Search

Your search keyword '"Elisabeta Marai, G."' showing total 7 results
Start Over Author "Elisabeta Marai, G."
7 results on '"Elisabeta Marai, G."'

6. FixingTIM: Interactive exploration of sequence and structural data to identify functional mutations in protein families

Author

Luciani, T, Wenskovitch, J, Chen, K, Koes, D, Travers, T, Elisabeta Marai, G, Luciani, T, Wenskovitch, J, Chen, K, Koes, D, Travers, T, and Elisabeta Marai, G

Abstract

Background: Knowledge of the 3D structure and functionality of proteins can lead to insight into the associated cellular processes, speed up the creation of pharmaceutical products, and develop drugs that are more effective in combating disease. Methods: We present the design and implementation of a visual mining and analysis tool to help identify protein mutations across a family of structural models and to help discover the effect of these mutations on protein function. We integrate 3D structure and sequence information in a common visual interface; multiple linked views and a computational backbone allow comparison at the molecular and atomic levels, while a novel trend-image visual abstraction allows for the sorting and mining of large collections of sequences and of their residues. Results: We evaluate our approach on the triosephosphate isomerase (TIM) family structural models and sequence data and show that our tool provides an effective, scalable way to navigate a family of proteins, as well as a means to inspect the structure and sequence of individual proteins. Conclusions: The TIM application shows that our tool can assist in the navigation of families of proteins, as well as in the exploration of individual protein structures. In conjunction with domain expert knowledge, this interactive tool can help provide biophysical insight into why specific mutations affect function and potentially suggest additional modifications to the protein that could be used to rescue functionality.

Published
2014

7. Collaborative Filtering for the Imputation of Patient Reported Outcomes.

Author

Anyimadu EA, Fuller CD, Zhang X, Elisabeta Marai G, and Canahuate G

Abstract

This study addresses the prevalent issue of missing data in patient-reported outcome datasets, particularly focusing on head and neck cancer patient symptom ratings sourced from the MD Anderson Symptom Inventory. Given that many data mining and machine learning algorithms necessitate complete datasets, the accurate imputation of missing data as an initial step becomes crucial. In this study we propose, for the first time, the use of collaborative filtering for imputing missing head and neck cancer patient symptom ratings. Two configurations of collaborative filtering, namely patient-based and symptom-based, leverage known ratings to infer the missing ones. Additionally, this study compares the performance of collaborative filtering with alternative imputation methods such as Multiple Imputation by Chained Equations, Nearest Neighbor Imputation, and Linear interpolation. Performance is compared using Root Mean Squared Error and Mean Absolute Error metrics. Findings demonstrate that collaborative filtering is a viable and comparatively superior approach for imputing missing patient symptom data.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results