Our ultimate goal is to investigate the risk factors and mechanisms contributing to the onset and progression of chronic diseases and cancer and develop predictive methods and tools that will improve health.  We use probabilistic graphical models and other machine learning methods to model biological processes and integrate and mine high-dimensional, multi-modal biomedical data.  We are very interested in the effect of gene regulatory networks and genotype in disease in combination with clinical data.


Indicative Recent Work

  1. A.J. Sedgewick, K. Buschur, I. Shi, J.D. Ramsey, V.K. Raghu, D.V. Manatakis, Y. Zhang, J. Bon, D. Chandra, C. Karoleski, F.C. Sciurba, P. Spirtes, C. Glymour, P.V. Benos, “Mixed Graphical Models for Integrative Causal Analysis with Application to Chronic Lung Disease Diagnosis and Prognosis”, Bioinformatics, (2018), accepted.  Abstract (PubMed) and pdf    PMID:30192904
  2. D.V. Manatakis, Vineet K. Raghu, and P.V. Benos, “piMGM: Incorporating Multi-Source Priors in Mixed Graphical Models for Learning Disease Networks” Bioinformatics (Proc ECCB), (2018),34:i848–i856.  Abstract (PubMed) and pdf   PMID:
  3. V.K. Raghu, A. Poon, P.V. Benos, “Evaluation of Causal Structure Learning Methods on Mixed Data Types”, PMLR, (2018), 92:48-65.  Abstract and pdf
  4. G.D. Kitsios, A. Fitch, D.V. Manatakis, S. Rapport, K. Li, S. Qin, J. Huwe, Y. Zhang, Y. Doi, J. Evankovich, W. Bain, J.S. Lee, B. Methe, P.V. Benos, A. Morris, B. McVerry, “Respiratory microbiome profiling for etiologic diagnosis of pneumonia in mechanically ventilated patients”, Frontiers in Microbiol, (2018), 9:1413.  Abstract (PubMed) and pdf   PMID:30042738.   PMCID:PMC6048198.
  5. V.K. Raghu, C.H. Beckwitt, K. Warita, A. Wells, P.V. Benos, Z.N. Oltvai, “Biomarker identification for statin sensitivity of cancer cell lines”, Biochem Biophys Res Commun, (2018), 495:659-665.  Abstract (PubMed) and pdf   PMID:29146185.   PMCID:PMC5827944