Expanding the clinical utility of liquid biopsy by using liquid transcriptome and artificial intelligence

Most of the current utilization of liquid biopsy (LBx) is based on analyzing cell-free DNA(cfDNA). There is limited data on using cell-free RNA (cfRNA) levels (liquid transcriptome) in LBx. The major hurdles for using liquid transcriptome is its low level in circulation and the dilutional effects of...

Full description

Saved in:
Bibliographic Details
Main Authors: Maher Albitar, Ahmad Charifa, Sally Agersborg, Andrew Pecora, Andrew Ip, Andre Goy
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:The Journal of Liquid Biopsy
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S295019542400136X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053947943813120
author Maher Albitar
Ahmad Charifa
Sally Agersborg
Andrew Pecora
Andrew Ip
Andre Goy
author_facet Maher Albitar
Ahmad Charifa
Sally Agersborg
Andrew Pecora
Andrew Ip
Andre Goy
author_sort Maher Albitar
collection DOAJ
description Most of the current utilization of liquid biopsy (LBx) is based on analyzing cell-free DNA(cfDNA). There is limited data on using cell-free RNA (cfRNA) levels (liquid transcriptome) in LBx. The major hurdles for using liquid transcriptome is its low level in circulation and the dilutional effects of various tissues that may pour their RNA into circulation. We explored the potential of using artificial intelligence (AI) to normalize the cancer-specific cfRNA and to enable liquid transcriptome to predict diagnosis. cfRNA transcriptomic data from 1009 peripheral blood samples was generated by hybrid capture next generation sequencing (NGS). Using two-thirds of samples for training and one third for testing, we demonstrate that AI is able to distinguish between normal control (N = 368) and patients with solid tumors (N = 404) with AUC = 0.820 (95 % CI: 0.760–0.879), patients with myeloid neoplasms (N = 99) with AUC = 0.858 (95 % CI: 0.793–0.924) and patients with lymphoid neoplasms (N = 128) with AUC = 0.788 (95 % CI: 0.687–0.888). Specific diagnosis was also possible when patients with lung, breast, colorectal, and myelodysplastic subgroups were tested. This data suggests that liquid transcriptomics when used with AI has the potential of transforming “liquid biopsy” to “true” biopsy, replacing the need for tissue biopsy.
format Article
id doaj-art-befa01532a904e60b8fd727cf648cb17
institution DOAJ
issn 2950-1954
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series The Journal of Liquid Biopsy
spelling doaj-art-befa01532a904e60b8fd727cf648cb172025-08-20T02:52:24ZengElsevierThe Journal of Liquid Biopsy2950-19542024-12-01610027010.1016/j.jlb.2024.100270Expanding the clinical utility of liquid biopsy by using liquid transcriptome and artificial intelligenceMaher Albitar0Ahmad Charifa1Sally Agersborg2Andrew Pecora3Andrew Ip4Andre Goy5Genomic Testing Cooperative, Lake Forest, CA, USA; Corresponding author.Genomic Testing Cooperative, Lake Forest, CA, USAGenomic Testing Cooperative, Lake Forest, CA, USAJohn Theurer Cancer Center, Hackensack, NJ, USAJohn Theurer Cancer Center, Hackensack, NJ, USAJohn Theurer Cancer Center, Hackensack, NJ, USAMost of the current utilization of liquid biopsy (LBx) is based on analyzing cell-free DNA(cfDNA). There is limited data on using cell-free RNA (cfRNA) levels (liquid transcriptome) in LBx. The major hurdles for using liquid transcriptome is its low level in circulation and the dilutional effects of various tissues that may pour their RNA into circulation. We explored the potential of using artificial intelligence (AI) to normalize the cancer-specific cfRNA and to enable liquid transcriptome to predict diagnosis. cfRNA transcriptomic data from 1009 peripheral blood samples was generated by hybrid capture next generation sequencing (NGS). Using two-thirds of samples for training and one third for testing, we demonstrate that AI is able to distinguish between normal control (N = 368) and patients with solid tumors (N = 404) with AUC = 0.820 (95 % CI: 0.760–0.879), patients with myeloid neoplasms (N = 99) with AUC = 0.858 (95 % CI: 0.793–0.924) and patients with lymphoid neoplasms (N = 128) with AUC = 0.788 (95 % CI: 0.687–0.888). Specific diagnosis was also possible when patients with lung, breast, colorectal, and myelodysplastic subgroups were tested. This data suggests that liquid transcriptomics when used with AI has the potential of transforming “liquid biopsy” to “true” biopsy, replacing the need for tissue biopsy.http://www.sciencedirect.com/science/article/pii/S295019542400136XLiquid biopsycell-free DNA (cfDNA)cell-free RNA (cfRNA)Cancer diagnosisNext generation sequencingArtificial intelligence (AI)
spellingShingle Maher Albitar
Ahmad Charifa
Sally Agersborg
Andrew Pecora
Andrew Ip
Andre Goy
Expanding the clinical utility of liquid biopsy by using liquid transcriptome and artificial intelligence
The Journal of Liquid Biopsy
Liquid biopsy
cell-free DNA (cfDNA)
cell-free RNA (cfRNA)
Cancer diagnosis
Next generation sequencing
Artificial intelligence (AI)
title Expanding the clinical utility of liquid biopsy by using liquid transcriptome and artificial intelligence
title_full Expanding the clinical utility of liquid biopsy by using liquid transcriptome and artificial intelligence
title_fullStr Expanding the clinical utility of liquid biopsy by using liquid transcriptome and artificial intelligence
title_full_unstemmed Expanding the clinical utility of liquid biopsy by using liquid transcriptome and artificial intelligence
title_short Expanding the clinical utility of liquid biopsy by using liquid transcriptome and artificial intelligence
title_sort expanding the clinical utility of liquid biopsy by using liquid transcriptome and artificial intelligence
topic Liquid biopsy
cell-free DNA (cfDNA)
cell-free RNA (cfRNA)
Cancer diagnosis
Next generation sequencing
Artificial intelligence (AI)
url http://www.sciencedirect.com/science/article/pii/S295019542400136X
work_keys_str_mv AT maheralbitar expandingtheclinicalutilityofliquidbiopsybyusingliquidtranscriptomeandartificialintelligence
AT ahmadcharifa expandingtheclinicalutilityofliquidbiopsybyusingliquidtranscriptomeandartificialintelligence
AT sallyagersborg expandingtheclinicalutilityofliquidbiopsybyusingliquidtranscriptomeandartificialintelligence
AT andrewpecora expandingtheclinicalutilityofliquidbiopsybyusingliquidtranscriptomeandartificialintelligence
AT andrewip expandingtheclinicalutilityofliquidbiopsybyusingliquidtranscriptomeandartificialintelligence
AT andregoy expandingtheclinicalutilityofliquidbiopsybyusingliquidtranscriptomeandartificialintelligence