Engineering biological systems offers huge benefits to bio economy, through the development of applications in the areas of drug delivery, bio remediation, signaling and so on. Several initiatives have already demonstrated the usefulness of signaling projects in different but interrelated fields including synthetic biology, molecular communications and nanotechnology in order to carry data using living systems. We then use a synthetic biology approach to control cellular response.
Decisions taken in parliament in the world affect societies and countries. These writings in parliaments are an important and significant resource for social scientists and political scientists. Most countries in the world publish their own parliamentary documents. However,these transcripts are not sufficiently understood by the public. It is the duty of linguists and NLP researchers to ensure that this resource is understandable. A study was carried out that collected all minutes of the Grand National Assembly of Turkish Parliament (TBMM) between 1920 and 20151.
Recent studies in Deep Learning have led to many advancements in problems regarding images. One of the obstacles that researchers have faced is training with Deep Learning methods requires a vast amount of data and computation power. Among the methods that try to overcome with mentioned problem, we are especially interested in transfer learning and using synthetic data.
Chatbots have become a popular communication tool with the recent improvements in NLP and machine learning techniques. We observed that every year same questions about regulations are asked over and over among the student groups. In our project we aimed to build a chatbot which answers to most frequently asked questions regarding rules and regulations of Bogazici University. We used Naive Bayes and Deep Neural Network as models to train our program with questions asked in previous years. In order to make our chatbot easily accessible we used a popular messaging platform, Telegram.
In this project I implemented a robust time-series-data visualization tool using reactjs. The tool takes a csv file as input and answers visualization queries with high efficiency. The data is represented as an n dimensional tensor where n and dimension sizes are determined by user. The program then takes different projections of that tensor to answer visualization queries.
Music transcription is the transformation of musical sound signals into human-readable form. Some trained people could achieve this task, with the help of their education and the human intuition. But it is very challenging to develop an automated transcriber, because we need to equip machines with this intuition. We do not realize it often, but there is great mathematical harmony in music. So if we could figure out the aspect of mathematics thoroughly, it would help us develop new technologies for the analysis and synthesis of music.
The aim of this project is to create a web based application which provides easy access to drug target interactions, or in a more general sense, protein ligand interactions.