A robust and interpretable gene signature for predicting the lymph node status of primary T1/T2 oral cavity squamous cell carcinoma

Abstract

Oral cavity squamous cell carcinoma (OSCC) affects more than 30 000 individuals in the United States annually, with smoking and alcohol consumption being the main risk factors. Management of early-stage tumors usually includes surgical resection followed by postoperative radiotherapy in certain cases. The cervical lymph nodes (LNs) are the most common site for local metastasis, and elective neck dissection is usually performed if the primary tumor thickness is greater than 3.5 mm. However, postoperative histological examination often reveals that many patients with early-stage disease are negative for neck nodal metastasis, posing a pressing need for improved risk stratification to either avoid overtreatment or prevent the disease progression. To this end, we aimed to identify a primary tumor gene signature that can accurately predict cervical LN metastasis in patients with early-stage OSCC.Using gene expression profiles from 189 samples, we trained K-top scoring pairs models and identified six gene pairs that can distinguish primary tumors with nodal metastasis from those without metastasis. The signature was further validated on an independent cohort of 35 patients using real-time polymerase chain reaction (PCR) in which it achieved an area under the receiver operating characteristic (ROC) curve and accuracy of 90% and 91%, respectively. These results indicate that such signature holds promise as a quick and cost effective method for detecting patients at high risk

ZNF92, an unexplored transcription factor with remarkably distinct breast cancer over-expression associated with prognosis and cell-of-origin

“…Interestingly, 23% of published breast cancer signatures showed a weaker association with outcome than the median of the random signatures of the same size 53 , 54 . Therefore, we used combined k-top scoring pairs (k-TSPs) 55 , 56 , leave-one-out single gene removal (SGR) and single gene significance analysis to identify a nine-gene subset of ET-60, henceforth referred as ET-9 (Table 1 , Supplementary Fig. 8 ).…”

Using biological constraints to improve prediction in precision oncology

“…For example, we have shown that such mechanistic signatures derived from microarrays or RNA-Seq studies can be implemented using technologies such as RT-PCR, which further increases their translational value. 37 …”

Notch-based gene signature for predicting the response to neoadjuvant chemotherapy in triple-negative breast cancer

“…To accomplish this, we used gene expression profiles from 369 pre-NACT TNBC samples, of which 223 samples were used for training and the remainder for testing. We leveraged our group's recent demonstration of the importance of incorporating biological constraints in predictive classifiers [9,42] and used this approach to identify a subset of features predictive of NACT response. Specifically, we first designed a biological mechanism capturing the Notch signaling network by pairing genes known to be upregulated with those downregulated by Notch signaling.…”

“…Altogether, these findings support the validity of our approach in the development of predictive classifiers amenable to an effective translation to clinical practice. As such, classifiers developed using this method can be easily implemented as a clinical test using real-time polymerase chain reaction, even when trained on gene expression profiles from microarrays or RNA-seq [42].…”