying pathogens in multiplexed arrays and compared it to five other methods. We evaluated these metrics: 1) accurate prediction, whether the top ranked prediction(s) match the real virus(es); 2) four accuracy scores. RESULTS: Though accurate prediction and high specificity and sensitivity can be achieved with several methods, the method based on hypergeometric distribution provides a significant advantage in term of positive predicting value with two to sixty folds the positive predicting values of other methods. CONCLUSION: The proposed multi-specie array analysis based on the hypergeometric distribution addresses shortcomings of previous methods by enhancing signals of positively hybridized probes.

The evolving complexity of genome-scale experiments has increasingly centralized the role of a highly computable, accurate, and comprehensive resource spanning multiple biological scales and viewpoints. To provide a resource to meet this need, we have significantly extended the PhenoGO database with gene-disease specific annotations and included an additional ten species. This a computationally-derived resource is primarily intended to provide phenotypic context (cell type, tissue, organ, and disease) for mining existing associations between gene products and GO terms specified in the Gene Ontology Databases Automated natural language processing (BioMedLEE) and computational ontology (PhenOS) methods were used to derive these relationships from the literature, expanding the database with information from ten additional species to include over 600,000 phenotypic contexts spanning eleven species from five GO annotation databases. A comprehensive evaluation evaluating the mappings (n = 300) found precision (positive predictive value) at 85%, and recall (sensitivity) at 76%. Phenotypes are encoded in general purpose ontologies such as Cell Ontology, the Unified Medical Language System, and in specialized ontologies such as the Mouse Anatomy and the Mammalian Phenotype Ontology. A web portal has also been developed, allowing for advanced filtering and querying of the database as well as download of the entire dataset http://www.phenogo.org.

BACKGROUND: Current outcome predictors based on "molecular profiling" rely on gene lists selected without consideration for their molecular mechanisms. This study was designed to demonstrate that we could learn about genes related to a specific mechanism and further use this knowledge to predict outcome in patients - a paradigm shift towards accurate "mechanism-anchored profiling". We propose a novel algorithm, PGnet, which predicts a tripartite mechanism-anchored network associated to epigenetic regulation consisting of phenotypes, genes and mechanisms. Genes termed as GEMs in this network meet all of the following criteria: (i) they are co-expressed with genes known to be involved in the biological mechanism of interest, (ii) they are also differentially expressed between distinct phenotypes relevant to the study, and (iii) as a biomodule, genes correlate with both the mechanism and the phenotype. RESULTS: This proof-of-concept study, which focuses on epigenetic mechanisms, was conducted in a well-studied set of 132 acute lymphoblastic leukemia (ALL) microarrays annotated with nine distinct phenotypes and three measures of response to therapy. We used established parametric and non parametric statistics to derive the PGnet tripartite network that consisted of 10 phenotypes and 33 significant clusters of GEMs comprising 535 distinct genes. The significance of PGnet was estimated from empirical p-values, and a robust subnetwork derived from ALL outcome data was produced by repeated random sampling. The evaluation of derived robust network to predict outcome (relapse of ALL) was significant (p = 3%), using one hundred three-fold cross-validations and the shrunken centroids classifier. CONCLUSION: To our knowledge, this is the first method predicting co-expression networks of genes associated with epigenetic mechanisms and to demonstrate its inherent capability to predict therapeutic outcome. This PGnet approach can be applied to any regulatory mechanisms including transcriptional or microRNA regulation in order to derive predictive molecular profiles that are mechanistically anchored. The implementation of PGnet in R is freely available at http://Lussierlab.org/publication/PGnet.

BACKGROUND: Biological data that are well-organized by an ontology, such as Gene Ontology, enables high-throughput availability of the semantic web. It can also be used to facilitate high throughput classification of biomedical information. However, to our knowledge, no evaluation has been published on automating classifications of human diseases genes using Gene Ontology. In this study, we evaluate automated classifications of well-defined human disease genes using their Gene Ontology annotations and compared them to a gold standard. This gold standard was independently conceived by Valle's research group, and contains 923 human disease genes organized in 14 categories of protein function. RESULTS: Two automated methods were applied to investigate the classification of human disease genes into independently pre-defined categories of protein function. One method used the structure of Gene Ontology by pre-selecting 74 Gene Ontology terms assigned to 11 protein function categories. The second method was based on the similarity of human disease genes clustered according to the information-theoretic distance of their Gene Ontology annotations. Compared to the categorization of human disease genes found in the gold standard, our automated methods can achieve an overall 56% and 47% precision with 62% and 71% recall respectively. However, approximately 15% of the studied human disease genes remain without GO annotations. CONCLUSION: Automated methods can recapitulate a significant portion of classification of the human disease genes. The method using information-theoretic distance performs slightly better on the precision with some loss in recall. For some protein function categories, such as 'hormone' and 'transcription factor', the automated methods perform particularly well, achieving precision and recall levels above 75%. In summary, this study demonstrates that for semantic webs, methods to automatically classify or analyze a majority of human disease genes require significant progress in both the Gene Ontology annotations and particularly in the utilization of these annotations.

OBJECTIVE: To characterize global structural features of large-scale biomedical terminologies using currently emerging statistical approaches. DESIGN: Given rapid growth of terminologies, this research was designed to address scalability. We selected 16 terminologies covering a variety of domains from the UMLS Metathesaurus, a collection of terminological systems. Each was modeled as a network in which nodes were atomic concepts and links were relationships asserted by the source vocabulary. For comparison against each terminology we created three random networks of equivalent size and density. MEASUREMENTS: Average node degree, node degree distribution, clustering coefficient, average path length. RESULTS: Eight of 16 terminologies exhibited the small-world characteristics of a short average path length and strong local clustering. An overlapping subset of nine exhibited a power law distribution in node degrees, indicative of a scale-free architecture. We attribute these features to specific design constraints. Constraints on node connectivity, common in more synthetic classification systems, localize the effects of changes and deletions. In contrast, small-world and scale-free features, common in comprehensive medical terminologies, promote flexible navigation and less restrictive organic-like growth. CONCLUSION: While thought of as synthetic, grid-like structures, some controlled terminologies are structurally indistinguishable from natural language networks. This paradoxical result suggests that terminology structure is shaped not only by formal logic-based semantics, but by rules analogous to those that govern social networks and biological systems. Graph theoretic modeling shows early promise as a framework for describing terminology structure. Deeper understanding of these techniques may inform the development of scalable terminologies and ontologies.

MOTIVATION: Natural language processing (NLP) techniques are increasingly being used in biology to automate the capture of new biological discoveries in text, which are being reported at a rapid rate. Yet, information represented in NLP data structures is classically very different from information organized with ontologies as found in model organisms or genetic databases. To facilitate the computational reuse and integration of information buried in unstructured text with that of genetic databases, we propose and evaluate a translational schema that represents a comprehensive set of phenotypic and genetic entities, as well as their closely related biomedical entities and relations as expressed in natural language. In addition, the schema connects different scales of biological information, and provides mappings from the textual information to existing ontologies, which are essential in biology for integration, organization, dissemination and knowledge management of heterogeneous phenotypic information. A common comprehensive representation for otherwise heterogeneous phenotypic and genetic datasets, such as the one proposed, is critical for advancing systems biology because it enables acquisition and reuse of unprecedented volumes of diverse types of knowledge and information from text. RESULTS: A novel representational schema, PGschema, was developed that enables translation of phenotypic, genetic and their closely related information found in textual narratives to a well-defined data structure comprising phenotypic and genetic concepts from established ontologies along with modifiers and relationships. Evaluation for coverage of a selected set of entities showed that 90% of the information could be represented (95% confidence interval: 86-93%; n = 268). Moreover, PGschema can be expressed automatically in an XML format using natural language techniques to process the text. To our knowledge, we are providing the first evaluation of a translational schema for NLP that contains declarative knowledge about genes and their associated biomedical data (e.g. phenotypes). AVAILABILITY: http://zellig.cpmc.columbia.edu/PGschema

With mounting availability of genomic and phenotypic databases, data integration and mining become increasingly challenging. While efforts have been put forward to analyze prokaryotic phenotypes, current computational technologies either lack high throughput capacity for genomic scale analysis, or are limited in their capability to integrate and mine data across different scales of biology. Consequently, simultaneous analysis of associations among genomes, phenotypes, and gene functions is prohibited. Here, we developed a high throughput computational approach, and demonstrated for the first time the feasibility of integrating large quantities of prokaryotic phenotypes along with genomic datasets for mining across multiple scales of biology (protein domains, pathways, molecular functions, and cellular processes). Applying this method over 59 fully sequenced prokaryotic species, we identified genetic basis and molecular mechanisms underlying the phenotypes in bacteria. We identified 3,711 significant correlations between 1,499 distinct Pfam and 63 phenotypes, with 2,650 correlations and 1,061 anti-correlations. Manual evaluation of a random sample of these significant correlations showed a minimal precision of 30% (95% confidence interval: 20%-42%; n = 50). We stratified the most significant 478 predictions and subjected 100 to manual evaluation, of which 60 were corroborated in the literature. We furthermore unveiled 10 significant correlations between phenotypes and KEGG pathways, eight of which were corroborated in the evaluation, and 309 significant correlations between phenotypes and 166 GO concepts evaluated using a random sample (minimal precision = 72%; 95% confidence interval: 60%-80%; n = 50). Additionally, we conducted a novel large-scale phenomic visualization analysis to provide insight into the modular nature of common molecular mechanisms spanning multiple biological scales and reused by related phenotypes (metaphenotypes). We propose that this method elucidates which classes of molecular mechanisms are associated with phenotypes or metaphenotypes and holds promise in facilitating a computable systems biology approach to genomic and biomedical research.

MOTIVATION: Visualizing relationships among biological information to facilitate understanding is crucial to biological research during the post-genomic era. Although different systems have been developed to view gene-phenotype relationships for specific databases, very few have been designed specifically as a general flexible tool for visualizing multidimensional genotypic and phenotypic information together. Our goal is to develop a method for visualizing multidimensional genotypic and phenotypic information and a model that unifies different biological databases in order to present the integrated knowledge using a uniform interface. RESULTS: We developed a novel, flexible and generalizable visualization tool, called PhenoGenesviewer (PGviewer), which in this paper was used to display gene-phenotype relationships from a human-curated database (OMIM) and from an automatic method using a Natural Language Processing tool called BioMedLEE. Data obtained from multiple databases were first integrated into a uniform structure and then organized by PGviewer. PGviewer provides a flexible query interface that allows dynamic selection and ordering of any desired dimension in the databases. Based on users' queries, results can be visualized using hierarchical expandable trees that present views specified by users according to their research interests. We believe that this method, which allows users to dynamically organize and visualize multiple dimensions, is a potentially powerful and promising tool that should substantially facilitate biological research. AVAILABILITY: PhenogenesViewer as well as its support and tutorial are available at http://www.dbmi.columbia.edu/pgviewer/ CONTACT: [email protected].

OBJECTIVE: The aim of this study was to develop a method based on natural language processing (NLP) that automatically maps an entire clinical document to codes with modifiers and to quantitatively evaluate the method. METHODS: An existing NLP system, MedLEE, was adapted to automatically generate codes. The method involves matching of structured output generated by MedLEE consisting of findings and modifiers to obtain the most specific code. Recall and precision applied to Unified Medical Language System (UMLS) coding were evaluated in two separate studies. Recall was measured using a test set of 150 randomly selected sentences, which were processed using MedLEE. Results were compared with a reference standard determined manually by seven experts. Precision was measured using a second test set of 150 randomly selected sentences from which UMLS codes were automatically generated by the method and then validated by experts. RESULTS: Recall of the system for UMLS coding of all terms was .77 (95% CI.72-.81), and for coding terms that had corresponding UMLS codes recall was .83 (.79-.87). Recall of the system for extracting all terms was .84 (.81-.88). Recall of the experts ranged from .69 to .91 for extracting terms. The precision of the system was .89 (.87-.91), and precision of the experts ranged from .61 to .91. CONCLUSION: Extraction of relevant clinical information and UMLS coding were accomplished using a method based on NLP. The method appeared to be comparable to or better than six experts. The advantage of the method is that it maps text to codes along with other related information, rendering the coded output suitable for effective retrieval.