Loading...
Search for:
protein-function-prediction
0.01 seconds
Protein Function Prediction Using Protein Structure and Computational Methods
, M.Sc. Thesis Sharif University of Technology ; Fatemizadeh, Emad (Supervisor) ; Arab, Shahriar ($item.subfieldsMap.e)
Abstract
Predicting the Amino Acids that have a catalytic effect in the enzymes, is a big step in appointing the activity of the enzymes and classifying them. This is a very challenging job, because an Amino Acid can appear in a variety of active sites.The biological activity of a protein usually depends on the existence of a small number of Amino Acids. Detecting these Amino Acids from the sequence of Amino Acids has many applications. Usually, the Amino Acids that are preserved are known as the Amino Acids that build up the active site, but the algorithms for finding the preserved Amino Acids are much more complex. There are a lot of algorithms for predicting the active sites of Amino Acids, but...
Protein Function Prediction using Protein Interaction Networks
, M.Sc. Thesis Sharif University of Technology ; Fatemizadeh, Emadoddin (Supervisor)
Abstract
Predicting protein function accurately is an important issue in the post genomic era. To achieve this goal, several approaches have been proposed deduce the function of unclassified proteins through sequence similarity, co expression profiles, and other information. Among these methods, the Global Optimization Method is an interesting and powerful tool that assigns functions to unclassified proteins based on their positions in a physical interaction network. To boost both the accuracy and speed of global optimization method, a new prediction method, Accurate Global Optimization Method (AGOM), is presented in this thesis, which employs optimal repetition method enhanced with frequency of...
Deep Learning in a Structured Output Space
, Ph.D. Dissertation Sharif University of Technology ; Rabiee, Hamid Reza (Supervisor) ; Soleymani, Mahdieh (Supervisor)
Abstract
A large number of machine learning problems are considered as structured output problems in which the goal is to find the mapping function between an input vector to a number of variables in the output side which are statistically correlated. Motivated by the advantages of simultaneous learning of these variables compared to learning them separately, many structured output models have been introduced. Decreasing the sample complexity, increasing the generalization ability and overcoming to noisy data are some of these benefits. So in the first step of this research we concentrate on one of classical but important problems in bioinformatics which is automatic protein function prediction....
GTED: Graph traversal edit distance
, Article 22nd International Conference on Research in Computational Molecular Biology, RECOMB 2018, 21 April 2018 through 24 April 2018 ; Volume 10812 LNBI , 2018 , Pages 37-53 ; 03029743 (ISSN); 9783319899282 (ISBN) ; Shrestha, A ; Sharifi Zarchi, A ; Gallagher, S. R ; Sahinalp, S. C ; Chitsaz, H ; Sharif University of Technology
Springer Verlag
2018
Abstract
Many problems in applied machine learning deal with graphs (also called networks), including social networks, security, web data mining, protein function prediction, and genome informatics. The kernel paradigm beautifully decouples the learning algorithm from the underlying geometric space, which renders graph kernels important for the aforementioned applications. In this paper, we give a new graph kernel which we call graph traversal edit distance (GTED). We introduce the GTED problem and give the first polynomial time algorithm for it. Informally, the graph traversal edit distance is the minimum edit distance between two strings formed by the edge labels of respective Eulerian traversals...