#   Computational Science and Engineering Capstone Project (APCOMP 297R)  

 



 The Computational Science and Engineering (CSE) capstone project is intended to integrate and apply the skills and ideas CSE students acquire in their core courses and electives. By requiring students to complete a substantial and challenging collaborative project, the capstone course prepares students for the professional world and ensure that they are trained to conduct research. Students deal with real-world problems, messy data sets, and the chance to work on an end-to-end solution to a problem using computational methods.



 

 Identifying submarkets using a Bayesian approach Various methods for predicting unobserved gene expression in maize Healthy Aging Signal Research Study Named Entity Recognition of IEEE Abstracts 

## Identifying submarkets using a Bayesian approach

 

 

 **Title**: Identifying submarkets using a Bayesian approach

 **Members**: Nam Luu Nhat, Preston Ching, Marcel Hedman, Owen Schafer

 **About**: In this project, we experiment on using a Bayesian hierarchical approach to identify submarkets of the Denver real estate market. The goal is to explore whether these submarket classifications, as a combination of geographical, physical and socio-environmental factors, will add value to the prediction of demand for residential housing in the Denver area.



 

 ![APCOMP 297R Team Rex poster](/sites/g/files/omnuum4586/files/seas-designfair/files/team_rex_poster_final.png)

 



 



 

 

 

## Various methods for predicting unobserved gene expression in maize

 

 

 **Title**: Various methods for predicting unobserved gene expression in maize

 **Members**:  Victor Avram, Eagon Meng, Wenhan Zhang, Sergio Jimenez

 **About**:  The project explored way of modeling the effects of gene perturbations and whether or not gene expression levels are informative of each other, specifically in maize. Several predictive models were built, with the ultimate goal of elucidating relationships across genes in the maize genome.



 



 



 

 

 

## Healthy Aging Signal Research Study

 

 

 **Title**: Healthy Aging Signal Research Study

 **Members**:  Eleonora Shantsila, Daniel Cox, Yaxin Lei, and Aaron Jacobson

 **About**:  The process of ageing causes observable changes in each of our cells. This process does not necessarily run at the same speed from person to person, meaning individuals of a given chronological age may have different biological ages. In this project we build models to predict true chronological age from DNA methylation data, with the goal of these to serve as a baseline against which specific individuals might be compared. Poor predictions would potentially indicate aberrant cellular ageing. Our best models predict chronological age over the entire range of adulthood to an error of less than four years.



 

 [](https://drive.google.com/file/d/1aBz-hW9xE7gZBY95eYNoePltRX9KQGtd/view)

 ![Merck Team poster](/sites/g/files/omnuum4586/files/seas-designfair/files/academic_poster_healthy_aging.png)

 



 



 

 

 

## Named Entity Recognition of IEEE Abstracts

 

 

 **Title**: Named Entity Recognition of IEEE Abstracts

 **Members**:  Paulina Toro Isaza, John Alling, You Wu, Justin Clark

 **About**:  The main objective of this project is to identify named entities in IEEE Xplore article abstracts. The three entity classes of interest are: Methods, Products, and Organizations. We are using state of the art Natural Language Processing models to extract these entities and then clustering them with other entities that have the same reference.