Cancer diagnosis, prognosis, mymargin and therapeutic response predictions are based on morphological information from histology slides and molecular profiles from genomic data. However, most deep ...learning-based objective outcome prediction and grading paradigms are based on histology or genomics alone and do not make use of the complementary information in an intuitive manner. In this work, we propose Pathomic Fusion , an interpretable strategy for end-to-end multimodal fusion of histology image and genomic (mutations, CNV, RNA-Seq) features for survival outcome prediction. Our approach models pairwise feature interactions across modalities by taking the Kronecker product of unimodal feature representations, and controls the expressiveness of each representation via a gating-based attention mechanism. Following supervised learning, we are able to interpret and saliently localize features across each modality, and understand how feature importance shifts when conditioning on multimodal input. We validate our approach using glioma and clear cell renal cell carcinoma datasets from the Cancer Genome Atlas (TCGA), which contains paired whole-slide image, genotype, and transcriptome data with ground truth survival and histologic grade labels. In a 15-fold cross-validation, our results demonstrate that the proposed multimodal fusion paradigm improves prognostic determinations from ground truth grading and molecular subtyping, as well as unimodal deep networks trained on histology and genomic data alone. The proposed method establishes insight and theory on how to train deep networks on multimodal biomedical data in an intuitive manner, which will be useful for other problems in medicine that seek to combine heterogeneous data streams for understanding diseases and predicting response and resistance to treatment. Code and trained models are made available at: https://github.com/mahmoodlab/PathomicFusion .
Targeted next-generation sequencing panels to identify genetic alterations in cancers are increasingly becoming an integral part of clinical practice. We report here the design, validation, and ...implementation of a comprehensive 95-gene next-generation sequencing panel targeted for hematologic malignancies that we named rapid heme panel. Rapid heme panel is amplicon based and covers hotspot regions of oncogenes and most of the coding regions of tumor suppressor genes. It is composed of 1330 amplicons and covers 175 kb of genomic sequence in total. Rapid heme panel's average coverage is 1500× with <5% of the amplicons with <50× coverage, and it reproducibly detects single nucleotide variants and small insertions/deletions at allele frequencies of ≥5%. Comparison with a capture-based next-generation sequencing assay showed that there is >95% concordance among a wide array of variants across a range of allele frequencies. Read count analyses that used rapid heme panel showed high concordance with karyotypic results when tumor content was >30%. The average turnaround time was 7 days over a 6-month span with an average volume of ≥40 specimens per week and a low sample fail rate (<1%), demonstrating its suitability for clinical application.
- The analysis of somatic mutations across multiple genes in cancer specimens may be used to aid clinical decision making. The analytical validation of targeted next-generation sequencing panels is ...important to assess accuracy and limitations.
- To report the development and validation of OncoPanel, a custom targeted next-generation sequencing assay for cancer.
- OncoPanel was designed for the detection of single-nucleotide variants, insertions and deletions, copy number alterations, and structural variants across 282 genes with evidence as drivers of cancer biology. We implemented a validation strategy using formalin-fixed, paraffin-embedded, fresh or frozen samples compared with results obtained by clinically validated orthogonal technologies.
- OncoPanel achieved 98% sensitivity and 100% specificity for the detection of single-nucleotide variants, and 84% sensitivity and 100% specificity for the detection of insertions and deletions compared with single-gene assays and mass spectrometry-based genotyping. Copy number detection achieved 86% sensitivity and 98% specificity compared with array comparative genomic hybridization. The sensitivity of structural variant detection was 74% compared with karyotype, fluorescence in situ hybridization, and polymerase chain reaction. Sensitivity was affected by inconsistency in the detection of FLT3 and NPM1 alterations and IGH rearrangements due to design limitations. Limit of detection studies demonstrated 98.4% concordance across triplicate runs for variants with allele fraction greater than 0.1 and at least 50× coverage.
- The analytical validation of OncoPanel demonstrates the ability of targeted next-generation sequencing to detect multiple types of genetic alterations across a panel of genes implicated in cancer biology.
An ASCO provisional clinical opinion offers timely clinical direction to ASCO's membership following publication or presentation of potentially practice-changing data from major studies. This ...provisional clinical opinion addresses the appropriate use of tumor genomic testing in patients with metastatic or advanced solid tumors.
An increasing number of therapies are approved to treat cancers harboring specific genomic biomarkers. However, there is a lack of clarity as to when tumor genomic sequencing should be ordered, what type of assays should be performed, and how to interpret the results for treatment selection.
Patients with metastatic or advanced cancer should undergo genomic sequencing in a certified laboratory if the presence of one or more specific genomic alterations has regulatory approval as biomarkers to guide the use of or exclusion from certain treatments for their disease. Multigene panel-based assays should be used if more than one biomarker-linked therapy is approved for the patient's disease. Site-agnostic approvals for any cancer with a high tumor mutation burden, mismatch repair deficiency, or neurotrophic tyrosine receptor kinase (
) fusions provide a rationale for genomic testing for all solid tumors. Multigene testing may also assist in treatment selection by identifying additional targets when there are few or no genotype-based therapy approvals for the patient's disease. For treatment planning, the clinician should consider the functional impact of the targeted alteration and expected efficacy of genomic biomarker-linked options relative to other approved or investigational treatments.Additional information is available at www.asco.org/assays-and-predictive-markers-guidelines.
To establish evidence-based recommendations for the molecular analysis of lung cancers that are that are required to guide EGFR- and ALK-directed therapies, addressing which patients and samples ...should be tested, and when and how testing should be performed.
Three cochairs without conflicts of interest were selected, one from each of the 3 sponsoring professional societies: College of American Pathologists, International Association for the Study of Lung Cancer, and Association for Molecular Pathology. Writing and advisory panels were constituted from additional experts from these societies.
Three unbiased literature searches of electronic databases were performed to capture articles published published from January 2004 through February 2012, yielding 1533 articles whose abstracts were screened to identify 521 pertinent articles that were then reviewed in detail for their relevance to the recommendations. Evidence was formally graded for each recommendation.
Initial recommendations were formulated by the cochairs and panel members at a public meeting. Each guideline section was assigned to at least 2 panelists. Drafts were circulated to the writing panel (version 1), advisory panel (version 2), and the public (version 3) before submission (version 4).
The 37 guideline items address 14 subjects, including 15 recommendations (evidence grade A/B). The major recommendations are to use testing for EGFR mutations and ALK fusions to guide patient selection for therapy with an epidermal growth factor receptor (EGFR) or anaplastic lymphoma kinase (ALK) inhibitor, respectively, in all patients with advanced-stage adenocarcinoma, regardless of sex, race, smoking history, or other clinical risk factors, and to prioritize EGFR and ALK testing over other molecular predictive tests. As scientific discoveries and clinical practice outpace the completion of randomized clinical trials, evidence-based guidelines developed by expert practitioners are vital for communicating emerging clinical standards. Already, new treatments targeting genetic alterations in other, less common driver oncogenes are being evaluated in lung cancer, and testing for these may be addressed in future versions of these guidelines.
Mismatch repair protein deficiency (MMR-D) and high microsatellite instability (MSI-H) are features of Lynch syndrome–associated colorectal carcinomas and have implications in clinical management. We ...evaluate the ability of a targeted next-generation sequencing panel to detect MMR-D and MSI-H based on mutational phenotype. Using a criterion of >40 total mutations per megabase or >5 single-base insertion or deletion mutations in repeats per megabase, sequencing achieves 92% sensitivity and 100% specificity for MMR-D by immunohistochemistry in a training cohort of 149 colorectal carcinomas and 91% sensitivity and 98% specificity for MMR-D in a validation cohort of 94 additional colorectal carcinomas. False-negative samples are attributable to tumor heterogeneity, and next-generation sequencing results are concordant with analysis of microsatellite loci by PCR. In a subset of 95 carcinomas with microsatellite analysis, sequencing achieves 100% sensitivity and 99% specificity for MSI-H in the combined training and validation set. False-positive results for MMR-D and MSI-H are attributable to ultramutated cancers with POLE mutations, which are confirmed by direct sequencing of the POLE gene and are detected by mutational signature analysis. These findings provide a framework for a targeted tumor sequencing panel to accurately detect MMR-D and MSI-H in colorectal carcinomas.
Abstract
Glioblastoma (GBM) is the most common primary malignant brain tumor, with a universally poor prognosis. The emergence of molecular biomarkers has had a significant impact on histological ...typing and diagnosis, as well as predicting patient survival and response to treatment. The methylation status of the O6-methylguanine-DNA methyl-transferase (MGMT) gene promoter is one such molecular biomarker. Despite the strong evidence supporting the role of MGMT methylation status in prognostication, its routine implementation in clinical practice has been challenging. The methods and optimal cutoff definitions for MGMT status determination remain controversial. Variation in detection methods between laboratories presents a major challenge for consensus. Moreover, consideration of other clinical and genetic/epigenetic factors must also be incorporated into treatment decision making. In this review, we distill the available evidence to summarize our position on the optimal use of available assays, and propose strategies for resolving cases with equivocal methylation status and a framework for incorporating this important assay into research and clinical practice.
To establish evidence-based recommendations for the molecular analysis of lung cancers that are required to guide EGFR- and ALK-directed therapies, addressing which patients and samples should be ...tested, and when and how testing should be performed.
Three cochairs without conflicts of interest were selected, one from each of the 3 sponsoring professional societies: College of American Pathologists, International Association for the Study of Lung Cancer, and Association for Molecular Pathology. Writing and advisory panels were constituted from additional experts from these societies.
Three unbiased literature searches of electronic databases were performed to capture articles published from January 2004 through February 2012, yielding 1533 articles whose abstracts were screened to identify 521 pertinent articles that were then reviewed in detail for their relevance to the recommendations. Evidence was formally graded for each recommendation.
Initial recommendations were formulated by the cochairs and panel members at a public meeting. Each guideline section was assigned to at least 2 panelists. Drafts were circulated to the writing panel (version 1), advisory panel (version 2), and the public (version 3) before submission (version 4).
The 37 guideline items address 14 subjects, including 15 recommendations (evidence grade A/B). The major recommendations are to use testing for EGFR mutations and ALK fusions to guide patient selection for therapy with an epidermal growth factor receptor (EGFR) or anaplastic lymphoma kinase (ALK) inhibitor, respectively, in all patients with advanced-stage adenocarcinoma, regardless of sex, race, smoking history, or other clinical risk factors, and to prioritize EGFR and ALK testing over other molecular predictive tests. As scientific discoveries and clinical practice outpace the completion of randomized clinical trials, evidence-based guidelines developed by expert practitioners are vital for communicating emerging clinical standards. Already, new treatments targeting genetic alterations in other, less common driver oncogenes are being evaluated in lung cancer, and testing for these may be addressed in future versions of these guidelines.
Widespread clinical laboratory implementation of next-generation sequencing-based cancer testing has highlighted the importance and potential benefits of standardizing the interpretation and ...reporting of molecular results among laboratories. A multidisciplinary working group tasked to assess the current status of next-generation sequencing-based cancer testing and establish standardized consensus classification, annotation, interpretation, and reporting conventions for somatic sequence variants was convened by the Association for Molecular Pathology with liaison representation from the American College of Medical Genetics and Genomics, American Society of Clinical Oncology, and College of American Pathologists. On the basis of the results of professional surveys, literature review, and the Working Group's subject matter expert consensus, a four-tiered system to categorize somatic sequence variations based on their clinical significances is proposed: tier I, variants with strong clinical significance; tier II, variants with potential clinical significance; tier III, variants of unknown clinical significance; and tier IV, variants deemed benign or likely benign. Cancer genomics is a rapidly evolving field; therefore, the clinical significance of any variant in therapy, diagnosis, or prognosis should be reevaluated on an ongoing basis. Reporting of genomic variants should follow standard nomenclature, with testing method and limitations clearly described. Clinical recommendations should be concise and correlate with histological and clinical findings.
PDF
