Language model enables end-to-end accurate detection of cancer from cell-free DNA
View abstract on PubMed
Summary
This summary is machine-generated.We developed the Affordable Cancer Interception and Diagnostics (ACID) model for cancer diagnosis using cell-free DNA (cfDNA) sequencing reads. ACID demonstrates superior performance in detecting cancer and hepatocellular carcinoma, offering an affordable and efficient diagnostic approach.
Area Of Science
- Genomics
- Bioinformatics
- Computational Biology
Background
- Early cancer detection is crucial for improving patient outcomes.
- Current methods for cancer diagnosis from cell-free DNA (cfDNA) can be complex and costly.
- Analyzing raw sequencing reads directly presents a challenge for diagnostic models.
Purpose Of The Study
- To introduce the Affordable Cancer Interception and Diagnostics (ACID) model for cancer diagnosis.
- To evaluate ACID's performance using raw cfDNA sequencing reads.
- To establish an efficient and affordable end-to-end paradigm for cancer detection.
Main Methods
- Formulated ACID as an autoregressive language model.
- Pretrained ACID using concatenated raw sequencing reads and diagnostic labels.
- Benchmarked ACID against three existing methods on whole-genome and bisulfite sequencing datasets.
Main Results
- ACID significantly outperformed the best benchmarked method in overall cancer diagnosis (AUROC, 0.924 vs. 0.853) and hepatocellular carcinoma detection (AUROC, 0.981 vs. 0.917).
- ACID achieved high accuracy using as few as 10,000 reads per sample.
- ACID demonstrated superior performance on bisulfite sequencing datasets compared to benchmarked methods.
Conclusions
- ACID provides an affordable, simple, and efficient end-to-end approach for cancer detection.
- The model effectively utilizes raw cfDNA sequencing reads for diagnosis.
- ACID shows promise for improving accessibility and accuracy in cancer diagnostics.
Related Concept Videos
Cells and tissues must meticulously coordinate their activities for the normal functioning of the human body. Therefore, they exhibit socially responsible behavior - resting, growing, dividing, differentiating, or dying - for the organism’s benefit. Cancer arises when cells divide uncontrollably and invade other tissues or organs.
Although people have known about cancer for centuries, it was only in 1761 that Giovanni Morgagni of Padua performed a detailed autopsy of...
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...

