A5041675442- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- Gene Regulatory Network Analysis
- Machine Learning in Bioinformatics
- Computational Drug Discovery Methods
- Complex Network Analysis Techniques
- Risk and Safety Analysis
- Occupational Health and Safety Research
- Protein Structure and Dynamics
- Fractal and DNA sequence analysis
- Evolutionary Algorithms and Applications
- RNA and protein synthesis mechanisms
- Spinal Cord Injury Research
- Network Security and Intrusion Detection
- Genetic Mapping and Diversity in Plants and Animals
- Remote-Sensing Image Classification
- Data Mining Algorithms and Applications
- Genomics and Chromatin Dynamics
- Nerve injury and regeneration
- Bayesian Modeling and Causal Inference
- Metaheuristic Optimization Algorithms Research
- Genomics and Phylogenetic Studies
- Opinion Dynamics and Social Influence
- Artificial Intelligence in Healthcare
- Brain Tumor Detection and Classification
University Medical Center Freiburg
2022-2025
University of Freiburg
2020-2025
University of Zanjan
2015-2023
University of Isfahan
2023
Institute for Research in Fundamental Sciences
2019
Amirkabir University of Technology
2008-2011
Institute for Advanced Studies in Basic Sciences
2010
Recent advancements in machine learning achieved by Deep Neural Networks (DNNs) have been significant. While demonstrating high accuracy, DNNs are associated with a huge number of parameters and computations, which leads to memory usage energy consumption. As result, deploying on devices constrained hardware resources poses significant challenges. To overcome this, various compression techniques widely employed optimize DNN accelerators. A promising approach is quantization, the...
The reconstruction of the topology gene regulatory networks (GRNs) using high throughput genomic data such as microarray expression is an important problem in systems biology. main challenge number genes and low samples; also are often impregnated with noise. In this paper, dealing noisy data, Kalman filter based method that has ability to use prior knowledge on learning network was used. proposed namely (KFLR), first phase by mutual information, regulations correlations were removed....
Training a back propagation neural network is an optimization problem to find optimal weight set in training process. The can fall into local minimum point during learning of patterns. Therefore, evolutionary algorithms be used train this obtain suitable initial set. In paper, novel approach proposed the based on asexual reproduction (ARO) algorithm. basic idea method apply ARO algorithm at first step search for global connection weights. Then, thoroughly performance evaluated using number...
<ns3:p>Scientific data analyses often combine several computational tools in automated pipelines, or workflows. Thousands of such workflows have been used the life sciences, though their composition has remained a cumbersome manual process due to lack standards for annotation, assembly, and implementation. Recent technological advances returned long-standing vision workflow into focus.</ns3:p><ns3:p> This article summarizes recent Lorentz Center workshop dedicated sciences. We survey...
This paper describes a rapid feasibility study of using GPT-4, large language model (LLM), to (semi)automate data extraction in systematic reviews. Despite the recent surge interest LLMs there is still lack understanding how design LLM-based automation tools and robustly evaluate their performance. During 2023 Evidence Synthesis Hackathon we conducted two studies. Firstly, automatically extract characteristics from human clinical, animal, social science domain We used studies each category...
SARS-CoV-2 pandemic first emerged in late 2019 China. It has since infected more than 298 million individuals and caused over 5 deaths globally. The identification of essential proteins a protein-protein interaction network (PPIN) is not only crucial understanding the process cellular life but also useful drug discovery. There are many centrality measures to detect influential nodes complex networks. Since (H1N1) influenza PPINs pose 553 common human proteins. Analyzing comparing these...
Supervised machine learning is an essential but difficult to use approach in biomedical data analysis. The Galaxy-ML toolkit ( https://galaxyproject.org/community/machine-learning/ ) makes supervised more accessible scientists by enabling them perform end-to-end reproducible analyses at large scale using only a web browser. extends Galaxy https://galaxyproject.org ), computational workbench used tens of thousands across the world, with suite tools for all aspects learning.
In this study, we introduce StructmRNA, a new BERT-based model that was designed for the detailed analysis of mRNA sequences and structures. The success DNABERT in understanding intricate language non-coding DNA with bidirectional encoder representations is extended to StructmRNA. This uses special dual-level masking technique covers both sequence structure, along conditional masking. enables StructmRNA adeptly generate meaningful embeddings sequences, even absence explicit structural data,...
A new structure learning approach for Bayesian networks based on asexual reproduction optimization (ARO) is proposed in this paper. ARO can be considered an evolutionary-based algorithm that mathematically models the budding mechanism of reproduction. In ARO, a parent produces bud through operator; thereafter, and its compete to survive according performance index obtained from underlying objective function problem: This leads fitter individual. The convergence measure analyzed. method...
Background: A central problem of systems biology is the reconstruction topology gene regulatory networks (GRNs) using high throughput genomic data like microarray expression data. The main challenge in that number genes high, samples low, and are often impregnated with noise. Objective: In this paper, we present a method for Gene Regulatory Network Inference Rotation Forest (GENIRF). Methods: rotation forest will exploit embedded variable ranking mechanism tree-based ensemble methods...
Previous efforts in gene network reconstruction have mainly focused on data-driven modeling, with little attention paid to knowledge-based approaches. Leveraging prior knowledge, however, is a promising paradigm that has been gaining momentum and computational biology research communities. This paper proposes two new algorithms for reconstructing from expression profiles without knowledge small sample high-dimensional settings. First, using tools the statistical estimation theory,...
BACKGROUND: Health and safety performance measurements aimed to provide information on the progress current situation of organizational strategies activities. OBJECTIVES: We developed a model determine select key indicators in order assess management systems. METHODS: This study has been designed six steps aiming at defining leading (LPIs) selecting (KPIs) using AHP method. RESULTS: According results analysis, 116 structural operational were defined based components OHSAS 18001 system. For...
In this study, in order to deal with the noise and uncertainty gene expression data, learning networks, especially Bayesian that have ability use prior knowledge, were used infer regulatory network. Learning networks are methods structure of network a process obtain relationships. One which been for measuring relationship between genes is correlation metrics, but high correlated not necessarily mean they causal effect on each other. Studies common inference yet pay attention their biological...
Community detection is a fundamental challenge in network science and graph theory that aims to reveal nodes' structures.While most methods consider Modularity as community quality measure, Max-Min improves the accuracy of measure by penalizing quantity when unrelated nodes are same community.In this paper, we propose approach based on linear programming using Modularity.The experimental results show our algorithm has better performance than previously known algorithms some well-known...
For understanding the function of an organism, it is necessary to know "which", "how fast", and "when" genes are expressed. A gene regulatory network represents how when interact with each other. Using genetic modeling, possible explain cell functions at molecular level. DNA microarrays can measure expression levels thousands simultaneously. Most methodologies have proposed so far for modeling networks from microarray data take into account only a small number genes. In this paper, two steps...