http://depot.umc.edu.dz/handle/123456789/14447 Tue, 02 Jun 2026 03:07:48 GMT 2026-06-02T03:07:48Z http://depot.umc.edu.dz/handle/123456789/14711 BP-09: Decoding the Genome: Advancing Anomaly Detection through Machine Learning ALIOUANE, Salah Eddine; CHEHILI, Hamza; BOULAHROUF, Khaled; ABDELAZIZ, Aya; HAMIDECHI, Mohamed Abdelhafid This presentation explores the fusion of genomic analysis and machine learning with the aim of revolutionizing anomaly detection in genetics. This advancement is seen as propelling precision medicine and enhancing advanced diagnostics. Objectives: The objectives include the investigation of the application of machine learning in the detection of genetic anomalies. This aims to elucidate its potential in early disease identification and the provision of personalized healthcare. Methods: The presentation begins with an introduction to genomics, highlighting the necessity of artificial intelligence in dealing with the vast amount of genomic big data. It then proceeds to delve into various machine learning tools, such as DeepVariant, VarSome Clinical, and Deep SEA. Throughout this exploration, the presentation unveils the data sources, predictive capabilities, and the profound impact these tools have on the interpretation of genomics. Results and discussion: During this segment, it is demonstrated that by harnessing the prowess of artificial intelligence, enhanced accuracy in the identification of genetic anomalies can be showcased. This results in the faster analysis of vast genomic datasets, opening the door to potential groundbreaking biomedical discoveries. Conclusion: In conclusion, the amalgamation of genomics and machine learning heralds a paradigm shift in the domains of disease detection and treatment, ushering in a new era characterized by tailored healthcare Thu, 05 Oct 2023 00:00:00 GMT http://depot.umc.edu.dz/handle/123456789/14711 2023-10-05T00:00:00Z http://depot.umc.edu.dz/handle/123456789/14710 BP-08: Exploring the Impact of Some Parameters and Their Interactions on the MAFFT MSA Tool Using the Design of Experiments ROUABAH, Safia; DAAS, Skander; BOULAHROUF, Khaled; HAMIDECHI, Mohamed Abdelhafid Multiple Sequence Alignment (MSA) is essential in bioinformatics for identifying conserved regions and evolutionary relationships among biological sequences. Due to its efficiency and precision, the MAFFT algorithm is a popular tool for conducting MSA. However, the effect of numerous parameters and their interactions on some performance metrics remains relatively underexplored. In this study, we investigate the effects and interactions of four important parameters: number of sequences, sequence length, insertion rate, and deletion rate, on four performance metrics of the MAFFT tool. By generating a diverse dataset of biological sequences, we carried out a comprehensive analysis of MAFFT's performance in terms of Sum of Pairs Score (SPS), Column Score (CS), and Delay. Through a series of controlled experiments using the design of experiments, we assessed the impact of parameters’ variation and their interactions on these performance metrics. Our findings indicate that the considered parameters and their interactions significantly influence the MAFFT’s performance across all the metrics. Specifically, the most influential parameter in terms of SPS and CS quality is the number of sequences. However, the sequence length parameter has a greater impact on the delay metric. Additionally, insertion and deletion rates, has a relatively lower impact on all alignment quality metrics. These results emphasize the importance of parameter impact and their interactions on the MAFFT tool. The study provides insights into the interplay between MAFFT's parameter settings and its performance, enabling researchers and practitioners to make informed decisions when applying the tool to biological sequence alignment tasks. Thu, 05 Oct 2023 00:00:00 GMT http://depot.umc.edu.dz/handle/123456789/14710 2023-10-05T00:00:00Z http://depot.umc.edu.dz/handle/123456789/14709 BP-07: The application of machine learning techniques in rare diseases NAIR, Safa; BOUCHEHAM, Anouar; CHEHILI, Hamza Emerging machine learning (ML) techniques have the potential to greatly improve rare disease (RDs) research and treatment. The use of artificial intelligence (AI) technologies can be especially advantageous for the study of RDs, which are a diverse group of diseases that impact a small percentage of the whole population and significantly underrepresented in basic and clinical research. The difficulties faced by RDs (such as small patient population, geographical dispersion, low diagnostic rates, etc.) can be overcome by using ML techniques. Objectives: This review aims to highlight the accomplishments of AI algorithms in the study of rare diseases and to guide researchers on which strategies have proven to be the most beneficial. Methods: The study will focus on a few rare diseases. The Orphanet categorization was used, and only RDs with Orpha codes were considered. And will look at which AI methodologies have been most successful in their research. Results and discussion: ML techniques demonstrate that no single strategy excels universally; success is dependent on unique tasks and resources. The complexity, interpretability, and data requirements of models differ. While deep learning can capture complicated patterns, it may be difficult to interpret, as opposed to simpler models such as logistic regression. There is a clear trade off between model complexity and performance. Ensemble learning, like random forests, is resistant to noisy data. Deep learning necessitates enormous computational resources. Tuning hyperparameters is crucial, and technique selection should be guided by domain-specific factors. Conclusion: In conclusion, from the standpoint of precision medicine, AI algorithms can help to design individualized treatment plans by finding biomarkers linked with a specific rare disease. AI systems that discover, forecast, and classify mutations can advance RDs diagnosis, raising these figures and uncovering new disease causes and therapeutic targets. The AI-mediated knowledge of RDs could considerably accelerate therapeutic development Thu, 05 Oct 2023 00:00:00 GMT http://depot.umc.edu.dz/handle/123456789/14709 2023-10-05T00:00:00Z http://depot.umc.edu.dz/handle/123456789/14708 BP-06: Metagenomics: A strategy to study complex microbiota FERHAOUI, Nerdjes; SEBAIHIA, Mohammed The development of genome-sequencing technologies, especially the application of next- generation sequencing (NGS), has accelerated the study of complex microbiota. Metagenomics plays a crucial role in expanding our knowledge of the microbial world, has numerous applications across various fields, and holds the potential to address pressing global challenges in health, the environment, and biotechnology. This new approach has the potential to uncover novel enzymes, pathways, and molecules with industrial applications. Furthermore, by analyzing metagenomic data, researchers can identify new natural products with therapeutic potential. Many antibiotics, antivirals, and other pharmaceuticals have been discovered through metagenomic approaches. This work is intended to introduce different research methods to study complex microbiota, with a specific focus on the current progress and application of metagenomics. We discuss here computer programs used in metagenomics such as MEGAN, Kraken and MePIC that allow analysis of large data sets by a single scientist. We also highlight the necessity to begin studying complex infections using metagenomics approach, which is essential for better understand the host–bacterial interactions Thu, 05 Oct 2023 00:00:00 GMT http://depot.umc.edu.dz/handle/123456789/14708 2023-10-05T00:00:00Z