Statistical Computing Series: Mealtime
The Statistical Computing Series hosted by Vanderbilt University Medical Center's Department of Biostatistics features presentations on the implementation of statistical models and methods, statistical computation, and graphics. These informal meetings allow experienced statisticians and developers to share their expertise on computing topics with practitioners across Vanderbilt. On Monday, November 25, 2024, at 1:30pm on Teams, principal biostatistician Josh DeClercq will present "Mealtime: A Shiny app for meal planning." Here is his description of the talk:
Have you ever come home from the grocery store and realize you have no idea what to cook? Do you have stacks of cookbooks that largely go unused? Mealtime is a data-driven approach to meal planning. This presentation will touch on how to deconstruct a recipe into its essential components to derive its "makeability" score. I'll explain how I scale this process to accommodate large numbers of recipes and ingredients and discuss how I leverage data to accommodate dietary restrictions. Finally, I will demonstrate how it all comes together in a Shiny application, sharing some tips and challenges I encountered along the way.
For access to this webinar, contact series organizer Ryan Moore.
All-department team publishes paper in Computational and Structural Biotechnology Journal
Congratulations to former visiting student Chia-Jung "Charlene" Chang (PhD candidate in biomedical engineering at National Cheng Kung University), research assistant professor Chih-Yuan Hsu, and professors Qi Liu and Yu Shyr on the publication of "VICTOR: Validation and inspection of cell type annotation through optimal regression." The article on this new method appeared online ahead of print on October 15 and will go to press as part of Computational and Structural Biotechnology Journal's December issue. As described in the paper's abstract:
Single-cell RNA sequencing provides unprecedent opportunities to explore the heterogeneity and dynamics inherent in cellular biology. An essential step in the data analysis involves the automatic annotation of cells. Despite development of numerous tools for automated cell annotation, assessing the reliability of predicted annotations remains challenging, particularly for rare and unknown cell types. Here, we introduce VICTOR: Validation and inspection of cell type annotation through optimal regression. VICTOR aims to gauge the confidence of cell annotations by an elastic-net regularized regression with optimal thresholds. We demonstrated that VICTOR performed well in identifying inaccurate annotations, surpassing existing methods in diagnostic ability across various single-cell datasets, including within-platform, cross-platform, cross-studies, and cross-omics settings.
Figure 1 in the paper provides an " One example in diagnosing the reliability of cell annotations. a) diagnostic performance of singleR, scmap, SCINA, scPred, CHETAH, scClassify, and Seurat. b) diagnostic performance of VICTOR when applied to annotations from singleR, scmap, SCINA, scPred, CHETAH, scClassify, and Seurat.
Vanderbilt Biostatistics at WSDS 2024
The 2024 Women in Statistics and Data Science Conference is underway in Reston, Virginia, from October 16 through 18. We are proud of the department members and alumni involved with this year's meeting. They include:
MS student Zongyue Teng
- First and presenting author of "Going for gold: Using record linkage and Bayesian hierarchical modeling to select winning gymnasts at the 2024 Paris Olympics" (speed session Wednesday, poster Thursday; graphic via WakeForestStats)
Sarah Lotspeich (PhD 2021)
- Co-author of "Quantifying the impact of measurement error on health disparities models" (speed session Wednesday, poster Thursday)
- Organizer of and speaker in "Mastering Data: Insights into Master's Degrees in Statistics and Analytics" (panel, Thursday)
- Organizer of "More than Statistics: Improving Maternal and Infant Health with Data" (invited session, Thursday)
- Co-author of "Adjusting for covariate misclassification to quantify the relationship between diabetes and local access to healthy food" (speed session 3, Thursday)
- Co-organizer of and speaker in "Statistical Methods For HIV Research: Battling An Epidemic With Linked, Missing, And Error-prone Data" (invited session, Thursday)
- Panelist for "Statistical Storytelling: Insights Into Effective Presentation Strategies" (Friday)
- Organizer of "Cause For Celebration: Adapting Causal Inference Methods For Challenging Datasets" (invited session, Friday)
PhD student Ashley Mullan
- First and presenting author of "Adjusting for covariate misclassification to quantify the relationship between diabetes and local access to healthy food" (speed session and poster, Thursday)
- Chair of and panelist for "Statistical Storytelling: Insights Into Effective Presentation Strategies" (Friday)
Lead biostatistician Amy Perkins
- First and presenting author of "Machine Learning Model Robustness and Performance Stability in Future Years when Predicting Adverse Events in a Veteran Population and a Diabetic Subpopulation" (speed session and poster, Thursday). Co-authors include assistant professor Amber Hackstadt and professor Michael Matheny.
Lucy D'Agostino McGowan (PhD 2018):
- Speaker in "Statistical Methods for Missing Data Imputation" (panel, Thursday)
- Co-organizer of "Statistical Methods For HIV Research: Battling An Epidemic With Linked, Missing, And Error-prone Data" (invited session, Thursday)
- Panelist for "Statistical Storytelling: Insights Into Effective Presentation Strategies" (Friday)
- Speaker in "Cause For Celebration: Adapting Causal Inference Methods For Challenging Datasets" (invited session, Friday)