Investigators from Hackensack Meridian John Theurer Cancer Center (JTCC), part of the NCI-designated Lombardi Comprehensive Cancer Center at Georgetown University and Genetic Testing Cooperative Inc. (GTC) published a groundbreaking study demonstrating the reliability of combining next-generation sequencing and artificial intelligence to accurately diagnose subtypes of blood cancers and solid tumors. This approach has the potential to become a part of routine cancer care and lead to improved patient outcomes. The study was published in the January 2023 issue of the American Journal of Pathology.
An accurate diagnosis of cancer is essential to ensure a patient receives the most effective therapy. But numerous studies have shown that errors in the diagnosis and classification of cancers continue to be a significant issue in current clinical practice. Relying only on the expertise of a pathologist and the way a tumor looks under a microscope can lead to significant discrepancies in cancer identification because of the subjective nature of the diagnostic process.
The JTCC and GTC researchers investigated a targeted transcriptome and artificial intelligence to diagnose blood cancers and solid tumors. DNA is the genetic code that carries the instructions for all the functions in the human body. In order for these instructions to be carried out, the DNA must be read and transcribed into RNA. A transcriptome is a collection of gene readouts in a cell. Analyzing the RNA of cancerous tissues by evaluating the transcriptome provides a tremendous amount of information about a cancer’s biology and surrounding environment.
In this study, RNA samples from 2,606 hematologic neoplasms and 2,038 solid tumors as well as normal bone marrow and lymph node samples were analyzed using next-generation sequencing with a targeted 1,408-gene panel. Twenty subtypes of hematologic neoplasms and 24 subtypes of solid tumors were identified. Machine learning was highly accurate for distinguishing between different diagnoses.
“Partnering state-of-the-art genomics with artificial intelligence, our team at JTCC and GTC demonstrated the potential of a new paradigm for more accurate and timely cancer diagnosis, which may improve treatment outcomes,” said senior author Maher Albitar, MD, CEO of GTC, which partners with Hackensack Meridian Health to run a genomic testing laboratory in Hackensack that offers next-generation sequencing.
The data indicate that targeted transcriptome analysis combined with artificial intelligence is highly useful for diagnosing and classifying various cancers.
“These results open the door for supplementing and eventually replacing current diagnostic technologies with a new approach that, in addition to more accurate diagnosis, should eventually lead to real-time disease monitoring during therapy to better guide care,” explained study co-authors Andre Goy, MD, MS, chairman and executive director of JTCC, and Andrew Pecora, MD, co-chief of the Division of Skin Cancer and Sarcoma at JTCC.
Concluded Robert C. Garrett, FACHE, CEO, Hackensack Meridian Health, “Our efforts in this area further demonstrate our commitment to innovation using advanced genomic and information technology to improve treatment outcomes for our patients with cancer.”
Source – Hackensack Meridian Health
Zhang H, Qureshi MA, Wahid M, Charifa A, Ehsan A, Ip A, De Dios I, Ma W, Sharma I, McCloskey J, Donato M, Siegel D, Gutierrez M, Pecora A, Goy A, Albitar M. (2023) Differential Diagnosis of Hematologic and Solid Tumors Using Targeted Transcriptome and Artificial Intelligence. Am J Pathol 193(1):51-59. [article]
Investigators from Hackensack Meridian John Theurer Cancer Center (JTCC), part of the NCI-designated Lombardi Comprehensive Cancer Center at Georgetown University and Genetic Testing Cooperative Inc. (GTC) published a groundbreaking study demonstrating the reliability of combining next-generation sequencing and artificial intelligence to accurately diagnose subtypes of blood cancers and solid tumors. This approach has the potential to become a part of routine cancer care and lead to improved patient outcomes. The study was published in the January 2023 issue of the American Journal of Pathology.
An accurate diagnosis of cancer is essential to ensure a patient receives the most effective therapy. But numerous studies have shown that errors in the diagnosis and classification of cancers continue to be a significant issue in current clinical practice. Relying only on the expertise of a pathologist and the way a tumor looks under a microscope can lead to significant discrepancies in cancer identification because of the subjective nature of the diagnostic process.
The JTCC and GTC researchers investigated a targeted transcriptome and artificial intelligence to diagnose blood cancers and solid tumors. DNA is the genetic code that carries the instructions for all the functions in the human body. In order for these instructions to be carried out, the DNA must be read and transcribed into RNA. A transcriptome is a collection of gene readouts in a cell. Analyzing the RNA of cancerous tissues by evaluating the transcriptome provides a tremendous amount of information about a cancer’s biology and surrounding environment.
In this study, RNA samples from 2,606 hematologic neoplasms and 2,038 solid tumors as well as normal bone marrow and lymph node samples were analyzed using next-generation sequencing with a targeted 1,408-gene panel. Twenty subtypes of hematologic neoplasms and 24 subtypes of solid tumors were identified. Machine learning was highly accurate for distinguishing between different diagnoses.
The data indicate that targeted transcriptome analysis combined with artificial intelligence is highly useful for diagnosing and classifying various cancers.
Source – Hackensack Meridian Health
Zhang H, Qureshi MA, Wahid M, Charifa A, Ehsan A, Ip A, De Dios I, Ma W, Sharma I, McCloskey J, Donato M, Siegel D, Gutierrez M, Pecora A, Goy A, Albitar M. (2023) Differential Diagnosis of Hematologic and Solid Tumors Using Targeted Transcriptome and Artificial Intelligence. Am J Pathol 193(1):51-59. [article]
Related Posts
POND-seq enables non-destructive RNA sequencing in living cells
Worm’s radical transformation shows metamorphosis can change the functions of cells
New method allows scientists to follow gene activity over time in the same cells
Single-cell and single-embryo RNA sequencing
RNA sequencing reveals functional chimeric mRNAs in mammalian immunity
Deep learning improves microRNA target prediction from sequence
Atlas of the brain’s striatum could guide researchers to new drug treatments
scLS – a computationally efficient differentially expressed gene detection algorithm
Spatial mapping of RNA turnover kinetics in the mouse brain
Immune cells offer insights on billion-dollar virus
SPIDER improves spatial transcriptomics data using single-cell RNA sequencing
Ultrafast and reference-free sequence discovery in single-cell data
ARCADIA combines RNA sequencing and spatial proteomics to reveal how tissue location shapes cell behavior
An end-to-end computational framework for “Record-seq” transcriptional recording data
A functionally integrated cross-tissue alternative splicing program during short-term calorie restriction
ExoShorkie – predicting RNA-seq coverage of exogenous genomes in yeast by transfer learning
Dietary oxidized plant sterol shifts macrophage state to fuel aortic inflammation
Bonsai reconstructs tree representations for distortion-free visualization and exploration of high-dimensional data
MiRQuery – a user-friendly web app for the interactive analysis and visualization of microRNA sequencing data
RNA sequencing resolves cryptic pathogenic variants in mitochondrial disease
Investigators from Hackensack Meridian John Theurer Cancer Center (JTCC), part of the NCI-designated Lombardi Comprehensive Cancer Center at Georgetown University and Genetic Testing Cooperative Inc. (GTC) published a groundbreaking study demonstrating the reliability of combining next-generation sequencing and artificial intelligence to accurately diagnose subtypes of blood cancers and solid tumors. This approach has the potential to become a part of routine cancer care and lead to improved patient outcomes. The study was published in the January 2023 issue of the American Journal of Pathology.
An accurate diagnosis of cancer is essential to ensure a patient receives the most effective therapy. But numerous studies have shown that errors in the diagnosis and classification of cancers continue to be a significant issue in current clinical practice. Relying only on the expertise of a pathologist and the way a tumor looks under a microscope can lead to significant discrepancies in cancer identification because of the subjective nature of the diagnostic process.
The JTCC and GTC researchers investigated a targeted transcriptome and artificial intelligence to diagnose blood cancers and solid tumors. DNA is the genetic code that carries the instructions for all the functions in the human body. In order for these instructions to be carried out, the DNA must be read and transcribed into RNA. A transcriptome is a collection of gene readouts in a cell. Analyzing the RNA of cancerous tissues by evaluating the transcriptome provides a tremendous amount of information about a cancer’s biology and surrounding environment.
In this study, RNA samples from 2,606 hematologic neoplasms and 2,038 solid tumors as well as normal bone marrow and lymph node samples were analyzed using next-generation sequencing with a targeted 1,408-gene panel. Twenty subtypes of hematologic neoplasms and 24 subtypes of solid tumors were identified. Machine learning was highly accurate for distinguishing between different diagnoses.
The data indicate that targeted transcriptome analysis combined with artificial intelligence is highly useful for diagnosing and classifying various cancers.
Source – Hackensack Meridian Health
Zhang H, Qureshi MA, Wahid M, Charifa A, Ehsan A, Ip A, De Dios I, Ma W, Sharma I, McCloskey J, Donato M, Siegel D, Gutierrez M, Pecora A, Goy A, Albitar M. (2023) Differential Diagnosis of Hematologic and Solid Tumors Using Targeted Transcriptome and Artificial Intelligence. Am J Pathol 193(1):51-59. [article]
Related Posts
POND-seq enables non-destructive RNA sequencing in living cells
Worm’s radical transformation shows metamorphosis can change the functions of cells
New method allows scientists to follow gene activity over time in the same cells
Single-cell and single-embryo RNA sequencing
RNA sequencing reveals functional chimeric mRNAs in mammalian immunity
Deep learning improves microRNA target prediction from sequence
Atlas of the brain’s striatum could guide researchers to new drug treatments
scLS – a computationally efficient differentially expressed gene detection algorithm
Spatial mapping of RNA turnover kinetics in the mouse brain
Immune cells offer insights on billion-dollar virus
SPIDER improves spatial transcriptomics data using single-cell RNA sequencing
Ultrafast and reference-free sequence discovery in single-cell data
ARCADIA combines RNA sequencing and spatial proteomics to reveal how tissue location shapes cell behavior
An end-to-end computational framework for “Record-seq” transcriptional recording data
A functionally integrated cross-tissue alternative splicing program during short-term calorie restriction
ExoShorkie – predicting RNA-seq coverage of exogenous genomes in yeast by transfer learning
Dietary oxidized plant sterol shifts macrophage state to fuel aortic inflammation
Bonsai reconstructs tree representations for distortion-free visualization and exploration of high-dimensional data
MiRQuery – a user-friendly web app for the interactive analysis and visualization of microRNA sequencing data
RNA sequencing resolves cryptic pathogenic variants in mitochondrial disease
Stay Connected
Submit a Post to the Blog
Recent Posts
Subscribe to the RNA-Seq Blog
RNA-Seq Products & Services