Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included “machine learning” or “artificial intelligence” and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.

/pdf/a-systematic-review-of-the-applications-of-artificial-4x6xtdp54q.pdf

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases.

Deep learning methods applied to chemistry can be used to accelerate the discovery of new molecules. This work introduces GraphINVENT, a platform developed for graph-based molecular design using graph neural networks (GNNs). GraphINVENT uses a tiered deep neural network architecture to probabilistically generate new molecules a single bond at a time. All models implemented in GraphINVENT can quickly learn to build molecules resembling the training set molecules without any explicit programming of chemical rules. The models have been benchmarked using the MOSES distribution-based metrics, showing how GraphINVENT models compare well with state-of-the-art generative models. This work is one of the first thorough graph-based molecular design studies, and illustrates how GNN-based models are promising tools for molecular discovery.

Graph networks for molecular design

This paper provides the first comparison of performance and energy efficiency of high productivity computing systems based on FPGA (Field-Programmable Gate Array) and GPU (Graphics Processing Unit) technologies. The search for higher performance compute solutions has recently led to great interest in heterogeneous systems containing FPGA and GPU accelerators. While these accelerators can provide significant performance improvements, they can also require much more design effort than a pure software solution, reducing programmer productivity. The CUDA system has provided a high productivity approach for programming GPUs. This paper evaluates the High-Productivity Reconfigurable Computer (HPRC) approach to FPGA programming, where a commodity CPU instruction set architecture is augmented with instructions which execute on a specialised FPGA co-processor, allowing the CPU and FPGA to co-operate closely while providing a programming model similar to that of traditional software. To compare the GPU and FPGA approaches, we select a set of established benchmarks with different memory access characteristics, and compare their performance and energy efficiency on an FPGA-based Hybrid-Core system with a GPU-based system. Our results show that while GPUs excel at streaming applications, high-productivity reconfigurable computing systems outperform GPUs in applications with poor locality characteristics and low memory bandwidth requirements.

Comparing performance and energy efficiency of FPGAs and GPUs for high productivity computing

The discovery of molecular structures with desired properties for applications in drug discovery, crop protection, or chemical biology is among the most impactful scientific challenges. However, given the complexity of biological systems and the associated cost for experiments and trials, molecular design is also scientifically very challenging, prone to failure, inherently expensive and time consuming [1, 2]. To improve our odds and the timelines in this process, and to identify good starting points, unbiased incorporation of knowledge through continuous analysis of literature and patents from different scientific fields is required [3]. The number of yearly publications is increasing, and a good collaboration between scientific experts across disciplines is required to fully evaluate the potential of a hypothesis. The theoretical space of chemistry, even when limited by molecular size, is huge [4] and dramatically exceeds what we can assess experimentally and even computationally. How to navigate through it efficiently and select molecules that satisfy the multiple parameters that need to be optimized and that are synthetically accessible [5]? The number of existing data points at the beginning of a project are low. How can we enrich projects in short time frames with informative molecules and data that are subsequently used to drive the design? With these questions in mind, it comes as no surprise that data mining and statistics have been integrated into molecular discovery and design pipelines to provide computational support in the prioritization of molecular hypotheses [6, 7]. Machine learning algorithms have been part of the routine toolbox of computational and medicinal chemists for decades. The recent increase in applications and coverage of these methodologies has been attributed to advances in computational power, the growing amount of digitized research data, and an increasing theoretical understanding of the algorithms and their shortcomings. However, given the gradual character of these evolutions, it might be counterintuitive to expect a dramatic revolution of molecular design. Nevertheless, extravagant claims have been made for the ability of Artificial Intelligence (AI) to accelerate the design process [8, 9]; how well founded are these claims? While there is unquestionably a lot of potential in novel computational tools, it is important to scrutinize them and compare their performance to already existing methods, to objectively distinguish real progress from promotion. Only such careful evaluations will enable us to shed light on whether novel artificial intelligence methods contribute to an evolution or a revolution of the established scientific discipline of computer-assisted molecular design [10].

/pdf/artificial-intelligence-in-chemistry-and-drug-design-43r2qn6juo.pdf

Artificial intelligence in chemistry and drug design.

The nature of modern astronomy means that a number of interesting problems exhibit a substantial computational bound and this situation is gradually worsening. Scientists, increasingly fighting for valuable resources on conventional high-performance computing (HPC) facilities--often with a limited customizable user environment--are increasingly looking to hardware acceleration solutions. We describe here a heterogeneous CPU/GPGPU/FPGA desktop computing system (the "Chimera"), built with commercial-off-the-shelf components. We show that this platform may be a viable alternative solution to many common computationally bound problems found in astronomy, however, not without significant challenges. The most significant bottleneck in pipelines involving real data is most likely to be the interconnect (in this case the PCI Express bus residing on the CPU motherboard). Finally, we speculate on the merits of our Chimera system on the entire landscape of parallel computing, through the analysis of representative problems from UC Berkeley's "Thirteen Dwarves."

/pdf/the-chimera-an-off-the-shelf-cpu-gpgpu-fpga-hybrid-computing-3qkaewf4b1.pdf

The Chimera: an off-the-shelf CPU/GPGPU/FPGA hybrid computing platform

Heterogeneous or co-processor architectures are becoming an important component of high productivity computing systems (HPCS). In this work the performance of a GPU based HPCS is compared with the performance of a commercially available FPGA based HPC. Contrary to previous approaches that focussed on specific examples, a broader analysis is performed by considering processes at an architectural level. A set of benchmarks is employed that use different process architectures in order to exploit the benefits of each technology. These include the asynchronous pipelines common to "map" tasks, a partially synchronous tree common to "reduce" tasks and a fully synchronous, fully connected mesh. We show that the GPU is more productive than the FPGA architecture for most of the benchmarks and conclude that FPGA-based HPCS is being marginalised by GPUs.

/pdf/gpu-versus-fpga-for-high-productivity-computing-3lodjrcucg.pdf

GPU Versus FPGA for High Productivity Computing

This paper introduces BRADSHAW (Biological Response Analysis and Design System using an Heterogenous, Automated Workflow), a system for automated molecular design which integrates methods for chemical structure generation, experimental design, active learning and cheminformatics tools. The simple user interface is designed to facilitate access to large scale automated design whilst minimising software development required to introduce new algorithms, a critical requirement in what is a very fast moving field. The system embodies a philosophy of automation, best practice, experimental design and the use of both traditional cheminformatics and modern machine learning algorithms.

/pdf/bradshaw-a-system-for-automated-molecular-design-4wb1ct23vj.pdf

BRADSHAW: a system for automated molecular design

In addition to routine clinical examination, unobtrusive and physical monitoring of Rheumatoid Arthritis (RA) patients provides an important source of information to enable understanding the impact of the disease on quality of life. Besides an increase in sedentary behaviour, pain in RA can negatively impact simple physical activities such as getting out of bed and standing up from a chair. The objective of this work is to develop a method that can generate fine-grained actigraphies to capture the impact of the disease on the daily activities of patients. A processing methodology is presented to automatically tag activity accelerometer data from a cohort of moderate-to-severe RA patients. A study of procesing methods based on machine learning and deep learning is provided. Thirty subjects, 10 RA patients and 20 healthy control subjects, were recruited in the study. A single tri-axial accelerometer was attached to the position of the fifth lumbar vertebra (L5) of each subject with a tag prediction granularity of 3 s. The proposed method is capable of handling unbalanced datasets from tagged data while accounting for long-duration activities such as sitting and lying, as well as short transitions such as sit-to-stand or lying-to-sit. The methodology also includes a novel mechanism for automatically applying a threshold to predictions by their confidence levels, in addition to a logical filter to correct for infeasible sequences of activities. Performance tests showed that the method was able to achieve around 95% accuracy and 81% F-score. The produced actigraphies can be helpful to generate objective RA disease-specific markers of patient mobility in-between clinical site visits.

Developing Fine-Grained Actigraphies for Rheumatoid Arthritis Patients from a Single Accelerometer Using Machine Learning.

High-level power and performance estimation of FPGA-based soft processors and its application to design space exploration

This paper presents a power and execution time estimation framework for an FPGA-based soft processor when considering the implementation of image compression techniques. Using the proposed framework, a quick power consumption and execution time estimate can be obtained early in the design phase allowing system designers to estimate these performance metrics without the need of implementing the algorithm or generating all possible soft processor architectures. This estimate is performed using both high-level algorithm parameters and soft processor architecture parameters. For system designers this can result in fast design space exploration. The model can predict the execution time of an algorithm with an average of 139% less relative error than predictions using only architecture parameters with the same framework.

http://cas.ee.ic.ac.uk/people/ccb98/papers/PowellFPL12.pdf

Adam Powell

Papers

GPU Versus FPGA for High Productivity Computing

BRADSHAW: a system for automated molecular design

Developing Fine-Grained Actigraphies for Rheumatoid Arthritis Patients from a Single Accelerometer Using Machine Learning.

High-level power and performance estimation of FPGA-based soft processors and its application to design space exploration

Early performance estimation of image compression methods on soft processors