Comprehensive genomic sequencing of prostate sarcomatoid carcinoma tumors identifies differences in genomic alterations compared to prostate adenocarcinoma tumors.

2017 ◽  
Vol 35 (6_suppl) ◽  
pp. 226-226 ◽  
Author(s):  
Sherri Z. Millis ◽  
Philip J. Stephens ◽  
Jeffrey S. Ross ◽  
Vincent A. Miller ◽  
Siraj Mahamed Ali ◽  
...  
Keyword(s):  
Clinical Care ◽  
Treatment Options ◽  
Sarcomatoid Carcinoma ◽  
Prostate Adenocarcinoma ◽  
Copy Number Alterations ◽  
Genomic Alterations ◽  
Comprehensive Genomic Profiling ◽  
Tumor Mutational Burden ◽  
Prostate Cancers ◽  
Worse Prognosis

226 Background: Sarcomatoid carcinoma of the prostate is a rare variant of prostatic cancer and has a significantly worse prognosis. The genomic features underpinning this rare subtype of malignancy are not well understood, and at present, there are no effective therapies. Methods: Tissue from 1417 prostate cancer patients was assayed by hybrid-capture based comprehensive genomic profiling (CGP) in the course of clinical care to evaluate genomic alterations (GA: base substitutions, indels, amplifications, copy number alterations, fusions/rearrangements) and targeted therapy opportunities. Tumor mutational burden (TMB) was calculated from a minimum of 1.11 Mb sequenced DNA and reported as mutations/Mb. Results: Profiling identified different patterns in GAs between prostate adenocarcinoma (1409) and prostate sarcomatoid carcinoma (8) (table), most notably in the commonly identified alterations in prostate cancers: TP53, RB1, and TMPRSS2-ERG. Additionally, the PI3K/mTOR pathway was altered in 50% of the sarcomatoid carcinoma cohort. None of the sarcomatoid carcinoma patients had a high TMB, while 4% of the prostate adenocarcinomas had TMB greater than 19 mutations/Mb. The sarcomatoid carcinoma cohort also had on average 8 GAs, while the prostate adenocarcinoma cohort had an average of 13 GAs. Conclusions: Genomic profiles of tumors from patients with prostate cancers reveal that those with sarcomatoid carcinoma features are more likely to have genomic alterations in TP53, RB1, and TMPRSS2 but fewer overall GA’s. Based on rearrangements and the sarcoma profile, utilization of a broad CGP panel that includes analysis of a larger panel of rearrangements identifies more commonly rearranged genes that would not be identified in non-comprehensive panels that do not evaluate these rearrangements. These findings may contribute to a better understanding of the oncogenesis of sarcomatoid prostate carcinoma and for defining novel systemic treatment options. [Table: see text]

Secondary genomic alterations in Ewing sarcoma.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. 11024-11024
Author(s):  
An Uche ◽  
Warren Allen Chow ◽  
Sherri Z. Millis
Keyword(s):  
Ewing Sarcoma ◽  
Transmembrane Domain ◽  
Clinical Care ◽  
Growth Factor Receptor ◽  
Bone Cancer ◽  
Genomic Alterations ◽  
Comprehensive Genomic Profiling ◽  
Tumor Mutational Burden ◽  
Breast And Prostate Cancer ◽  
N 93

11024 Background: Ewing sarcoma (ES) is the second most common bone cancer in children and young adults. The prognosis of recurrent or metastatic ES is poor, with a 5-year overall survival <30%. ES is characterized by translocations involving ETS transcription factors ( EWS– FLI and EWS– ERG translocations are the most common). Secondary somatic alterations in ES are infrequently described. Aberrations in fibroblast growth factor receptor 4 ( FGFR4), a receptor tyrosine kinase protein that plays an important role in cellular processes,have been shown to contribute to carcinogenesis in different types of cancer.More recently, the FGFR4-Gly388Arg (G388R) single nucleotide polymorphism (SNP), with the substitution of arginine instead of glycine in the transmembrane domain of the receptor, is found to significantly increase the risk of breast and prostate cancer. Mouse embryonic fibroblasts derived from knock-in strain of homologous FGFR4-G388R mice display a transformed phenotype, and TGFα-induced mammary carcinogenesis in this strain is significantly enhanced. The association between FGFR4 G338R SNP and ES has not been evaluated. We evaluated the frequency of FGFR4 G338R and whether comprehensive genomic profiling (CGP) might uncover additional, potentially targetable, genomic alterations (GA) in ES. Methods: Tissue from 253 patients with ES was assayed by hybrid-capture based CGP (FoundationOne Heme, next generation sequencing (NGS), analysis which includes both DNA sequencing of 406 genes and RNA sequencing of 265 genes), performed in the course of clinical care to evaluate GAs, including base substitutions, indels, amplifications, copy number alterations and gene fusions/rearrangements. Tumor mutational burden (TMB) was calculated from a minimum of 1.4 Mb sequenced DNA and reported as mutations/Mb. Microsatellite instability (MSI) status was determined by a novel algorithm analyzing 114 specific loci. Results: CGP identified several GAs in ES: TP53 (n= 50, 20%), MLL3 (n=15, 6%), MSH3 (n=14, 5%), ARID1A (n=11, 4%) and FGFR4 (n=3, 1%). FGFR4 G338R SNP was found in almost half of the patients (n=123, 49%). Conclusions: Secondary GAs in TP53, MLL3, MSH3, ARID1A and FGFR4 were found in more than one third of patients with ES (n=93, 37%). FGFR4 G388R SNP was detected in nearly half of patients, and may represent an alternative method of sarcomagenesis. Overall, the frequency of these GAs is significantly greater than previously reported. These GAs may inform the potential for targeted therapies.

Comprehensive genomic sequencing of appendiceal cancer tumors to identify different genomic alterations by subtype, novel treatment opportunities, and improved outcomes.

2017 ◽  
Vol 35 (4_suppl) ◽  
pp. 599-599
Author(s):  
Celina Ang ◽  
Aatur D. Singhi ◽  
Alexa Betzig Schrock ◽  
Jeffrey S. Ross ◽  
Philip J. Stephens ◽  
...  
Keyword(s):  
Case Reports ◽  
Clinical Care ◽  
Current Treatment ◽  
Appendiceal Cancer ◽  
Genomic Alterations ◽  
Mek Inhibitors ◽  
Improved Outcomes ◽  
Individualized Approach ◽  
Comprehensive Genomic Profiling ◽  
Tumor Mutational Burden

599 Background: Appendiceal cancers are rare and consist of mucinous (M), adenocarcinoma (A), goblet cell carcinoma (GCC), pseudomyxoma peritonei (PMP), and several even rarer histologies. Current treatment involves surgical resection or debulking; no standard exists for adjuvant chemotherapy or metastatic disease treatment. Systemic treatment is often based on chemotherapy regimens used in colorectal cancer. Methods: Tissue from 518 appendiceal cancer patients was assayed by hybrid-capture based comprehensive genomic profiling (CGP) in the course of clinical care to evaluate genomic alterations (GA: base substitutions, indels, amplifications, copy number alterations, fusions/rearrangements) and targeted therapy opportunities; 315 genes frequently altered in cancer were assayed. Tumor mutational burden (TMB) was calculated from a minimum of 1.11 Mb sequenced DNA and reported as mutations/Mb. Results: Profiling across all appendiceal cancer histological subtypes identified different patterns in GAs across subtypes (table), most notably in GNAS, KRAS, and TP53. No PMP exhibited microsatellite instability (MSI-H) or high TMB ( > 20 mutations/Mb); MSI-H cases included 3 M, 4 A, 1 GCC; 3-7% 12% A and 6% m had high TMB. Case reports of patients with tumors harboring GNAS alterations showed response to MEK inhibitors. Conclusions: Genomic profiles of tumors from patients with appendiceal cancers reveal differing profiles from colorectal cancers (CRC) and considerable heterogeneity between subtypes, suggesting an individualized approach to treatment. Therapeutic options include clinical trials targeting pathways involving KRAS, BRAF, GNAS, PIK3CA, FBXW7, SMAD4, APC, and ATM. Recent case reports indicate that GNAS is a clinical target for MEK inhibitors. Overall, given the poor prognosis of advanced stage appendiceal carcinoma patients, CGP may identify novel, unanticipated therapeutic targets in a significant subset of patients, including immunotherapy for high TMB patients. [Table: see text]

Comprehensive genomic profiling of renal cell carcinoma with sarcomatoid dedifferentiation to pinpoint recurrent genomic alterations.

2016 ◽  
Vol 34 (2_suppl) ◽  
pp. 537-537
Author(s):  
Gabriel G. Malouf ◽  
Siraj Mahamed Ali ◽  
Kai Wang ◽  
Sohail Balasubramanian ◽  
Jeffrey S. Ross ◽  
...  
Keyword(s):  
Renal Cell Carcinoma ◽  
Cell Carcinoma ◽  
Renal Cell ◽  
Clear Cell ◽  
Clinical Care ◽  
Genomic Profiling ◽  
Genomic Features ◽  
Routine Clinical Care ◽  
Comprehensive Genomic Profiling ◽  
Worse Prognosis

537 Background: Renal cell carcinoma with sarcomatoid dedifferentiation (sRCC) is found in five percent of all renal cell carcinoma (RCC) cases, and has a significantly worse prognosis relative to matched highgrade RCC with only epithelial elements. The genomic features underpinning sRCC are not well understood, and at present, there are no specific or effective therapies for sRCC. Methods: We conducted comprehensive genomic profiling (CGP) on paired epithelial and sarcomatoid areas of 3 sRCC cases. In the course of routine clinical care, CGP was performed on another 23 sRCC harboring diverse epithelial components. CGP was conducted using a hybrid capture next generation DNA sequencing assay(NGS) of 236 cancer-related genes plus 19 genes frequently rearranged in cancer. Results were compared with 56 similarly sequenced cases of clear cell RCC devoid of sarcomatoid component, and with clear cell TCGA. Results: Two of three sRCC cases that underwent CGP of both their epithelial and the sarcomatoid components demonstrated identical mutational profiles, and a third case demonstrated commonly disrupted genes. Of the 23 sRCC, TP53(43%), CDKN2A(30%), VHL(26%) and NF2(22%) were the most frequently altered genes. NF2 mutations were mutually exclusive with TP53 but not with VHL mutations. Conclusions: Two of three sRCC cases that underwent CGP of both their epithelial and the sarcomatoid components demonstrated identical mutational profiles, and a third case demonstrated commonly disrupted genes. Of the 23 sRCC, TP53(43%), CDKN2A(30%), VHL(26%) and NF2(22%) were the most frequently altered genes. NF2 mutations were mutually exclusive with TP53 but not with VHL mutations.

Genomic alterations (GA) and tumor mutational burden (TMB) in large cell neuroendocrine carcinoma of lung (L-LCNEC) as compared to small cell lung carcinoma (SCLC) as assessed via comprehensive genomic profiling (CGP).

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. 8517-8517 ◽  
Author(s):  
Young Kwang Chae ◽  
Keerthi Tamragouri ◽  
Jon Chung ◽  
Alexa Betzig Schrock ◽  
Bhaskar Kolla ◽  
...  
Keyword(s):  
Small Cell Lung Carcinoma ◽  
Clinical Care ◽  
Large Cell ◽  
Smoking History ◽  
Genomic Profiling ◽  
Wild Type ◽  
Cell Lung Carcinoma ◽  
Mutational Burden ◽  
Comprehensive Genomic Profiling ◽  
Tumor Mutational Burden

8517 Background: SCLC and L-LCNEC are aggressive neoplasms that are both associated with smoking history and are thought to overlap in clinical, histogenetic, and genomic features. We reviewed the genomic profiles of >1187 patients to assess the genomic similarities of these diseases. Methods: Comprehensive genomic profiling (CGP) of tumors from 300 L-LCNEC and 887 SCLC patients in the course of clinical care was performed to suggest pathways to benefit from therapy. Results: Commonly altered genes in both diseases included TP53, RB1, MYC/MYCL1, MLL2, LRP1B and PTEN; alterations in other genes occurred at somewhat differing frequencies (table). For both diseases, RB1 mutation significantly co-occurred with TP53 mutations (p<0.001), but occurred in a mutually exclusive fashion to STK11 and CDKN2A (p<0.001). RB1 was mutually exclusive with KRAS for L-LCNEC but not for SCLC. The interquartile range for SCLC and L-LCNEC TMB is 7.9 and 12.6 with the 75% quartile being 14.4 and 17.1 respectively. Cases of both diseases will be presented with radiographic response to genomically matched targeted therapy and immunotherapy, particularly in cases of high TMB. Conclusions: Given the similar overall genomic profiles and clinical behavior of a subset of these diseases, they could be conceived of as a single disease to be further classified by genomically defined classes such as SCLC-type ( TP53/ RB1mutated) and NSCLC-like (wild type for one or both). By analogy to NSLC and melanoma, benefit from immunotherapy appears most likely for only the upper quartile of cases in TMB. [Table: see text]

Impact of age on genomic alterations associated with pancreatic ductal adenocarcinoma (PDAC).

2017 ◽  
Vol 35 (4_suppl) ◽  
pp. 282-282
Author(s):  
Ben George ◽  
Mark Bailey ◽  
Alexa Betzig Schrock ◽  
Lauren Thorpe ◽  
Laurie M. Gay ◽  
...  
Keyword(s):  
Large Scale ◽  
Kinase Domain ◽  
Ductal Adenocarcinoma ◽  
Genomic Alterations ◽  
Kras Mutations ◽  
Entire Study ◽  
Formalin Fixed Paraffin Embedded ◽  
Comprehensive Genomic Profiling ◽  
Tumor Mutational Burden ◽  
Metastatic Sites

282 Background: Large scale, retrospective, sequencing projects have identified well-defined subtypes of PDAC, but therapeutic paradigms remain unchanged. We hypothesized that genomic alterations associated with PDAC in young adults (YA, age < 50) are distinctly different from that of older adults (OA, age > 50) to identify an enrichment of targetable alterations. Methods: DNA was extracted from formalin fixed paraffin embedded (FFPE) PDAC clinical specimens and comprehensive genomic profiling (CGP) was performed on hybrid-capture, adaptor ligation based libraries to a mean coverage depth of > 600 for up to 315 genes plus 47 introns from 19 genes frequently rearranged in cancer. Results: CGP was performed on 1533 FFPE PDAC specimens, 566 (36.9%) were from the primary tumor, 967 (63.1%) from metastatic sites. Median age at diagnosis was 63 years (yrs), 180 (11.7%) were YA. KRAS mutations were identified in 78.7 of YA and 87.7% of OA. The differentially altered genes between the two groups were KRAS (p = 0.004), TP53 (p = 0.04), BRCA2 (p = 0.02), AKT2 (p = 0.03), MAP2K4 (P = 0.003) and DNMT3A (p = 0.0002). The median tumor mutational burden (TMB) for the entire study set was 2.7 (YA – 2.5, OA –2.7). BRAF kinase domain deletion was observed in 1 patient (OA). ALK fusions were present in 2 patients (1 YA & 1 OA) and these patients had durable responses to specific ALK inhibitors. Conclusions: The majority of the genomic alterations identified were not significantly different on the basis of age. However, identification of subpopulations, such as ALK kinase fusions and BRAF kinase domain deletions that can translate into sustained clinical benefit from matched targeted therapy is promising. This underscores the importance of CGP in PDAC to investigate other targetable genomic alterations.

Efficacy of systemic treatment for metastatic renal cell carcinoma (mRCC) guided by comprehensive genomic profiling (CGP).

2019 ◽  
Vol 37 (27_suppl) ◽  
pp. 63-63
Author(s):  
Paulo Gustavo Bergerot ◽  
Cristiane Decat Bergerot ◽  
Nazli Dizman ◽  
Nicholas Salgia ◽  
Joann Hsu ◽  
...  
Keyword(s):  
Renal Cell Carcinoma ◽  
Cell Carcinoma ◽  
Metastatic Renal Cell Carcinoma ◽  
Renal Cell ◽  
Cox Regression ◽  
Clinical Care ◽  
Genomic Profiling ◽  
Genomic Alterations ◽  
Comprehensive Genomic Profiling

63 Background: Comprehensive genomic profiling (CGP) has been used to guide treatment selection in metastatic renal cell carcinoma (mRCC). This study sought to determine if genomic alterations guided treatment and contributed to improved outcomes. Methods: From a single institution, patients (pts) diagnosed with mRCC who had CGP in the course of clinical care were identified. Pts were tested on a CLIAA-certified platform (FoundationOne; Cambridge, MA). Pts who died/initiated hospice within the 30 days after the test was performed or who were lost to follow-up were excluded. Duration of therapy (DOT) was measured as months between first and last day of therapy following CGP test. The Kaplan-Meier method was undertaken to estimate the association of CGP-directed therapy with overall survival (OS). Cox regression was also performed and adjusted for histologic subgroup. Results: A total of 64 patients underwent CGP between February 2014 and August 2018. From this group, 15 patients were excluded due to death/hospice within 30 d (n = 10) and lack of follow-up (n = 5). Median age at diagnosis was 60 years (range, 24-84), and 79% were male. Most patients (69%) were diagnosed with clear cell RCC. The median identified genomic alterations (GAs) was 3 (range, 0-7). The most common GAs were VHL (54%), PBRM1 (28%), TERT (21%), TP53 (15%), BAP1 (13%), and SETD2 (13%). Of the 49 patients included in this analysis, 47% had actionable mutations based on their CGP results. Of those, 13 patients received directed-therapy of whom 57% had stable disease, 28% had partial response, and 14% had progressive disease. The median time from CGP test to treatment was 1 month (range, 0-17). The median duration of directed-therapy was 12 months (range, 1-28) and of non-directed therapy was 4 months (range, 1-40) (P = 0.04). Directed-therapy was significantly associated with better OS (adjusted HR, 0.32 [95% CI, 0.13 to 0.82]; P = 0.018) compared to non-directed therapy. Conclusions: This study provides preliminary evidence to justify CGP-guided therapy in mRCC. Forthcoming studies should prospectively explore the use of CGP in treatment allocation for mRCC to validate these findings.

Cyclin pathway genomic alterations across 5,356 prostate cancers.

2020 ◽  
Vol 38 (6_suppl) ◽  
pp. 179-179
Author(s):  
Denis Leonardo Fontes Jardim ◽  
Sherri Z. Millis ◽  
Michele Sue-Ann Woo ◽  
Jeffrey S. Ross ◽  
Siraj Mahamed Ali ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Genomic Profiling ◽  
Genomic Alterations ◽  
Resistance Pathway ◽  
Lower Likelihood ◽  
Ccnd1 Amplification ◽  
Comprehensive Genomic Profiling ◽  
Prostate Cancers ◽  
Copy Number Changes ◽  
Generation Sequencing

179 Background: The cyclin pathway is comprised of possible targetable alterations as well as resistant alterations that affect treatment, including hormonal agents. We describe the landscape of cyclin genomic alterations in prostate cancer. Methods: Consecutive samples were analyzed in a CLIA-certified laboratory using comprehensive genomic profiling (CGP) performed by next-generation sequencing (315 genes, >500X coverage). We describe alterations in activating genes (Table) and co-alterations in resistant genes ( RB1 and CCNE1) (related to cyclin inhibition) and androgen receptor ( AR). Results: Alterations in any cyclin pathway genes were found in 9.7% of the 5,356 tumors analyzed. Frequent alterations included CCND1 amplification (4.2%) and CDKN2A and B loss (2.4% each). Frequencies were substantially different according to prostate cancer histology (Table). The majority of alterations were copy number changes. Alterations in possible resistance genes, RB1 and CCNE1 were detected in 9.7% (up to 54.6% in neuroendocrine) and 1.2% of cases, respectively, while AR alterations were seen in 20.9% (up to 27.3% in anaplastic). Co-occurrence analysis demonstrated a lower likelihood of concomitant vs. isolated alterations in cyclin activating and resistance pathway (odds ratio (OR), 0.44, p<0.001). Conversely, we detected a higher likelihood of co-occurrence between AR and cyclin alterations (OR 1.79, p<0.001). Conclusions: Cyclin pathway genomic abnormalities were observed in about 10% of prostate cancer tumors, and are more frequently associated with concomitant AR alterations and absence of co-alterations associated with resistance to cyclin inhibition.[Table: see text]

NF2 mutation-driven renal cell carcinomas (RCC): A comprehensive genomic profiling (CGP) study.

2020 ◽  
Vol 38 (6_suppl) ◽  
pp. 726-726
Author(s):  
Evgeny Yakirevich ◽  
Carmen Perrino ◽  
Andrea Necchi ◽  
Petros Grivas ◽  
Gennady Bratslavsky ◽  
...  
Keyword(s):  
Clear Cell ◽  
Collecting Duct ◽  
High Status ◽  
Genomic Alterations ◽  
Mutational Burden ◽  
Gender And Age ◽  
Comprehensive Genomic Profiling ◽  
Tumor Mutational Burden ◽  
Male Preponderance ◽  
Ffpe Tissues

726 Background: NF2 genomic alterations (GA) have been associated with aggressive behavior in RCC. Methods: FFPE tissues from 1,386 clear cell (ccRCC), 307 papillary (pRCC), 72 chromophobe (chRCC), 145 sarcomatoid (sRCC), 54 collecting duct (cdRCC),37 medullary (medRCC) and 134 unclassified (nosRCC) underwent hybrid-capture based CGP to evaluate all classes of genomic alterations (GA). Tumor mutational burden (TMB) was determined on up to 1.1 Mbp of sequenced DNA and MSI was determined on 114 loci. PD-L1 expression was determined by IHC (Dako 22C3). Results: 140 (7%) RCC featured NF2 GA which were predominantly short variant (SV) mutations. Gender and age were similar with male preponderance in all histologic subtypes. NF2 GA frequency was highest in cdRCC (20%) and sRCC (19%) and lowest in ccRCC (3%). The medRCC at 5% NF2 GA and chRCC at 0% NF2 GA were not further evaluated. VHL and PBRM1 GA were significantly more frequent in NF2 altered ccRCC than all other RCC (P < 0.001). Other mTOR pathway GA were uncommon. Potentially targetable kinase GA in NF2-mutated RCC included BRAF (2% of ccRCC), EGFR (3% of pRCC), ERBB3 (4% of sRCC) and PIK3CA (9% of cdRCC). No NF2 mutated RCC featured MSI -high status and both TMB and PD-L1 expression levels were extremely low in all subsets with exception of high PD-L1 staining in sRCC tumors. Conclusions: cdRCC, sRCC, pRCC and nosRCC are enriched in NF2 GA. Low PBRM1 GA, TMB and MSI- high predict resistance to immunotherapy in NF2 mutated RCC although the high PD-L1 expression in sRCC is noteworthy.[Table: see text]

scholarly journals Genomic Profiling of Combined Hepatocellular Cholangiocarcinoma Reveals Genomics Similar to Either Hepatocellular Carcinoma or Cholangiocarcinoma

2021 ◽  
pp. 1285-1296
Author(s):  
Karthikeyan Murugesan ◽  
Radwa Sharaf ◽  
Meagan Montesion ◽  
Jay A. Moore ◽  
James Pao ◽  
...  
Keyword(s):  
Hepatitis B Virus ◽  
Hepatitis B ◽  
Clinical Care ◽  
Liver Carcinoma ◽  
Genomic Profiling ◽  
B Virus ◽  
Comprehensive Genomic Profiling ◽  
Tumor Mutational Burden ◽  
Combined Hepatocellular Cholangiocarcinoma

PURPOSE Combined hepatocellular cholangiocarcinoma (cHCC-CCA) is a rare, aggressive primary liver carcinoma, with morphologic features of both hepatocellular carcinomas (HCC) and liver cholangiocarcinomas (CCA). METHODS The genomic profiles of 4,975 CCA, 1,470 HCC, and 73 cHCC-CCA cases arising from comprehensive genomic profiling in the course of clinical care were reviewed for genomic alterations (GA), tumor mutational burden, microsatellite instability status, genomic loss of heterozygosity, chromosomal aneuploidy, genomic ancestry, and hepatitis B virus status. RESULTS In cHCC-CCA, GA were most common in TP53 (65.8%), TERT (49.3%), and PTEN (9.6%), and 24.6% cHCC-CCA harbored potentially targetable GA. Other GA were predominantly associated with either HCC or CCA, including, but not limited to, TERT, FGFR2, IDH1, and presence of hepatitis B virus. On the basis of these features, a machine learning (ML) model was trained to classify a cHCC-CCA case as CCA-like or HCC-like. Of cHCC-CCA cases, 16% (12/73) were ML-classified as CCA-like and 58% (42/73) cHCC-CCA were ML-classified as HCC-like. The ML model classified more than 70% of cHCC-CCA as CCA-like or HCC-like on the basis of genomic profiles, without additional clinico-pathologic input. CONCLUSION These findings demonstrate the use of ML for classification as based on a targeted exome panel used during routine clinical care. Classification of cHCC-CCA by genomic features alone creates insights into the biology of the disease and warrants further investigation for relevance to clinical care.

Sign in / Sign up

Export Citation Format

Share Document