Machine Learning Provides an Accurate Classification of Diffuse Large B-Cell Lymphoma from Immunohistochemical Data.

BACKGROUND: The classification of diffuse large B-cell lymphomas into Germinal Center (GCB) and non-GC subtypes defines disease subgroups which are different both in terms of gene expression and prognosis. Given their clinical significance, several classification algorithms have been designed, some by making use of widely availability immunohistochemical techniques. Despite their high concordance with gene expression profiles (GEP) and prognostic value, these algorithms were based on technical and biological assumptions that could be improved in terms of performance for classification. METHODS: In order to overcome this limitation, a new algorithm was obtained by analyzing a previously published dataset of 475 patients by using an automatic classification tree method. RESULTS: The resulting algorithm classifies correctly 91.6% of the cases when compared to GEP, displaying a Receiver-Operator Characteristic (ROC) area under the curve of 0.934. Noteworthy features of this algorithm include the capability to classify GEP-unclassifiable cases and a significant prognostic value, both in terms of overall survival (60 months for non-GC vs not reached for GCB, P = 0.007) and progression-free survival (61.9 months vs not reached, P = 0.017). CONCLUSION: By using a machine learning classification method that avoids most pre-assumptions, the novel algorithm obtained is accurate and maintains relevant features for clinical implementation.

Farnesyltransferase inhibitors: molecular evidence of therapeutic efficacy in acute lymphoblastic leukemia through cyclin D1 inhibition.

BACKGROUND: Farnesyltransferase inhibitors have the ability to interfere with various intracellular pathways, reducing cell survival and proliferation. They have become an attractive tool for cancer therapy, namely acute leukemias. In this work, we have studied the efficacy of α-hydroxyfarnesylphosphonic acid (α-HFPA) in CEM (acute T-cell lymphoblastic leukemia) in culture. MATERIALS AND METHODS: CEM cells were incubated with α-HFPA at different concentrations; viability and proliferation studies were performed using the trypan blue exclusion assay and cell morphological analysis. Expression of lamin A/C, cyclin D1 and BAD were analyzed by flow cytometry. RESULTS: Our results show that α-HFPA significantly decreases Farnesyltransferase activity, reduces cell proliferation and induces cell death through apoptosis in CEM cells, which is correlated with a reduction of cyclin D1 levels. CONCLUSION: This study suggests that α-HFPA blocks the cell cycle and induces cell death through apoptosis in CEM cells and may be a therapeutic approach in ALL.