IPDS: A semantic mediator‐based system using Spark for the integration of heterogeneous proteomics data sources

Messaoudi, Chaimaa; Fissoune, Rachida; Badir, Hassan

doi:10.1002/cpe.5814

Cited by 7 publications

(5 citation statements)

References 80 publications

(96 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PRIDE database is available with the aim to archive various types of proteomics mass spectrometry data for reproducible research, facilitate protein-centric integration of MS-based data for variant and modification analysis, and furnish MS-based expression data to the Expression Atlas [ 10 ]. An integrated proteomics data system (IPDS), a data integration platform, is developed to collect the expanding heterogeneous proteomic data and its relevant information and to make this information easily accessible to the scientific community [ 6 ]. Despite all these and other databases, to our best knowledge, there is no publicly available dataset/repository dedicated to a biomedical data integration system that is curated especially for a machine learning point of view, where all MS files are mapped to its respective patient medical history without personal information disclosure.…”

Section: Discussionmentioning

confidence: 99%

“…By utilizing a shared query engine and, in some circumstances, a data processing framework like Spark, these systems provide consolidated access to multiple data stores, such as the Relational Database Management System (RDBMS), NoSQL, and Hadoop Distributed File System (HDFS). In a nutshell, multistore systems enable seamless access to many types of data sources through the use of a common querying and processing approach, making it easier to analyze and extract insights from data stored in different forms and locations [ 6 ].…”

Section: Discussionmentioning

confidence: 99%

“…For instance, deep learning techniques such as convolutional neural networks and recurrent neural networks have shown promise in analyzing large-scale proteome data [ 5 ]. Additionally, cloud-based technologies such as Apache Spark and Hadoop can be used to parallelize data processing and facilitate data sharing among different researchers [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Retrieval of Heterogeneous Proteomic Data for Machine Learning

Rafay

Aziz

Zia³

et al. 2023

JPM

View full text Add to dashboard Cite

Proteomics instrumentation and the corresponding bioinformatics tools have evolved at a rapid pace in the last 20 years, whereas the exploitation of deep learning techniques in proteomics is on the horizon. The ability to revisit proteomics raw data, in particular, could be a valuable resource for machine learning applications seeking new insight into protein expression and functions of previously acquired data from different instruments under various lab conditions. We map publicly available proteomics repositories (such as ProteomeXchange) and relevant publications to extract MS/MS data to form one large database that contains the patient history and mass spectrometric data acquired for the patient sample. The extracted mapped dataset should enable the research to overcome the issues attached to the dispersions of proteomics data on the internet, which makes it difficult to apply emerging new bioinformatics tools and deep learning algorithms. The workflow proposed in this study enables a linked large dataset of heart-related proteomics data, which could be easily and efficiently applied to machine learning and deep learning algorithms for futuristic predictions of heart diseases and modeling. Data scraping and crawling offer a powerful tool to harvest and prepare the training and test datasets; however, the authors advocate caution because of ethical and legal issues, as well as the need to ensure the quality and accuracy of the data that are being collected.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Retrieval of Heterogeneous Proteomic Data for Machine Learning

Rafay

Aziz

Zia³

et al. 2023

JPM

View full text Add to dashboard Cite

show abstract

“…The fifth paper, entitled “IPDS: A semantic mediator‐based system using Spark for the integration of heterogeneous proteomics data sources” by Messaoudi et al 5 . focuses on facilitating the ingestion of big data, generated on various systems and platforms.…”

Section: Introductionmentioning

confidence: 99%

“…The fifth paper, entitled "IPDS: A semantic mediator-based system using Spark for the integration of heterogeneous proteomics data sources" by Messaoudi et al 5 focuses on facilitating the ingestion of big data, generated on various systems and platforms. It presents an overview of biomedical data integration systems focusing on ontology-based semantic systems and big data technologies based systems such as Apache Spark and proposes a semantic data integration system, called Integrated Proteomics Data System (IPDS), which uses a mediator approach.…”

mentioning

confidence: 99%

Towards understanding and harnessing the potential of Africa in digitalization

Benkrid

Badir

Lô

et al. 2020

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Towards understanding and harnessing the potential of Africa in digitalization 1 BACKGROUND Nowadays, the digital transformation is an intensive subject that refers to all the changes related to a process with the integration of advanced digital technologies such as cloud computing, Internet of Things, three-dimensional printing, artificial intelligence, and transportation in all aspects of human society. Digitalization affects any firm, any sector, any type of job, any function in organizations/institutions. Then it has become ubiquitous in multiple domains such as oil and gas, disease management, finance, banking, transportation, education, healthcare, agriculture, energy, environment, gastronomy, government services, and so forth. Africa is the world's second-largest and second-most-populous continent. Despite a wide range of natural resources, the continent suffers from many problems such as poverty, diseases, illiteracy, weak infrastructure, political instability, and conflicts. The continent features a relatively young population, as well as a diaspora of expatriate African researchers all willing to contribute to its development. Digital communication has spread very fast with improved access to the Internet. All these must enable an African shift to a successful digitalization transformation story with the promotion of technological advancements. The promotion of high education and research in Africa is one of the important keys for achieving digital transformation. This special issue has been launched by five researchers: four from African countries: Algeria, Morocco, Senegal, and Tunisia, and one from the African diaspora, working in France. This issue is dedicated to African young researchers contributing to digitalization efforts. An open call for papers has been organized, where it attracted 25 papers covering topics related to digitalization transformation, more particularly big data analytics, data integration, data mining, social media data exploitation, decision support systems, cloud computing, smart applications, Internet of Things, data security and risk, web services, quality of data transmission, recommendation, and combinatorial optimization methods. All submissions were peer-reviewed by at least two reviewers from our international program committee consisting of academia and industrials from 12 different countries and working on the various topics of our special issues. After two rounds of reviews, we finally accepted 11 papers, making an acceptance rate of 44%. One of the interesting characteristics of our accepted papers is that some of them integrate real case studies involving important domains in Africa such as Algerian mobile telecommunication and transportation services in the Maghreb countries. We

show abstract