• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Desmond delali kwasi Attadjei
Prediction of Effects of Genetic Variants in Personalized Medicine
Big Data Systems
(Master’s programme)
8
2018
Cancer remains one of the severe and detrimental diseases that continues to cause a lot of mortality. Various researches are ongoing to help understand and mange it carefully. Among these research and experiments can be found the application of natural language processing and machine learning techniques. To further help the situation, classification machine learning techniques are heavily adopted in the field, with the use of different data sets.

In this study, a supervised machine learning task in the form of a classification task to classify driver cells and passenger cells of cancer was carried out on a text annotation data. The classification task is preceded by the application and comparison of some word vector representation models- unsupervised machine learning task, which include Word2Vec, Doc2Vec and FastText model; of which the Word2Vec model was the best based on its vectors high predictive effectiveness.

After word vectorisation, a classification and comparison task were performed on the Neural Network model, the Random Forest Model and the Support Vector Machine (SVM) models. Random forest model outperformed all the other models with a training accuracy of 63.75 percent, which is also followed by the Neural Network model (61.78%) surpassing the SVM model by making an accuracy of 61.65%. However, the neural network did worse in making prediction (59.68% accuracy). The Random forest model's prediction accuracy still exceeds the training and prediction accuracy of the remaining models, it has been adjudged the best performing one.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses