Combinatorial Discriminant Analysis Applied to RNAseq Data Reveals a Set of 10 Transcripts as Signatures of Exposure of Cattle to Mycobacterium avium subsp. paratuberculosis

Malvisi, M.; Curti, Nico; Remondini, Daniel; Iorio, Maria Grazia De; Palazzo, Fiorentina; Gandini, G.; Vitali, Silvia; Polli, M.; Williams, J. L.; Minozzi, Giulietta

doi:10.3390/ani10020253

Cited by 6 publications

(5 citation statements)

References 45 publications

(77 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This procedure can be applied once, or recursively until the core network, i.e., a network with all nodes with at least two links, is reached. We have tested the efficacy of this empirical approach in some real cases 11,26 , obtaining a smaller-dimensional signature with comparable performance, even if we remark that this is an empirical result lacking a solid theoretical basis and further tools could be used for feature selection like the SHAP algorithm 27 . • (Optional) The classifier used in the feature selection and the final classification does not need to be a Discriminant Analysis classifier, but can in principle be any classifier.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A network approach for low dimensional signatures from high throughput data

Curti

Levi

Giampieri

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

One of the main objectives of high-throughput genomics studies is to obtain a low-dimensional set of observables—a signature—for sample classification purposes (diagnosis, prognosis, stratification). Biological data, such as gene or protein expression, are commonly characterized by an up/down regulation behavior, for which discriminant-based methods could perform with high accuracy and easy interpretability. To obtain the most out of these methods features selection is even more critical, but it is known to be a NP-hard problem, and thus most feature selection approaches focuses on one feature at the time (k-best, Sequential Feature Selection, recursive feature elimination). We propose DNetPRO, Discriminant Analysis with Network PROcessing, a supervised network-based signature identification method. This method implements a network-based heuristic to generate one or more signatures out of the best performing feature pairs. The algorithm is easily scalable, allowing efficient computing for high number of observables ($$10^3$$ 10 3 –$$10^5$$ 10 5 ). We show applications on real high-throughput genomic datasets in which our method outperforms existing results, or is compatible with them but with a smaller number of selected features. Moreover, the geometrical simplicity of the resulting class-separation surfaces allows a clearer interpretation of the obtained signatures in comparison to nonlinear classification models.

show abstract

Section: Methodsmentioning

confidence: 99%

“…a "windowed" optimal range of activity, Fig. 1b bottom) are much less common 11 . Thus, discriminant-based methods (and logistic regression methods alike) could provide good classification performances in these cases if applied in at least 2-dimensional spaces to account for situations as shown in Fig.…”

mentioning

confidence: 99%

A network approach for low dimensional signatures from high throughput data

Curti

Levi

Giampieri

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…In cattle, a 10-gene expression signature (TRPV4, RIC8B, IL5RA, ERF, CDC40, RDM1, EPHX1, STAU1, TLE1, and ASB8) has been described that is able to discriminate between ELISA-negative, clinically healthy and JD exposed animals [98]. This finding suggests that RNA expression analysis may be useful as a diagnostic tool to identify infected or exposed animals before they become seropositive, which can be detected with the ELISA test.…”

Section: Biomarker Discovery By Transcriptomic Approachesmentioning

confidence: 96%

Using Omics Approaches in the Discovery of Biomarkers for Early Diagnosis of Johne’s Disease in Sheep and Goats

Palazzo

Martino

Mancini

et al. 2021

Animals

Self Cite

View full text Add to dashboard Cite

Johne’s disease (JD) is caused by Mycobacterium avium subsp. paratuberculosis (MAP) and is an important and emerging problem in livestock; therefore, its control and prevention is a priority to reduce economic losses and health risks. Most JD research has been carried out on cattle, but interest in the pathogenesis and diagnosis of this disease in sheep and goats is greatest in developing countries. Sheep and goats are also a relevant part of livestock production in Europe and Australia, and these species provide an excellent resource to study and better understand the mechanism of survival of MAP and gain insights into possible approaches to control this disease. This review gives an overview of the literature on paratuberculosis in sheep and goats, highlighting the immunological aspects and the potential for “omics” approaches to identify effective biomarkers for the early detection of infection. As JD has a long incubation period before the disease becomes evident, early diagnosis is important to control the spread of the disease.

show abstract

Section: Dnetpro Algorithmmentioning

confidence: 99%

DNetPRO: A network approach for low-dimensional signatures from high-throughput data

Curti

Levi

Giampieri

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

One of the main objectives of high-throughput genomics studies is to obtain a low-dimensional set of observables - a signature - for sample classification purposes (diagnosis, prognosis, stratification). We propose DNetPRO, Discriminant Analysis with Network PROcessing, a supervised network-based signature identification method. The algorithm is easily scalable, allowing efficient computing for high number of observables (103 –105). We show applications on real high-throughput genomic datasets in which our method outperforms existing results or is compatible with them, but with a smaller number of selected features. Moreover, the geometrical simplicity of the resulting class-separation surfaces allows a clearer interpretation of the obtained signatures in comparison to nonlinear classification models.

show abstract

Combinatorial Discriminant Analysis Applied to RNAseq Data Reveals a Set of 10 Transcripts as Signatures of Exposure of Cattle to Mycobacterium avium subsp. paratuberculosis

Cited by 6 publications

References 45 publications

A network approach for low dimensional signatures from high throughput data

A network approach for low dimensional signatures from high throughput data

Using Omics Approaches in the Discovery of Biomarkers for Early Diagnosis of Johne’s Disease in Sheep and Goats

DNetPRO: A network approach for low-dimensional signatures from high-throughput data

Contact Info

Product

Resources

About