Binary classification of copy number alteration profiles in liquid biopsy with potential clinical impact in advanced NSCLC

Abstract

Liquid biopsy has recently emerged as an important tool in clinical practice particularly for lung cancer patients. We retrospectively evaluated cell-free DNA analyses performed at our Institution by next generation sequencing methodology detecting the major classes of genetic alterations. Starting from the graphical representation of chromosomal alterations provided by the analysis software, we developed a support vector machine classifier to automatically classify chromosomal profiles as stable (SCP) or unstable (UCP). High concordance was found between our binary classification and tumor fraction evaluation performed using shallow whole genome sequencing. Among clinical features, UCP patients were more likely to have ≥ 3 metastatic sites and liver metastases. Longitudinal assessment of chromosomal profiles in 33 patients with lung cancer receiving immune checkpoint inhibitors (ICIs) showed that only patients that experienced early death or hyperprogressive disease retained or acquired an UCP within 3 weeks from the beginning of ICIs. UCP was not observed following ICIs among patients that experienced progressive disease or clinical benefit. In conclusion, our binary classification, applied to whole copy number alteration profiles, could be useful for clinical risk stratification during systemic treatment for non-small cell lung cancer patients.

Keywords: Copy number alterations; Immunotherapy; Liquid biopsy; Machine learning; Tumor fraction.

Figure 1

Chromosomal profiles in cfDNA samples analyzed by AVENIO ctDNA Expanded Kit. The image shows two examples of cfDNA samples with a stable pattern (SCP, panel a) and two examples of cfDNA samples with aneuploidy (UCP, panel b), as visually classified by two independent experienced researchers. The panel (c) shows two examples of cfDNA samples from healthy controls (Ctrl). Samples in panels (a) and (b) are from patients, whose plasma was analyzed by NGS with AVENIO ctDNA Expanded kit at diagnosis to assess possible actionable mutations. For each plot, the x-axis represents the loci targeted by the AVENIO Expanded kit, while the y-axis represents the log2 copy ratio observed at these loci. SCP stable chromosomal profile, UCP unstable chromosomal profile, Ctrl healthy donor.

Figure 2

Concordance between sWGS analysis and binary SCP/UCP classification of chromosomal profiles. SCP and UCP representative cases analyzed with AVENIO expanded panel and the binary classifier are shown on the left panel. sWGS analysis and tumor fraction detection were performed in parallel as shown on the right panel. SCP stable chromosomal profile, UCP unstable chromosomal profile.

Figure 3

Association between the SCP/UCP binary classification and clinical outcome. SCP/ UCP classification was performed in 33 patients enrolled in the MAGIC-1 study both at baseline (T1) and following one cycle of ICIs (T2). For clinical outcome, patients were divided in 2 groups according the presence or absence of potential detrimental effects (ED + HPD and PD + CB, respectively). HPD hyperprogressive disease, ED early death, PD progressive disease, CB clinical benefit, SCP stable chromosomal profile, UCP unstable chromosomal profile.

Figure 4

Representative analyses of dynamic assessment of CNAs and response to immunotherapy. Representative plots of CNAs generated using AVENIO ctDNA Expanded Kit for patients undergoing immunotherapy treatment. Analyses were performed at baseline (T1) and following 1 cycle of ICI (T2); T3 represents CT scan re-evaluation. In the upper panel, plots of two patients that belong to the CB group are shown (M#185 and M#251). In the lower panel, two patients that experienced ED are included (M#191 and M#301). ED early death, CB clinical benefit, SCP stable chromosomal profile, UCP unstable chromosomal profile.