Large-Scale Discovery of Disease-Disease and Disease-Gene Associations
Electronic Health Records
Genetic Diseases, Inborn
Genetic Predisposition to Disease
Genome-Wide Association Study
Permanent link to this recordhttp://hdl.handle.net/20.500.12613/5028
MetadataShow full item record
Abstract© 2016 The Author(s). Data-driven phenotype analyses on Electronic Health Record (EHR) data have recently drawn benefits across many areas of clinical practice, uncovering new links in the medical sciences that can potentially affect the well-being of millions of patients. In this paper, EHR data is used to discover novel relationships between diseases by studying their comorbidities (co-occurrences in patients). A novel embedding model is designed to extract knowledge from disease comorbidities by learning from a large-scale EHR database comprising more than 35 million inpatient cases spanning nearly a decade, revealing significant improvements on disease phenotyping over current computational approaches. In addition, the use of the proposed methodology is extended to discover novel disease-gene associations by including valuable domain knowledge from genome-wide association studies. To evaluate our approach, its effectiveness is compared against a held-out set where, again, it revealed very compelling results. For selected diseases, we further identify candidate gene lists for which disease-gene associations were not studied previously. Thus, our approach provides biomedical researchers with new tools to filter genes of interest, thus, reducing costly lab studies.
Citation to related workSpringer Science and Business Media LLC
Has partScientific Reports
ADA complianceFor Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact email@example.com
Showing items related by title, author, creator and subject.
Continuing trastuzumab beyond disease progression: Outcomes analysis in patients with metastatic breast cancerCancello, G; Montagna, E; D'Agostino, D; Giuliano, M; Giordano, A; Di Lorenzo, G; Plaitano, M; De Placido, S; De Laurentiis, M; Giordano, Antonio|0000-0002-5959-016X (2008-07-16)Introduction: We performed a retrospective analysis of HER2-overexpressing metastatic breast cancer patients to describe clinical outcomes of those who, despite progression of the disease (PD), maintained trastuzumab for multiple chemotherapy lines. We also compared survival of these patients with that of those who halted trastuzumab at first PD.Methods: We identified 101 patients treated between July 2000 and January 2007. Nineteen were still receiving the first-line trastuzumab-based treatment without evidence of PD and were not included in this analysis. Of the remaining 82 patients, 59 retained trastuzumab for one or more additional lines of chemotherapy after PD, according to our institution policy. Twenty-three patients who changed treating institution and stopped trastuzumab at first progression were used as a control group.Results: For patients retaining trastuzumab, the median follow-up was 39.6 months. Clinical outcomes showed the typical degradation between first and second lines of therapy which we would expect by halting trastuzumab at first progression. Response rates were 35% and 16% and median times to progression were 7.25 and 5.25 months for the first and second lines of trastuzumab therapy, respectively. The median overall survival (OS) rates were 70 months for patients who retained trastuzumab and 56 months for patients who halted the drug (hazard ratio [HR] 0.87, 95% confidence interval [CI] 0.51 to 1.18; P = 0.52). If we consider OS from the start of trastuzumab therapy, the figures are 53.9 and 34.8 months, respectively (HR 0.78, 95% CI 0.58 to 1.32; P = 0.2).Conclusion: A nonstatistically significant trend of improved survival for patients retaining trastuzumab is observed. This is in line with most retrospective analyses and recent randomized data. Retaining trastuzumab after progression is a reasonable option, but further randomized data are warranted to better define its role in comparison with other available options. © 2008 Cancello et al.; licensee BioMed Central Ltd.
Synonymous substitution rates predict HIV disease progression as a result of underlying replication dynamicsLemey, P; Kosakovsky Pond, SL; Drummond, AJ; Pybus, OG; Shapiro, B; Barroso, H; Taveira, N; Rambaut, A; Pond, Sergei L. Kosakovsky|0000-0003-4817-4029 (2007-01-01)Upon HIV transmission, some patients develop AIDS in only a few months, while others remain disease free for 20 or more years. This variation in the rate of disease progression is poorly understood and has been attributed to host genetics, host immune responses, co-infection, viral genetics, and adaptation. Here, we develop a new "relaxed-clock" phylogenetic method to estimate absolute rates of synonymous and nonsynonymous substitution through time. We identify an unexpected association between the synonymous substitution rate of HIV and disease progression parameters. Since immune activation is the major determinant of HIV disease progression, we propose that this process can also determine viral generation times, by creating favourable conditions for HIV replication. These conclusions may apply more generally to HIV evolution, since we also observed an overall low synonymous substitution rate for HIV-2, which is known to be less pathogenic than HIV-1 and capable of tempering the detrimental effects of immune activation. Humoral immune responses, on the other hand, are the major determinant of nonsynonymous rate changes through time in the envelope gene, and our relaxed-clock estimates support a decrease in selective pressure as a consequence of immune system collapse. © 2007 Lemey et al.