SUMMARY Therapy development for adult diffuse glioma is hindered by incomplete knowledge of somatic glioma driving alterations and suboptimal disease classification. We defined the complete set of genes associated with 1,122 diffuse grade II-III-IV gliomas from The Cancer Genome Atlas and used molecular profiles to improve disease classification, identify molecular correlations, and provide insights into the progression from low- to high-grade disease. Whole genome sequencing data analysis determined that ATRX but not TERT promoter mutations are associated with increased telomere length. Recent advances in glioma classification based on IDH mutation and 1p/19q co-deletion status were recapitulated through analysis of DNA methylation profiles, which identified clinically relevant molecular subsets. A subtype of IDH-mutant glioma was associated with DNA demethylation and poor outcome; a group of IDH-wildtype diffuse glioma showed molecular similarity to pilocytic astrocytoma and relatively favorable survival. Understanding of cohesive disease groups may aid improved clinical outcomes.

Cancer immunotherapy is revolutionizing the clinical management of several tumors, but has demonstrated limited activity in breast cancer. The development of more effective treatments is hindered by incomplete knowledge of the genetic determinant of immune responsiveness. To fill this gap, we mined copy number alteration, somatic mutation, and expression data from The Cancer Genome Atlas (TCGA). By using RNA-sequencing data from 1,004 breast cancers, we defined distinct immune phenotypes characterized by progressive expression of transcripts previously associated with immune-mediated rejection. The T helper 1 (Th-1) phenotype (ICR4), which also displays upregulation of immune-regulatory transcripts such as PDL1, PD1, FOXP3, IDO1, and CTLA4, was associated with prolonged patients' survival. We validated these findings in an independent meta-cohort of 1,954 breast cancer gene expression data. Chromosome segment 4q21, which includes genes encoding for the Th-1 chemokines CXCL9-11, was significantly amplified only in the immune favorable phenotype (ICR4). The mutation and neoantigen load progressively decreased from ICR4 to ICR1 but could not fully explain immune phenotypic differences. Mutations of TP53 were enriched in the immune favorable phenotype (ICR4). Conversely, the presence of MAP3K1 and MAP2K4 mutations were tightly associated with an immune-unfavorable phenotype (ICR1). Using both the TCGA and the validation dataset, the degree of MAPK deregulation segregates breast tumors according to their immune disposition. These findings suggest that mutation-driven perturbations of MAPK pathways are linked to the negative regulation of intratumoral immune response in breast cancer. Modulations of MAPK pathways could be experimentally tested to enhance breast cancer immune sensitivity.

Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We analyze our dataset and compare it with five VQA-Grounding datasets to demonstrate what makes it similar and different. We then evaluate the SOTA VQA and VQA-Grounding models and demonstrate that current SOTA algorithms often fail to identify the correct visual evidence where the answer is located. These models regularly struggle when the visual evidence occupies a small fraction of the image, for images that are higher quality, as well as for visual questions that require skills in text recognition. The dataset, evaluation server, and leaderboard all can be found at the following link: https://vizwiz.org/tasksand-datasets/answer-grounding-for-vqa/.

No abstract

We examine the issue of bias in datasets designed to train visual question answering (VQA) algorithms. These datasets include a collection of natural language questions about images (aka ‐ visual questions). We consider three popular datasets that are captured by people with sight, people who are blind, and generated by computers. We first demonstrate that machine learning algorithms can be trained to recognize each dataset's bias, and so determine the source of a novel visual question. We then discuss potential risks and benefits of biased VQA datasets and corresponding machine learning algorithms that can identify the source of a visual question; e.g., whether it comes from a person with sight, a person who is blind, or bot (aka ‐ computer). Our ultimate aim is to inspire the development of more inclusive VQA systems.

We investigate what, if any, benefits arise from employing hybrid algorithm-crowdsourcing approaches over conventional approaches of relying exclusively on algorithms or crowds to annotate images.  We introduce a framework that enables users to investigate different hybrid workflows for three popular image analysis tasks: image classification, object detection, and image captioning.   Three hybrid approaches are included that are based on having workers: (i) verify predicted labels, (ii) correct predicted labels, and (iii) annotate images for which algorithms have low confidence in their predictions.  Deep learning algorithms are employed in these workflows since they offer high performance for image annotation tasks.  Each workflow is evaluated with respect to annotation quality and worker time to completion on images coming from three diverse datasets (i.e., VOC, MSCOCO, VizWiz). Inspired by our findings, we offer recommendations regarding when and how to employ deep learning with crowdsourcing to achieve desired quality and efficiency for image annotation.

No abstract

BackgroundCopy number variations are important in the detection and progression of significant tumors and diseases. Recently, Whole Exome Sequencing is gaining popularity with copy number variations detection due to low cost and better efficiency. In this work, we developed VEGAWES for accurate and robust detection of copy number variations on WES data. VEGAWES is an extension to a variational based segmentation algorithm, VEGA: Variational estimator for genomic aberrations, which has previously outperformed several algorithms on segmenting array comparative genomic hybridization data.ResultsWe tested this algorithm on synthetic data and 100 Glioblastoma Multiforme primary tumor samples. The results on the real data were analyzed with segmentation obtained from Single-nucleotide polymorphism data as ground truth. We compared our results with two other segmentation algorithms and assessed the performance based on accuracy and time.ConclusionsIn terms of both accuracy and time, VEGAWES provided better results on the synthetic data and tumor samples demonstrating its potential in robust detection of aberrant regions in the genome.