Empirical Analysis of Programmable ETL Tools

Biswas, Neepa; Sarkar, Anamitra; Mondal, Kartick Chandra

doi:10.1007/978-981-13-8581-0_22

Cited by 7 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…business intelligence space for data integration, the up-front cost of 16 those solutions led us to instead develop an open and lightweight 17 integration tool in Python using an agile approach, which became 18 SIRAD. 2), yet none of the 28 features identified provide for separation of PII or anonymization of 29 sensitive data [5][6][7][8]. This is consistent with our initial assessment that existing business intelligence tools would require the cost of adapting or [12] and to identify the effects of SNAP 97 participation on the nutritional content of purchased food [13].…”

Section: Introductionsupporting

confidence: 62%

SIRAD: Secure Infrastructure for Research with Administrative Data

Howison

Goggins

2022

Software Impacts

View full text Add to dashboard Cite

Governments collect large quantities of administrative records through the programs and services they administer. These data can generate important insights into new policy and evaluations of existing policy but are often difficult to access because they are siloed across government agencies and subject to privacy laws and regulations. We developed a data integration pipeline, SIRAD, that securely joins administrative data sets from multiple government agencies and replaces personally identifiable information with anonymous identifiers to maintain privacy while facilitating research, insights, and fact-based policy. Data processed with SIRAD have been used in nine research studies and 75 policy memos.

show abstract

Section: Introductionsupporting

confidence: 62%

SIRAD: Secure Infrastructure for Research with Administrative Data

Howison

Goggins

2022

Software Impacts

View full text Add to dashboard Cite

show abstract

“…Overall, the process of extracting, transforming, and loading ETL data from homogeneous or heterogeneous sources was established to access our data (Biswas et al, 2020;Biswas et al, 2018). In short, it was an essential component in cleansing, customizing, reformatting, integrating, and inserting the prerequired data (Greiff et al, 2015;Tecnico, 2015).…”

Section: Score Prioritization Genementioning

confidence: 99%

Adjustment of p-value expression to ontology using machine learning for genetic prediction, prioritization, interaction, and its validation in glomerular disease

Ettetuani,

Chahboune,

Moussa

2023

Front. Genet.

View full text Add to dashboard Cite

The results of gene expression analysis based on p-value can be extracted and sorted by their absolute statistical significance and then applied to multiple similarity scores of their gene ontology (GO) terms to promote the combination and adjustment of these scores as essential predictive tasks for understanding biological/clinical pathways. The latter allows the possibility to assess whether certain aspects of gene function may be associated with other varieties of genes, to evaluate regulation, and to link them into networks that prioritize candidate genes for classification by applying machine learning techniques. We then detect significant genetic interactions based on our algorithm to validate the results. Finally, based on specifically selected tissues according to their normalized gene expression and frequencies of occurrence from their different biological and clinical inputs, a reported classification of genes under the subject category has validated the abstract (glomerular diseases) as a case study.

show abstract

“…Overall, a full process of extracting transforming, and loading (ETL) data from homogeneous or heterogeneous sources [52,53] was established to access our data. In short, it's an essential component in cleansing, customization, reformatting, integration, and insertion of our prerequired data [54,55,56].…”

Section: Score Prioritization (Genementioning

confidence: 99%

Adjustment of p-Value Expression To Ontology Using Machine Learning For Genetic Prediction, Prioritization, Interaction, And Its Validation In Glomerular Disease

Ettetuani

Chahboune

Moussa

2022

Preprint

View full text Add to dashboard Cite

Background: The selection of gene expression mixed to multiple similarity scores of their gene ontology terms (GO), were adjusted by our algorithm as essential prediction tasks for evaluating the regulatory pathways. Moreover applying machine learning techniques, in order to link the gene products into networks that prioritize candidate genes as classification. Finally detecting some significant genetic interactions by applying our algorithm model as validation of the results. Results: Experimental validation of all associations facilitates the discovery of causative genes known to be related to glomerular diseases (GD). As well as EGR1, IL33, BMP2, SLAMF8. In which their GO annotations related to this gene include kidney vasculature development, regulation of cell activation/ inflammatory/immune effector/adaptive immune/glomerulus/glomerular mesangial cell proliferation development, etc. Other genes as TNXA, FCER1A, NME3, FMOD, BTG2, PTGER4, AXL, CYP1A2, CYTL1, BHLHE40, IFI16, SPON1, ETNPPL, COL14A1, ITGAV, MYOZ2, CAMK2A, SORT1, RANBP1, in which their variants information include complement a set of C3, C4, and C7 measurement, serum IgE/IgA measurement, c-reactive protein measurement, nephrotic syndrome, immune system disease, tuberculosis, glomerular filtration rate, chronic kidney disease, etc. The lasts enable a rapid interpretation of complex gene expression studies. As well, other high-throughput genomics assays illustrate an overview of a computational model for gene prioritization and their genetic interactions. Conclusions: The furtherance of combining and adjusting the genes expression to multiple similarity scores of their gene ontology (GO) and interacting all possible cross-association of the results reported classification of genes between among to the subject category and validated the abstracts.

show abstract

Empirical Analysis of Programmable ETL Tools

Cited by 7 publications

References 11 publications

SIRAD: Secure Infrastructure for Research with Administrative Data

SIRAD: Secure Infrastructure for Research with Administrative Data

Adjustment of p-value expression to ontology using machine learning for genetic prediction, prioritization, interaction, and its validation in glomerular disease

Adjustment of p-Value Expression To Ontology Using Machine Learning For Genetic Prediction, Prioritization, Interaction, And Its Validation In Glomerular Disease

Contact Info

Product

Resources

About