Stephen‐John Sammut

This paper presents a machine learning-assisted vibrational spectroscopy method for rapid, label-free DNA fragment length analysis with high accuracy.

This paper demonstrates that ATR-FTIR spectroscopy with regression models can rapidly and non-destructively quantify DNA methylation and hydroxymethylation in DNA samples, including circulating tumor DNA.

Path2Space predicts spatial gene expression and tumor microenvironment from histopathology slides, identifying new breast cancer subgroups and improving biomarker prediction.

This paper develops a machine learning-assisted ATR-FTIR spectroscopy method to rapidly and label-free quantify cancer biomarkers like CA125 in clinical samples.

This paper develops DECODEM to predict chemotherapy response by integrating deconvolved expression patterns of immune, stromal, and tumor cells in breast cancer, finding that cell-type-specific expression is predictive of response.

This study shows chemotherapy induces a Wnt-active diapause-DTP state in breast cancer cells, which can be targeted by combined Wnt and chemotherapy inhibition.

This paper introduces a method that uses causal signals from genetic screens to improve the robustness and interpretability of AI models for cancer medicine, showing effective generalization across data and biological contexts.

This study uses ctDNA from metastatic breast cancer patients and a Bayesian model to predict treatment response and progression-free survival, outperforming alternative methods.

A personalized ctDNA test achieves high accuracy for residual disease detection after neoadjuvant therapy in breast cancer.

NG-TAS is a cost-effective method for profiling ctDNA mutations in cancer patients, showing consistent detection of mutations at >1% allele fraction.

This study demonstrates that shallow whole genome sequencing (sWGS) can robustly profile copy number alterations in FFPE breast cancer tissues, even with low-quality DNA.