Early clinical trial unit tumor board: a real-world experience in a national cancer network

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.

RNA-sequencing based first choice of treatment and determination of risk in multiple myeloma

Background

Immunotherapeutic targets in multiple myeloma (MM) have variable expression height and are partly expressed in subfractions of patients only. With increasing numbers of available compounds, strategies for appropriate choice of targets (combinations) are warranted. Simultaneously, risk assessment is advisable as patient's life expectancy varies between months and decades.

Methods

We first assess feasibility of RNA-sequencing in a multicenter trial (GMMG-MM5, n=604 patients). Next, we use a clinical routine cohort of untreated symptomatic myeloma patients undergoing autologous stem cell transplantation (n=535, median follow-up (FU) 64 months) to perform RNA-sequencing, gene expression profiling (GEP), and iFISH by ten-probe panel on CD138-purified malignant plasma cells. We subsequently compare target expression to plasma cell precursors, MGUS (n=59), asymptomatic (n=142) and relapsed (n=69) myeloma patients, myeloma cell lines (n=26), and between longitudinal samples (MM vs. relapsed MM). Data are validated using the independent MMRF CoMMpass-cohort (n=767, FU 31 months).

Results

RNA-sequencing is feasible in 90.8% of patients (GMMG-MM5). Actionable immune-oncological targets (n=19) can be divided in those expressed in all normal and >99% of MM-patients (CD38, SLAMF7, BCMA, GPRC5D, FCRH5, TACI, CD74, CD44, CD37, CD79B), those with expression loss in subfractions of MM-patients (BAFF-R [81.3%], CD19 [57.9%], CD20 [82.8%], CD22 [28.4%]), aberrantly expressed in MM (NY-ESO1/2 [12%], MUC1 [12.7%], CD30 [4.9%], mutated BRAF V600E/K [2.1%]), and resistance-conveying target-mutations e.g., against part but not all BCMA-directed treatments. Risk is assessable regarding proliferation, translated GEP- (UAMS70-, SKY92-, RS-score) and de novo (LfM-HRS) defined risk scores. LfM-HRS delineates three groups of 40%, 38%, and 22% of patients with 5-year and 12-year survival rates of 84% (49%), 67% (18%), and 32% (0%). R-ISS and RNA-sequencing identify partially overlapping patient populations, with R-ISS missing, e.g., 30% (22/72) of highly proliferative myeloma.

Conclusion

RNA-sequencing based assessment of risk and targets for first choice treatment is possible in clinical routine.