About
8
Publications
29,673
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6
Citations
Citations since 2017
Introduction
Shima Shafiee currently collaborates at the Department of Computer Engineering, Razi University, Kermanshah, Iran as a Ph.D. researcher. Shima's research is on bioinformatics, computational intelligence with R, Bio weka, and Biopython. She is interested in the applications of machine learning and deep learning-based methods in bioinformatics. Also, her interests are the prediction of computational cancer biology, protein patterns, and analyzing biological networks.
Publications
Publications (8)
Since in bioinformatics it remains challenging to predict important amino acid residues for the binding amino acid residues regions and to perform binding region-based protein interactions. the present article focused to predict protein-peptide binding amino acid residues regions using various distinct feature groups (structure and sequence-based f...
Prediction of peptide-binding site of proteins is significant and essential task in different processes such as understanding biological processes, protein functional analysis, comparison of functional sites, comprehension of the transactions mechanism, drug design, cellular signaling, and cancer treatment. Predictive analysis of the protein-peptid...
Peptide-binding proteins play significant roles in various applications such as gene expression, metabolism, signal transmission, DNA (Deoxyribose Nucleic Acid) repair, and replication. Investigating the binding residues in protein-peptide complexes, especially from their sequence only, is challenging experimentally and computationally. Although se...
Peptide-binding proteins prediction is important in understanding biological interaction, protein performance analysis, cellular processes, drug design, and even cancer prediction, so using experimental predictive methods, despite their operational capabilities, has limitations such as being costly and need to spend more time, differences between u...
With the increasing growth of technology and information technology, human beings are always looking for a means to facilitate human activities, which, like humans, include processes of thinking, decision-making, solving logical problems through knowledge learning, controlling critical situations, accurate analysis of natural human behaviors and ot...
این مطالعه بر روی مسائل بهینه سازی چند هدفه با الگورتیم متاهیورستیک(ژنتیک چند هدفه با مرتب سازی نامغلوب)متمرکز است. در واقع با توجه به زمانبر بودن و پیچیدگی روشهای کلاسیک توجهات بسوی روش های بهینه سازی هوشمند تک و چند هدفه منعکس شده است. با توجه به کارایی مسائل بهینه سازی در حوزه علم و صنعت، در این مطالعه به ارائه این مسائل بهینه سازی با روشهای مخت...
As one of the classical problems in combinatorial optimization, the Bin Packing Problem has assumed a branch of computer sciences and a special form of 0-1 knapsack problem and it is derived from the family of NP-Hard. This study aims at achieving the optimal packing based on the minimum linear time and maximum applied bins with a focus on increasi...
Questions
Questions (71)
Hello dear researchers
There is a data set with a blessing rate of 1 to 17 means that the number of negative classes is 17 times the number of positive classes
To address this problem, sampling methods and GAN networks are candidates.
Which one do you recommend?
Please explain your reason in full? refer your reference(s)?
Thank you so much for your comments
Hello, dear researchers
The deep learning network, called Generative Adversarial Networks (GANs), has various roles in optimization problems.
Can GAN be used as a feature construct? Can you please introduce a suitable reference for the GAN-based feature construct?
Thank you so much for your attention and participation.
