GARFIELD-NGS: Genomic vARiants FIltering by dEep Learning moDels in NGS

Ravasio, V.; Ritelli, Marco; Legati, Andrea; Giacopuzzi, Edoardo

doi:10.1093/bioinformatics/bty303

Cited by 29 publications

(23 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the rs190436077 causes a Glutamate (with a negatively charged side chain) to Glutamine (carrying a neutral side chain) change at the 79th amino acid and it has also been predicted to disrupt an ESE site. Moreover, it falls within the loop connecting the rst two helical structures of the protein, which contributes to the formation of the binding site for IL6/IL6R complex to gp130 (23). The rs190436077 may therefore be experimentally investigated to verify its potential role on the alteration of IL6 binding ability and could be also evaluated for potential effects on the a nity with IL6 drugs, which may cause an altered drug response or effectiveness.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Investigation of genetic variations of IL6 and IL6R as potential prognostic and pharmacogenetics biomarkers: implications for COVID19 and neuroinflammatory disorders.

Strafella

Caputo

Termine

et al. 2020

Preprint

View full text Add to dashboard Cite

In the present study, we investigated the distribution of genetic variations in IL6 and IL6R genes, which may be employed as prognostic and pharmacogenetic biomarkers for COVID-19 and neurodegenerative diseases. The study was performed on 271 samples representative of the Italian general population and identified seven variants (rs140764737, rs142164099, rs2069849, rs142759801, rs190436077, rs148171375, rs13306435) in IL6 and five variants (rs2228144, rs2229237, rs2228145, rs28730735, rs143810642) within IL6R, respectively. These variants have been predicted to affect the expression and binding ability of IL6 and IL6R. The Ingenuity Pathway Analysis (IPA) showed that IL6 and IL6R appeared to be implicated in several pathogenetic mechanisms associated with COVID19 severity and mortality as well as with neurodegenerative diseases mediated by neuroinflammation. Thus, the availability of IL6-IL6R-related biomarkers for COVID19 disease may be helpful to counteract harmful complications and prevent multi-organ failure. At the same time, IL6-IL6R-related biomarkers could also be useful for assessing the susceptibility and progression of neuroinflammatory disorders and undertake the most suitable treatment strategies to improve patients’ prognosis and quality of life. In conclusion, this study showed how IL6 pleiotropic activity could be exploited to meet different clinical needs and realize precision medicine protocols for chronic, age-related and modern public health emergencies.

show abstract

Section: Resultsmentioning

confidence: 99%

“…In particular, vcfR is a package that enables to visualize, manipulate and perform the quality control of VCF data [22]. GARFIELD-NGS is an informatics tool, which relies on deep learning models to dissect false and true variants in exome sequencing experiments [23].…”

Section: Methodsmentioning

confidence: 99%

Investigation of genetic variations of IL6 and IL6R as potential prognostic and pharmacogenetics biomarkers: implications for COVID19 and neuroinflammatory disorders.

Strafella

Caputo

Termine

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Following this, needlestack does not correct for sample-specific artifacts such as (i) (sample specific) stochastic alignment errors and we recommend to use it in conjunction with an assembly based re-alignment method (27); (ii) polymerase errors introduced in PCR amplification step; (iii) complex errors leading to features like strand bias. Such errors remain a feature in NGS data ( Figures 2C and 3A), thus additional error correction (28,29) and/or validation techniques are needed. This can be achieved with hard filtering on the output statistics such as the VAF or the strand bias, but also with machine-learning-based approaches applied to multiple variant summary statistics when validated data are available to inform the model.…”

Section: Discussionmentioning

confidence: 99%

Needlestack: an ultra-sensitive variant caller for multi-sample next generation sequencing data

Delhomme

Avogbe

Gabriel

et al. 2019

Preprint

View full text Add to dashboard Cite

ABSTRACTThe emergence of Next-Generation Sequencing (NGS) has revolutionized the way of reaching a genome sequence, with the promise of potentially providing a comprehensive characterization of DNA variations. Nevertheless, detecting somatic mutations is still a difficult problem, in particular when trying to identify low abundance mutations such as subclonal mutations, tumour-derived alterations in body fluids or somatic mutations from histological normal tissue. The main challenge is to precisely distinguish between sequencing artefacts and true mutations, particularly when the latter are so rare they reach similar abundance levels as artefacts. Here, we present needlestack, a highly sensitive variant caller, which directly learns from the data the level of systematic sequencing errors to accurately call mutations. Needlestack is based on the idea that the sequencing error rate can be dynamically estimated from analyzing multiple samples together. We show that the sequencing error rate varies across alterations, illustrating the need to precisely estimate it. We evaluate the performance of needlestack for various types of variations, and we show that needlestack is robust among positions and outperforms existing state-of-the-art method for low abundance mutations. Needlestack, along with its source code is freely available on the GitHub plateform: https://github.com/IARCbioinfo/needlestack.

show abstract

“…The model with its wrapper code is merely 219 kilobases in size and can easily run on any modern-day POSIX compliant computer and a graphics card isn’t necessary for the same. A similar tool, GARFIELD-NGS was released in 2018 by Ravasio et al , 4 but the has much lower accuracy of 0.804 for INDELs and comparable accuracy of 0.955 for SNVs. Also, it utilizes different models for INDELs and SNVs, is incapable of multiplexing and is developed in H 2 O.ai, which is a commercial software.…”

Section: Discussionmentioning

confidence: 99%

Intelli-NGS: Intelligent NGS, a deep neural network-based artificial intelligence to delineate good and bad variant calls from IonTorrent sequencer data

Singh

Bhatia

2019

Preprint

View full text Add to dashboard Cite

show abstract

GARFIELD-NGS: Genomic vARiants FIltering by dEep Learning moDels in NGS

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 29 publications

References 11 publications

Investigation of genetic variations of IL6 and IL6R as potential prognostic and pharmacogenetics biomarkers: implications for COVID19 and neuroinflammatory disorders.

Investigation of genetic variations of IL6 and IL6R as potential prognostic and pharmacogenetics biomarkers: implications for COVID19 and neuroinflammatory disorders.

Needlestack: an ultra-sensitive variant caller for multi-sample next generation sequencing data

Intelli-NGS: Intelligent NGS, a deep neural network-based artificial intelligence to delineate good and bad variant calls from IonTorrent sequencer data

Contact Info

Product

Resources

About