I'm Slaviana Pavlovich

These words are here to provide the reader with a basic impression of how actual text will appear in its final presentation. This is dummy copy. It is not meant to be read. It has been placed here solely to demonstrate the look and feel of finished, typeset text. These words are here to provide the reader with a basic impression of how actual text will appear in its final presentation. Only for show.

These words are here to provide the reader with a basic impression of how actual text will appear in its final presentation. This is dummy copy. It is not meant to be read. It has been placed here solely to demonstrate the look and feel of finished, typeset text. These words are here to provide the reader with a basic impression of how actual text will appear in its final presentation. Only for show.

Atopic Dermatitis and Psoriasis are skin conditions affecting approximately 20% and 2% of the global population respectively. Although these diseases are well known to physicians and have been for some time, their causes have eluded scientists up until fairly recently. In this project, we sought to uncover some of the inherent genetic causes of these conditions by identifying key genetic markers that may make people more susceptible to the diseases. To do this, a dataset containing the genes of both healthy and unhealthy patients was scrutinised using a variety of Machine Learning techniques. The results of this study have highlighted a number of genes that may place people at a greater disposition to these conditions.

Acknowledgment: This project was submitted as part of my MSc in Bioinformatics and Theoretical Systems Biology at Imperial College London.

The Microbiome Metabolism Exploration Tool (Memento) is a “1-click” microbiome analysis web tool for clinicians. Memento receives a person of interest’s (POI’s) raw 16S amplicon sequence information and infers the significant enzymatic and metabolic pathways taking place. After querying the Memento database (consisting of 2062 microbiome associated enzymatic reactions and 1176 exogenous compounds), the tool outputs the likely interactions of a given drug in the POI’s microbiome. As a tool aimed at clinicians and researchers, Memento associates 144 academic publications and 1185 applications of drugs to the database to allow the clinician to browse relevant texts alongside the tool. Memento also tailors a premade Operational Taxonomic Unit (OTU) taxonomic classifier (from scikit-learn) to give researchers and clinicians a high-level view of dysbiosis in the POI’s microbiome (with up to 85% accuracy). Memento was validated using data from recent 16S rRNA amplicon studies and reproduces similar trends to the current consensus, whilst also providing clinically relevant drug and publication information.

As a proof-of-concept, Memento has demonstrated that highly relevant clinical information can be extracted from 16S amplicon data. The web tool serves as a benchmark for new user-friendly bioinformatic implementations aimed to take steps towards personalised medicine in the microbiome clinical setting.

Acknowledgment: This project was submitted as part of my MSc in Bioinformatics and Theoretical Systems Biology at Imperial College London.

Genetic drift is the change in the frequency of a gene variant in a population over multiple generations. An individual’s alleles are a sample of those in present their parents and chance has a role in determining whether that individual will survive and reproduce. Genetic drift may cause gene variants to disappear completely from a population and thereby reduce genetic variation. The script simulates the two genetic drift models.

Acknowledgment: This project was submitted as part of my MSc in Bioinformatics and Theoretical Systems Biology at Imperial College London.

The Smith- Waterman algorithm is used for determining similar regions between two strings of nucleic acid sequences or protein sequences. Instead of looking at the entire sequence, the Smith–Waterman algorithm compares segments of all possible lengths and optimizes the similarity measure.

Acknowledgment: This project was submitted as part of my MSc in Bioinformatics and Theoretical Systems Biology at Imperial College London.

An innovative research method, data mining, was employed for data cleaning, pre-processing and analysis of 515,743 customer hotel reviews from Booking.com. The analysis offers new insights into the key determinants of customer satisfaction, showing that customers particularly value the locations of hotels, friendly staff and clean rooms. There is a moderate positive correlation between customer sentiment (emotion expressed in the text of the review) and given rating. To address an inconsistency that could occur between customer sentiments and ratings, with the latter being potentially misleading and not supported by the text of the review, the supervised machine learning techniques were compared on the ability to predict the customer ratings, on the 10-star scale, based on reviewers’ text. Support Vector Machines algorithm delivers the most accurate results, achieving an accuracy of 76%. The findings from this research suggest that the analysis of online reviews can provide the means for bridging the gap between customers’ perception of service quality and managers’ understanding of it.

Acknowledgment: This dissertation was submitted as part of my BSc in Information Management for Business at University College London.

Author: Slaviana Pavlovich.

Publication Date: 15^th October 2016.

In October 2016 I wrote a paper titled: “Should society encourage the development of 3D Printing, particularly 3D bioprinting of tissues and organs?”, which was published in the International Journal of Scientific & Technology Research. I wrote the paper in my free time during my A-levels, having decided to research the economic, psychological and social impact of the 3D bioprinting technology. After discussing the topic on forums online, the journal approached me to publish my paper. This was an excellent experience for me as it was the first time I had my skills as a researcher recognised independently by an external body.