Selected Projects:• Led research in supervised machine learning classifiers for the prediction of gene targets for drug discovery efforts. Authored Python code stack managing complex API queries across company platform for the assembly of training and annotation data for user-selected disease indications, performance comparisons of a suite of classifiers using nested cross-validation, and downstream analysis of feature weights to inform future data generation efforts• Formulated novel metrics for gauging the replicability of gene expression correlations across cohorts and between human, animal, and in vitro models based on the probability distributions of correlation matrix elements, becoming one of the core protocols for the company drug discovery platform used to select disease signatures for neurodegenerative, neuropsychiatric, and autoimmune indications • Formulated a novel expansion of Gene Set Analysis (GSA; Efron and Tibshirani (2007), Ann. Appl. Stat. 1(1):107-129) to quantify the consistency of set-wise gene dysregulation across experiments and between human, animal, and in vitro models; Python code for this and custom implementation of efficiency-enhanced versions of original GSA calculations was incorporated into the company analytic pipeline, becoming one of the core protocols for weighing strength of evidence for the company drug discovery platform• Devised flexible Generalized Linear Mixed Modeling protocol enabling the efficient analysis and plotting of diverse microscopy experimental outputs for bench scientists across the company

Selected Projects:• Formulated novel unsupervised machine learning approach for the detection of clusters of co-expressed genes, similar in spirit to Langfelder Horvath (2008, BMC Bioinformatics 9:559) but based on probability theoretic reasoning for increased validity of output; adopted as one of the core protocols for the company drug discovery platform used to select disease signatures for neurodegenerative, neuropsychiatric, and autoimmune indications • Conducted study design, power analysis, and results reporting for in vitro and in vivo studies using outcomes including rodent biomarker and behavioral endpoints, histological changes, cell survival, cellular morphological differentiation, gene expression, puncta and stress granule formation, and immunofluorescence in collaboration with bench scientists across the company • Implemented software for the fitting of random-effects hazard models for an automated pipeline tracking survival and morphology of neurons for in vitro experiments

Novel Methods Development (see publications)Application of t-distributed Heckman selection models for multiply missing-not-at-random (MNAR) data with complex sampling designQuantified time-dependent vulnerability to exposures with multi-hierarchy Bayesian modeling using a Metropolis-within-Gibbs algorithmTechnical DomainsGeneralized linear mixed models, Poisson hidden Markov models, dependent mixture models, multivariate t-distributed models, Heckman selection models, spatial conditional autoregressive modeling, hierarchical Bayesian modeling, Integrated Nested Laplacian Approximation (INLA), geodatabases, spatial Scan statistics, meta-analysisProject TopicsEmergency department visits by patients with sickle cell disease, Parkinson’s disease incidence and prevalence, amyotrophic lateral sclerosis incidence, pediatric lead exposure, environmental health surveillance database design, breast cancer geography, exposure risk analysis, drinking water safetySpecial RolesPrincipal investigator, leader of statewide stakeholder-driven science education program, shepherded of applications through Committee for the Protection of Human Subjects, navigated bureaucracies across multiple state agencies for project adherence to institutional standards for confidentiality protection

Technical DomainsReal-world data, non-parametric locally-weighted spatial estimationProject TopicsEnvironmental health surveillance, pediatric asthma, maternal and infant health, pesticide exposure, autism spectrum disordersSpecial RolesPrincipal Investigator, program evaluation, convened multi-region task force for stakeholder-led evaluation of public health surveillance activities

Health Services Research, Institute of Health Policy Studies

General Pediatrics