Knowing the evolutionary relationships among different species, valuable information is obtained. One of its applications is the Tree of Life project.

Drug discovery is the therapeutic process of suggesting new candidate medications.
This process takes a lot of time and money before a new drug is discoverd. Furthermore, more than 90% of drugs fail during the development process.

This way so much cost and time is saved by bypassing many early-stage clinical trials which the drug has already passed. This approach is specially effective in many fields of medicine where a wide variety of somewhat similar diseases have related underlying mechanisims and causes.

represented by Mahro moridi

Location : Amirkabir University Of Technology, Department Of Mathematics & Computer Science , room 312

Time : 11 Oct , 16:30 – 18

Non-coding RNAs are RNA molecules that do not translate into proteins. These RNAs are functionally important in many biological processes. Their biological functions are highly related to their interaction partners. RNA-RNA interactions are one of the possibilities. It is desired to use computational methods to study and predict the interaction partners of non-coding RNAs.
We first study the RNA-RNA interaction pattern using experimental validated RNA-RNA interaction data, we study the sRNA-mRNA interaction data and combine some features about interaction sites into the Turner Energy Model. We develop a genetic algorithm based program RIPGA to solve the RNA_RNA interaction prediction problem.

represented by Parham Hafezi

Location : Amirkabir University Of Technology, Department Of Mathematics & Computer Science , room 313

Time : 25 Oct , 16:30 – 18

Reconstruction of the haplotype, based on sequenced data of the Snipes genome, plays an important role in genetic studies, including complex genetic diseases and evolutionary studies. Sequences of Snipes on a chromosome are called haplotypes. Computational methods can greatly reduce the cost and time of laboratory extraction of haplotypes. One of the computational methods is the reconstruction of one person’s haplotypes from the snippets of that person, which calls for the reconstruction of the haplotype from Snape fragments. This problem is correction and removal of Snip fragments from a chromosome to form a complete haplotype.

represented by Samin Jamshidi

Location : Amirkabir University Of Technology, Department Of Mathematics & Computer Science , room 313

Time : 25 Oct , 16:30 – 18

In recent times, many methods have been introduced to reconstruct gene expression regulation networks, but most of these methods do not consider the existence of time delay relation.

We are going to introduce a method called GA / PSO with DTW, which looks at these relationships and, in the end, we will try to improve this algorithm.

In this algorithm, the input data for solving the problem is the data obtained from the microarray; microarray technology is one of the most powerful and most useful methods for studying the behavior of the genome, since this technology provides the ability to measure the levels of expression of different genes simultaneously.

represented by Mahya Moshraf

Location : Amirkabir University Of Technology, Department Of Mathematics & Computer Science , room 313

Time : 15 Nov , 16:30 – 18

According to structure-dependent function of proteins, two main challenging problems called Protein Structure Prediction (PSP) and Inverse Protein Folding (IPF) are investigated. In spite of IPF essential
applications, it has not been investigated as much as PSP problem.

In fact, the ultimate goal of IPF problem or protein design is to create proteins with enhanced properties or even novel functions. One of the major computational challenges in protein design is its large sequence space, namely searching through all plausible sequences is impossible. Inasmuch as, protein secondary structure represents an appropriate primary scaffold of the protein conformation, undoubtedly studying the Protein Secondary Structure Inverse Folding (PSSIF) problem is a quantum leap forward in protein design, as it can reduce the search space.

represented by Marziyeh Movahedi

Location : Amirkabir University Of Technology, Department Of Mathematics & Computer Science , room 312

Time : 29 Nov , 16:30 – 18

In a system for identifying each member, an identifier is assigned to it. Nature also attributes to any living creature an identifier known as DNA. As a result, obtaining DNA of an organism is one of the most important ways to know that living organism.

The ideal way to get DNA is to have devices that receive a cell from an organism as an input and give us the DNA strand. But such technology is not available at the moment. Current devices give us discontinuous patches of DNA as output. In the assembly of the genome, the goal of obtaining the main DNA strand is to assemble these pieces.

In this presentation, we will review the history of the methods presented in this regard. We present a suggestion for improving these methods.

represented by Shohre Masoumi

Location : Amirkabir University Of Technology, Department Of Mathematics & Computer Science , room 311

Time : 19 Dec , 16:30 – 18

The problem of determining which nucleotides of an RNA sequence are paired or unpaired in the secondary structure of an RNA can be studied by different machine learning techniques. Successful state inference of RNA sequences can be used to get further insights into the RNA secondary structure. Typical tools for this task, such as hidden Markov models, exhibit poor performance in RNA state inference, owing in part to their inability to recognize nonlocal dependencies. Bidirectional long short-term memory (LSTM) neural networks have emerged as a powerful tool that can model global nonlinear sequence dependency and have achieved state-of-the-art performances on many different classification problems. This paper presents a method for RNA state inference centered around deep bidirectional LSTM networks.

represented by Mohadeseh Lotfi & AmirHossein Roozbahany

Location : Amirkabir University Of Technology, Department Of Mathematics & Computer Science , room 313

Time : 27 Dec , 16:30 – 18

Transcription factors are key gene regulators, responsible for modulating the conversion of genetic information from DNA to RNA. Though these factors can be discovered experimentally, computational biologists have become increasingly interested in learning tran- scription factor binding sites from sequence data computationally. Though traditional machine learning architectures, including support vector machines and regression trees have shown moderately successful results in both simulated and experimental data sets, these models suffer from relatively low classification accuracy, typically measured by area under the receiver operating characteristic curve (auROC).

represented by Hossein Banki Kashki

Location : Amirkabir University Of Technology, Department Of Mathematics & Computer Science , room 313 

Time : 3 Jan , 16:30 – 18