Unit:
Department of Informatics and TelecommunicationsΠληροφορική
Supervisors info:
Ηλίας Μανωλάκος, Καθηγητής, Τμήμα Πληροφορικής και Τηλεπικοινωνιών, Εθνικό και Καποδιστριακό Πανεπιστήμιο Αθηνών
Original Title:
MLscANApp: Creating an Interactive RShiny Interface for scRNA-seq Bioinformatics Data Analysis
Translated title:
MLscANApp: Creating an Interactive RShiny Interface for scRNA-seq Bioinformatics Data Analysis
Summary:
Single-cell RNA sequencing (scRNA-seq) has revolutionized the study of gene expression, profiles offering detailed insights into cellular heterogeneity and dynamic biological processes. However, analyzing scRNA-seq datasets presents significant challenges due to their high dimensionality, noisy gene expressions, and the need for sophisticated computational methods to draw meaningful biological conclusions.
MLscAN (Machine Learning for Single-Cell ANalytics) is an R package that provides a comprehensive pipeline for unbiased scRNA-seq data analysis. By using exclusively only unsupervised machine learning methods such as dimensionality reduction, clustering, trajectory inference, and gene regulatory network reconstruction, MLscAN enables researchers to infer cell states and identify cell state transitions and the molecular drivers of these biological progression processes—all without relying on any prior knowledge. Despite its powerful features, MLscAN requires some programming expertise in R which presents a barrier to use for many life scientists.
To overcome this challenge, this thesis introduces MLscANApp (Machine Learning for Single-Cell ANalytics Application), an RShiny application designed to make MLscAN’s many capabilities accessible through a user-friendly graphical interface (GUI). MLscANApp allows life scientists to conduct the MLscAN workflow of comprehensive scRNA-seq analyses without the need for coding skills. Users can leverage the full functionality of the MLscAN pipeline, by getting guidance for their analysis at each step and interpreting results through a plethora of interactive and insightful visualizations. This application bridges the gap between complex computational methods and practical research, making advanced scRNA-seq-based analysis accessible to a broader scientific community.
Main subject category:
Technology - Computer science
Keywords:
Single-cell RNA-sequencing, R, Biological Data Analysis, RShiny Application, Machine Learning, Bioinformatics, Data Visualization
File:
File access is restricted until 2025-04-15.
BSc_THESIS-Violetta.pdf
5 MB
File access is restricted until 2025-04-15.
