Sundar R, Kumarakulasinghe NB, Chan YH, et al. - Researchers investigated a gene signature to predict survival advantage from paclitaxel chemotherapy in patients suffering from gastric cancer (GC). GC samples were used from SAMIT [Stomach cancer Adjuvant Multi-Institutional group Trial was a 2×2 factorial randomised phase III study wherein GC patients were randomly assigned to Pac-S-1 (paclitaxel +S-1{an oral combination of tegafur, gimeracil and oteracil}), Pac-UFT (paclitaxel +UFT{an oral combination of uracil and tegafur}), S-1 alone or UFT alone following curative surgery]. From the Pac-S-1 training cohort, the random forest model produced a 19-gene signature allocating patients to two groups: Pac-Sensitive and Pac-Resistant. A significant improvement in disease free survival was seen in Pac-Sensitive patients in the Pac-UFT validation cohort. Benefit for Pac-Sensitive was predicted by the signature, in the external Pac-Ram (paclitaxel and ramucirumab) validation cohort. Overall, a gene signature representing the first predictive biomarker for paclitaxel benefit was discovered herein by employing machine-learning techniques on one of the largest GC trials (SAMIT).