ALFAssay: A feed‑forward neural network for quantitative fragmentomics‑based ctDNA profiling in breast cancer.

AI / informaticsPLoS computational biology· Jul 2026

ALFAssay: A feed‑forward neural network for quantitative fragmentomics‑based ctDNA profiling in breast cancer.

Alexandra Stanciu, Andrea Gombos, Elisa Agostinetto … Michail Ignatiadis

Read paper

Molecular Genetic PathologyAI / informaticsQ1IF 3.5

New neural network tool detects circulating tumor DNA in breast cancer with 87% sensitivity.

ALFAssay: A feed‑forward neural network for quantitative fragmentomics‑based ctDNA profiling in breast cancer.

Alexandra Stanciu … Michail Ignatiadis

PLoS computational biology · Jul 2026 · Q1 in Genetics

Background

The analysis of cell‑free DNA (cfDNA) is transforming cancer diagnostics, yet quantifying the fraction of circulating tumour DNA (ctDNA) from shallow whole‑genome sequencing (sWGS) remains challenging in tumours with low copy‑number aberration burden.

Results

correctly flags most cancers with tumor DNA in the blood

Sensitivity

0.87

Specificity

0.94

More results

We introduce ALFAssay, a feed‑forward neural network that estimates ctDNA fraction from fragmentation profiles of cfDNA in breast cancer.

The resulting 408‑dimensional vectors are input to a fully connected network trained against ichorCNA‑derived ctDNA fractions using five‑fold cross‑validation.

More results

Its ctDNA predictions stratify patients by progression‑free survival and add complementary prognostic value to available tools.

“

Conclusion

ALFAssay thus expands the bioinformatics toolkit for ctDNA quantification and highlights the potential of fragmentation signatures to augment multi‑modal liquid‑biopsy workflows.

ALFAssay: A feed‑forward neural network for quantitative fragmentomics‑based ctDNA profiling in breast cancer.

ALFAssay: A feed‑forward neural network for quantitative fragmentomics‑based ctDNA profiling in breast cancer.

Related papers