Machine learning to improve interpretability of clinical, radiological and panel-based genomic data of glioma grade 4 patients undergoing surgical resection.

BACKGROUND: Glioma grade 4 (GG4) tumors, including astrocytoma IDH-mutant grade 4 and the astrocytoma IDH wt are the most common and aggressive primary tumors of the central nervous system. Surgery followed by Stupp protocol still remains the first-line treatment in GG4 tumors. Although Stupp combination can prolong survival, prognosis of treated adult patients with GG4 still remains unfavorable. The introduction of innovative multi-parametric prognostic models may allow refinement of prognosis of these patients. Here, Machine Learning (ML) was applied to investigate the contribution in predicting overall survival (OS) of different available data (e.g. clinical data, radiological data, or panel-based sequencing data such as presence of somatic mutations and amplification) in a mono-institutional GG4 cohort. METHODS: By next-generation sequencing, using a panel of 523 genes, we performed analysis of copy number variations and of types and distribution of nonsynonymous mutations in 102 cases including 39 carmustine wafer (CW) treated cases. We also calculated tumor mutational burden (TMB). ML was applied using eXtreme Gradient Boosting for survival (XGBoost-Surv) to integrate clinical and radiological information with genomic data. RESULTS: By ML modeling (concordance (c)- index = 0.682 for the best model), the role of predicting OS of radiological parameters including extent of resection, preoperative volume and residual volume was confirmed. An association between CW application and longer OS was also showed. Regarding gene mutations, a role in predicting OS was defined for mutations of BRAF and of other genes involved in the PI3K-AKT-mTOR signaling pathway. Moreover, an association between high TMB and shorter OS was suggested. Consistently, when a cutoff of 1.7 mutations/megabase was applied, cases with higher TMB showed significantly shorter OS than cases with lower TMB. CONCLUSIONS: The contribution of tumor volumetric data, somatic gene mutations and TBM in predicting OS of GG4 patients was defined by ML modeling.

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.

Tumor genotype, location, and malignant potential shape the immunogenicity of primary untreated gastrointestinal stromal tumors.

Intratumoral immune infiltrate was recently reported in gastrointestinal stromal tumors (GISTs). However, the tumor-intrinsic factors that dictate GIST immunogenicity are still largely undefined. To shed light on this issue, a large cohort (82 samples) of primary untreated GISTs, representative of major clinicopathological variables, was investigated by an integrated immunohistochemical, transcriptomic, and computational approach. Our results indicate that tumor genotype, location, and malignant potential concur to shape the immunogenicity of primary naive GISTs. Immune infiltration was greater in overt GISTs compared with that in lesions with limited malignant potential (miniGISTs), in KIT/PDGFRA-mutated tumors compared with that in KIT/PDGFRA WT tumors, and in PDGFRA-mutated compared with KIT-mutated GISTs. Within the KIT-mutated subset, a higher degree of immune colonization was detected in the intestine. Immune hot tumors showed expression patterns compatible with a potentially proficient but curbed antigen-specific immunity, hinting at sensitivity to immunomodulatory treatments. Poorly infiltrated GISTs, primarily KIT/PDGFRA WT intestinal tumors, showed activation of Hedgehog and WNT/ß-catenin immune excluding pathways. This finding discloses a potential therapeutic vulnerability, as the targeting of these pathways might prove effective by both inhibiting pro-oncogenic signals and fostering antitumor immune responses. Finally, an intriguing anticorrelation between immune infiltration and ANO1/DOG1 expression was observed, suggesting an immunomodulatory activity for anoctamin-1.

Neurofibromin C terminus-specific antibody (clone NFC) is a valuable tool for the identification of NF1-inactivated GISTs.

An increasing body of evidence supports the involvement of NF1 mutations, constitutional or somatic, in the pathogenesis of gastrointestinal stromal tumors (GISTs). Due to the large size of the NF1 locus, the existence of multiple pseudogenes and the wide spectrum of mechanisms of gene inactivation, the analysis of NF1 gene status is still challenging for most laboratories. Here we sought to assess the efficacy of a recently developed neurofibromin-specific antibody (NFC) in detecting NF1-inactivated GISTs. NFC reactivity was analyzed in a series of 98 GISTs. Of these, 29 were 'NF1-associated' (17 with ascertained NF1 mutations and 12 arising in the context of clinically diagnosed Neurofibromatosis type 1 syndrome and thus considered bona fine NF1 inactivated); 38 were 'NF1-unrelated' (either wild-type or carrying non-pathogenic variants of NF1). Thirty-one additional GISTs with no available information on NF1 gene status or with NF1 gene variants of uncertain pathogenic significance were also included in the analysis. Cases were scored as NFC negative when, in the presence of NFC positive internal controls, no cytoplasmic staining was detected in the neoplastic cells. NFC immunoreactivity was lost in 24/29 (83%) NF1-associated GISTs as opposed to only 2/38 (5%) NF1-unrelated GISTs (P=3e-11). NFC staining loss significantly correlated (P=0.007) with the presence of biallelic NF1 inactivation, due essentially to large deletions or truncating mutations. NFC reactivity was instead retained in two cases in which the NF1 alteration was heterozygous and in one case where the pathogenic NF1 variant, although homo/hemizygous, was a missense mutation predicted not to affect neurofibromin half-life. Overall this study provides evidence that NFC is a valuable tool for identifying NF1-inactivated GISTs, thus serving as a surrogate for molecular analysis.

Quadruple-Negative GIST Is a Sentinel for Unrecognized Neurofibromatosis Type 1 Syndrome.

PURPOSE: The majority of gastrointestinal stromal tumors (GIST) are driven by KIT, PDGFRA, or, less commonly, BRAF mutations, and SDH gene inactivation is involved in a limited fraction of gastric lesions. However, about 10% of GISTs are devoid of any of such alterations and are poorly responsive to standard treatments. This study aims to shed light on the molecular drivers of quadruple-negative GISTs. EXPERIMENTAL DESIGN: Twenty-two sporadic quadruple-negative GISTs with no prior association with Neurofibromatosis Type 1 syndrome were molecularly profiled for a panel of genes belonging to tyrosine kinase pathways or previously implicated in GISTs. For comparison purposes, 24 GISTs carrying KIT, PDGFRA, or SDH gene mutations were also analyzed. Molecular findings were correlated to clinicopathologic features. RESULTS: Most quadruple-negative GISTs featured intestinal localization, with a female predilection. About 60% (13/22) of quadruple-negative tumors carried NF1 pathogenic mutations, often associated with biallelic inactivation. The analysis of normal tissues, available in 11 cases, indicated the constitutional nature of the NF1 mutation in 7 of 11 cases, unveiling an unrecognized Neurofibromatosis Type 1 syndromic condition. Multifocality and a multinodular pattern of growth were common findings in NF1-mutated quadruple-negative GISTs. CONCLUSIONS: NF1 gene mutations are frequent in quadruple-negative GISTs and are often constitutional, indicating that a significant fraction of patients with apparently sporadic quadruple-negative GISTs are affected by unrecognized Neurofibromatosis Type 1 syndrome. Hence, a diagnosis of quadruple-negative GIST, especially if multifocal or with a multinodular growth pattern and a nongastric location, should alert the clinician to a possible Neurofibromatosis Type 1 syndromic condition. Clin Cancer Res; 23(1); 273-82. ©2016 AACR.

Pulsed light beams in vacuum with superluminal and negative group velocities.

We study the group velocity of pulsed light beams in vacuum. Gouy's phase associated with the diffraction of transversally limited pulses can create a strong anomalous dispersion in vacuum leading to highly superluminal and negative group velocities. As a consequence, a focusing pulse can diverge beyond the focus before converging into it. The experimental feasibility is discussed.