Effective identification of oncogenic mutations is essential for diagnosis, forecasting resistance, and metastasis in remission. It is required for an optimal drug regimen. We develop a framework to discover mutations that co-exist in different oncoproteins, and those that are excluded, likely encoding oncogene-induced senescence. First, mapping the proteins onto pathways assists combinatorial drug selections and helps to detect metastases. Second, it provides the molecular basis for synthetic lethality, to date investigated at the genome level. Our pan-cancer profiles of ~60,000 tumor sequences, detect 3424 co-existing tumor-specific mutations. Mapping them onto pathways indicates that they preferentially promote specific primary tumors. We uncover metastatic mutations and provide metastatic breast-cancer markers. This work not only clarifies the mechanistic basis of intratumor mutational diversity but usefully reveals markers for metastasis in patients' genomes and introduces a novel computational framework for detecting metastasis based on tumor mutational profiles. Mapping the mutations onto pathways provides an invaluable metastasis-targeting resource, guiding drug combinations.

Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse corpus of images and corresponding text captions scraped from the internet. Despite this, VLMs often struggle with compositional reasoning tasks which require a fine-grained understanding of the complex interactions of objects and their attributes. This failure can be attributed to two main factors: 1) Contrastive approaches have traditionally focused on mining negative examples from existing datasets. However, the mined negative examples might not be difficult for the model to discriminate from the positive. An alternative to mining would be negative sample generation 2) But existing generative approaches primarily focus on generating hard negative texts associated with a given image. Mining in the other direction, i.e., generating negative image samples associated with a given text has been ignored. To overcome both these limitations, we propose a framework that not only mines in both directions but also generates challenging negative samples in both modalities, i.e., images and texts. Leveraging these generative hard negative samples, we significantly enhance VLMs’ performance in tasks involving multimodal compositional reasoning. Our code and dataset are released at https://ugorsahin.github.io/enhancing-multimodal-compositional-reasoning-of-vlm.html.

SUMMARY: The detection and prediction of true neoantigens is of great importance for the field of cancer immunotherapy. Wesearched the literature for proposed neoantigen features and integrated them into a toolbox called NEOantigen Feature toolbOX (NeoFox). NeoFox is an easy-to-use Python package that enables the annotation of neoantigen candidates with 16 neoantigen features. AVAILABILITY AND IMPLEMENTATION: NeoFox is freely available as an open source Python package released under the GNU General Public License (GPL) v3 license at https://github.com/TRON-Bioinformatics/neofox. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Gene fusions are an important class of transcriptional variants that can influence cancer development and can be predicted from RNA sequencing (RNA-seq) data by multiple existing tools. However, the real-world performance of these tools is unclear due to the lack of known positive and negative events, especially with regard to fusion genes in individual samples. Often simulated reads are used, but these cannot account for all technical biases in RNA-seq data generated from real samples. RESULTS: Here, we present ArtiFuse, a novel approach that simulates fusion genes by sequence modification to the genomic reference, and therefore, can be applied to any RNA-seq dataset without the need for any simulated reads. We demonstrate our approach on eight RNA-seq datasets for three fusion gene prediction tools: average recall values peak for all three tools between 0.4 and 0.56 for high-quality and high-coverage datasets. As ArtiFuse affords total control over involved genes and breakpoint position, we also assessed performance with regard to gene-related properties, showing a drop-in recall value for low-expressed genes in high-coverage samples and genes with co-expressed paralogues. Overall tool performance assessed from ArtiFusions is lower compared to previously reported estimates on simulated reads. Due to the use of real RNA-seq datasets, we believe that ArtiFuse provides a more realistic benchmark that can be used to develop more accurate fusion gene prediction tools for application in clinical settings. AVAILABILITY AND IMPLEMENTATION: ArtiFuse is implemented in Python. The source code and documentation are available at https://github.com/TRON-Bioinformatics/ArtiFusion. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Genetic diseases are driven by aberrations of the human genome. Identification of such aberrations including structural variations (SVs) is key to our understanding. Conventional short-reads whole genome sequencing (cWGS) can identify SVs to base-pair resolution, but utilizes only short-range information and suffers from high false discovery rate (FDR). Linked-reads sequencing (10XWGS) utilizes long-range information by linkage of short-reads originating from the same large DNA molecule. This can mitigate alignment-based artefacts especially in repetitive regions and should enable better prediction of SVs. However, an unbiased evaluation of this technology is not available. In this study, we performed a comprehensive analysis of different types and sizes of SVs predicted by both the technologies and validated with an independent PCR based approach. The SVs commonly identified by both the technologies were highly specific, while validation rate dropped for uncommon events. A particularly high FDR was observed for SVs only found by 10XWGS. To improve FDR and sensitivity, statistical models for both the technologies were trained. Using our approach, we characterized SVs from the MCF7 cell line and a primary breast cancer tumor with high precision. This approach improves SV prediction and can therefore help in understanding the underlying genetics in various diseases.

In this paper, we introduce a framework for a system which intelligently assigns an edge detection filter to an image based only on features taken from the image. The system has four parts, the training set which consists of an image and its edge image ground truth, feature extraction, training filter creation, and system training. A prototype system of this framework is given. In the system feature extraction is performed using a GIST methodology which extracts color, intensity, and orientation information as features. The set of image features are used as the input to a single hidden layer feed forward neural network trained using back propagation. The system trains against a set of linear Cellular Automata filters which are determined to best solve the edge image according to the Bad delay Delta Metric. This metric takes into account false positives and false negative error by scaling the errors relative to the perpendicular distance that they are off from the ground truth. The system was trained and tested against the images from the Berkeley Segmentation Database. The results from the testing indicate that the system performs better than standard methods in many cases but on the whole is only on par across a wide range of images.

Block matching algorithms successfully reduce the computational load of the motion estimation. Block based motion estimation algorithms rely on block matching of the macro blocks defined in the search windows. In this paper, particle swarm optimization (PSO) is applied on block-matching problem. Particle swarm optimization is a computationally efficient iterative search algorithm that finds the best matching block between two consecutive frames. Finding the moving block in the image sequence requires a minimization algorithm. Using particle swarm optimization, the computational cost of the block matching is aimed to decrease. Particle swarm optimization is a heuristic algorithm and necessarily dependent on the selections of the parameters assigned. In our case, the particle swarm algorithm is designed to work on a small subset of the population of blocks. The position of a macro block in the estimated image can be revealed by the motion vectors generated by the particle swarm optimized block.

In this paper we discuss the application of two-dimensional linear cellular automata rules to the problems of edge detection in monochromatic images. We proposed an efficient and simple method of edge detection based on uniform cellular automata transition matrix representation. We investigate of cellular automata linear rules for edge detection by using matrix representation, in some cases they are strong and some other rules are not in fact useful for practical edge detection. All rules give computationally effective result since the computation mechanism consist only matrix multiplication. Finally, we present some results of the proposed linear rules for edge detection and compare with some classical results.

SUMMARY: We have developed a laboratory information management system (LIMS) for a next-generation sequencing (NGS) laboratory within the existing Galaxy platform. The system provides lab technicians standard and customizable sample information forms, barcoded submission forms, tracking of input sample quality, multiplex-capable automatic flow cell design and automatically generated sample sheets to aid physical flow cell preparation. In addition, the platform provides the researcher with a user-friendly interface to create a request, submit accompanying samples, upload sample quality measurements and access to the sequencing results. As the LIMS is within the Galaxy platform, the researcher has access to all Galaxy analysis tools and workflows. The system reports requests and associated information to a message queuing system, such that information can be posted and stored in external systems, such as a wiki. Through an API, raw sequencing results can be automatically pre-processed and uploaded to the appropriate request folder. Developed for the Illumina HiSeq 2000 instrument, many features are directly applicable to other instruments. AVAILABILITY AND IMPLEMENTATION: The code and documentation are available at http://tron-mainz.de/tron-facilities/computational-medicine/galaxy-lims/

EMG based input device is a natural means of human computer interface (HCI) because the electrical activity induced by the human's arm muscle movements can be interpreted and transformed into computer's control commands. In this paper, we describe an approach for classifying electromyography (EMG) signals using a multilayer perceptron neural network (MLP) and Bayesian classifier (BC) with the wavelet transformation technique for feature selection to discriminate 6 classes of motions to control a mouse. Wavelet Transformation (WT) was applied to raw EMG data and in order to decrease the dimension of the feature sets, principle component analysis (PCA) and sequential forward selection (SFS) were utilized.

MOTIVATION: Next-generation sequencing technology enables an entirely new perspective for clinical research and will speed up personalized medicine. In contrast to microarray-based approaches, RNA-Seq analysis provides a much more comprehensive and unbiased view of gene expression. Although the perspective is clear and the long-term success of this new technology obvious, bioinformatics resources making these data easily available especially to the biomedical research community are still evolving. RESULTS: We have generated RNA-Seq Atlas, a web-based repository of RNA-Seq gene expression profiles and query tools. The website offers open and easy access to RNA-Seq gene expression profiles and tools to both compare tissues and find genes with specific expression patterns. To enlarge the scope of the RNA-Seq Atlas, the data were linked to common functional and genetic databases, in particular offering information on the respective gene, signaling pathway analysis and evaluation of biological functions by means of gene ontologies. Additionally, data were linked to several microarray gene profiles, including BioGPS normal tissue profiles and NCI60 cancer cell line expression data. Our data search interface allows an integrative detailed comparison between our RNA-Seq data and the microarray information. This is the first database providing data mining tools and open access to large scale RNA-Seq expression profiles. Its applications will be versatile, as it will be beneficial in identifying tissue specific genes and expression profiles, comparison of gene expression profiles among diverse tissues, but also systems biology approaches linking tissue function to gene expression changes. AVAILABILITY AND IMPLEMENTATION: http://medicalgenomics.org/rna_seq_atlas.

Next generation sequencing (NGS) has enabled high throughput discovery of somatic mutations. Detection depends on experimental design, lab platforms, parameters and analysis algorithms. However, NGS-based somatic mutation detection is prone to erroneous calls, with reported validation rates near 54% and congruence between algorithms less than 50%. Here, we developed an algorithm to assign a single statistic, a false discovery rate (FDR), to each somatic mutation identified by NGS. This FDR confidence value accurately discriminates true mutations from erroneous calls. Using sequencing data generated from triplicate exome profiling of C57BL/6 mice and B16-F10 melanoma cells, we used the existing algorithms GATK, SAMtools and SomaticSNiPer to identify somatic mutations. For each identified mutation, our algorithm assigned an FDR. We selected 139 mutations for validation, including 50 somatic mutations assigned a low FDR (high confidence) and 44 mutations assigned a high FDR (low confidence). All of the high confidence somatic mutations validated (50 of 50), none of the 44 low confidence somatic mutations validated, and 15 of 45 mutations with an intermediate FDR validated. Furthermore, the assignment of a single FDR to individual mutations enables statistical comparisons of lab and computation methodologies, including ROC curves and AUC metrics. Using the HiSeq 2000, single end 50 nt reads from replicates generate the highest confidence somatic mutation call set.

BACKGROUND: Peptide microarrays offer an enormous potential as a screening tool for peptidomics experiments and have recently seen an increased field of application ranging from immunological studies to systems biology. By allowing the parallel analysis of thousands of peptides in a single run they are suitable for high-throughput settings. Since data characteristics of peptide microarrays differ from DNA oligonucleotide microarrays, computational methods need to be tailored to these specifications to allow a robust and automated data analysis. While follow-up experiments can ensure the specificity of results, sensitivity cannot be recovered in later steps. Providing sensitivity is thus a primary goal of data analysis procedures. To this end we created rapmad (Robust Alignment of Peptide MicroArray Data), a novel computational tool implemented in R. RESULTS: We evaluated rapmad in antibody reactivity experiments for several thousand peptide spots and compared it to two existing algorithms for the analysis of peptide microarrays. rapmad displays competitive and superior behavior to existing software solutions. Particularly, it shows substantially improved sensitivity for low intensity settings without sacrificing specificity. It thereby contributes to increasing the effectiveness of high throughput screening experiments. CONCLUSIONS: rapmad allows the robust and sensitive, automated analysis of high-throughput peptide array data. The rapmad R-package as well as the data sets are available from http://www.tron-mz.de/compmed.