Over the years, interest in computational storage devices has been growing steadily. This is largely due to the rise of data-intensive applications, such as machine learning, online video distribution, astrophysics, and genomics. Moving compute operations closer to the data provides benefits in terms of scaling possibilities and energy efficiency. The development of computational storage devices has been limited by the need for specialized and complex hardware. In this work, we propose a portable Linux-based firmware framework for the development of NVMe computational storage devices. Our firmware runs on a variety of hardware platforms ranging from expensive FPGA solutions to inexpensive off-the-shelf single board computers. The firmware leverages the vast Linux software ecosystem to facilitate the development and prototyping of novel computational storage devices. We benchmark our firmware on multiple hardware platforms and demonstrate its versatility through several computational examples including a content-aware disk image search engine based on natural language processing and AI-driven image recognition.

Electrochemical devices and systems are significant for the development of therapeutic drug monitoring (TDM) and personalized therapy. However, electrochemical sensors are usually not that much selective. Therefore, innovative machine learning (ML) approaches are now required to improve the selectivity at system level based on cyclic voltammograms (CV) obtained from electrochemical sensors in order to assure the quantification of several different drugs simultaneously present into the blood of patients. Based on an Artificial Neural Network (ANN), this paper proposes a novel model TwoWayANN along with an adaptive weighted cross-entropy loss (AWCEL) to address drugs interaction effectively and decline the quantification error range. The simulated dataset of etoposide (ETO) and methotrexate (MTX), proposed here as model drugs, is demonstrated to validate the efficacy of our proposed method. Our TwoWayANN model achieves the accuracy at 100% and 99.35% for ETO and MTX respectively within the error range of ±5μM. Our results are important for the development of point-of-care systems for applications in personalized therapy.

MOTIVATION: Generation of genotype data has been growing exponentially over the last decade. With the large size of recent datasets comes a storage and computational burden with ever increasing costs. To reduce this burden, we propose XSI, a file format with reduced storage footprint that also allows computation on the compressed data and we show how this can improve future analyses. RESULTS: We show that xSqueezeIt (XSI) allows for a file size reduction of 4-20× compared with compressed BCF and demonstrate its potential for 'compressive genomics' on the UK Biobank whole-genome sequencing genotypes with 8× faster loading times, 5× faster run of homozygozity computation, 30× faster dot products computation and 280× faster allele counts. AVAILABILITY AND IMPLEMENTATION: The XSI file format specifications, API and command line tool are released under open-source (MIT) license and are available at https://github.com/rwk-unil/xSqueezeIt. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The Pair-HMM forward algorithm is an essential algorithm found in many genomic related analyses. The high number of floating point operations in the algorithm makes it one of the main contributors to the compute time of analysis pipelines. To speed-up computations we propose an FPGA-based hardware accelerator for the Amazon AWS F1 Cloud platform. The accelerator is open source and has been tested within the popular Genomic Analysis Toolkit (GATK) pipeline. The accelerator achieved up to 15 × speed-up against the software implementation when used in-pipeline. The accelerator has also been tested in the experimental Spark (distributed) version of the GATK HaplotypeCaller tool. An in-depth analysis of the compute time contributions allowed to point out the main bottlenecks for accelerators in the GATK pipeline, resulting in a hybrid CPU-FPGA solution to best exploit both resources.

Poor adherence to medical regimen causes approximately 33% to 69% of medication-related hospitalizations and accounts for $100 billion in annual health care costs. In this paper we address the problem of unintentional non adherence, when patient fails to take a medication due to forgetfulness or carelessness. We present the safe approach to software implementation of a portable reminder device with enabled personalization of medical regimen. The presented prototype is designed for imatinib administration, a drug used to treat Chronic Myeloid Leukemia (CML). However, thanks to the component-based structure of the software, the method can be applied to other cases by replacing implementation of certain components.

Fault tolerance is a crucial operational aspect of biological systems and the self-repair capabilities of complex organisms far exceeds that of even the most advanced electronic devices. While many of the processes used by nature to achieve fault tolerance cannot easily be applied to silicon-based systems, in this paper we show that mechanisms loosely inspired by the operation of multicellular organisms can be transported to electronic systems to provide self-repair capabilities. Features such as dynamic routing, reconfiguration, and on-chip reprogramming can be invaluable for the realization of adaptive hardware systems and for the design of highly complex systems based on the kind of unreliable components that are likely to be introduced in the not-too-distant future. In this paper, we describe the implementation of fault tolerant features that address error detection and recovery through dynamic routing, reconfiguration, and on-chip reprogramming in a novel application specific integrated circuit. We take inspiration from three biological models:phylogenesis, ontogenesis,andepigenesis(hence the POE in POEtic). As in nature, our approach is based on a set of separate and complementary techniques that exploit the novel mechanisms provided by our device in the particular context of fault tolerance.