cudaMap: a GPU accelerated program for gene expression connectivity mapping

The Potential of a Stratified Approach to Drug Repurposing in Alzheimer's Disease

Alzheimer's disease (AD) is a complex neurodegenerative condition that is characterized by the build-up of amyloid-beta plaques and neurofibrillary tangles. While multiple theories explaining the aetiology of the disease have been suggested, the underlying cause of the disease is still unknown. Despite this, several modifiable and non-modifiable factors that increase the risk of developing AD have been identified. To date, only eight AD drugs have ever gained regulatory approval, including six symptomatic and two disease-modifying drugs. However, not all are available in all countries and high costs associated with new disease-modifying biologics prevent large proportions of the patient population from accessing them. With the current patient population expected to triple by 2050, it is imperative that new, effective, and affordable drugs become available to patients. Traditional drug development strategies have a 99% failure rate in AD, which is far higher than in other disease areas. Even when a drug does reach the market, additional barriers such as high cost and lack of accessibility prevent patients from benefiting from them. In this review, we discuss how a stratified medicine drug repurposing approach may address some of the limitations and barriers that traditional strategies face in relation to drug development in AD. We believe that novel, stratified drug repurposing studies may expedite the discovery of alternative, effective, and more affordable treatment options for a rapidly expanding patient population in comparison with traditional drug development methods.

Data Integration Challenges for Machine Learning in Precision Medicine

A main goal of Precision Medicine is that of incorporating and integrating the vast corpora on different databases about the molecular and environmental origins of disease, into analytic frameworks, allowing the development of individualized, context-dependent diagnostics, and therapeutic approaches. In this regard, artificial intelligence and machine learning approaches can be used to build analytical models of complex disease aimed at prediction of personalized health conditions and outcomes. Such models must handle the wide heterogeneity of individuals in both their genetic predisposition and their social and environmental determinants. Computational approaches to medicine need to be able to efficiently manage, visualize and integrate, large datasets combining structure, and unstructured formats. This needs to be done while constrained by different levels of confidentiality, ideally doing so within a unified analytical architecture. Efficient data integration and management is key to the successful application of computational intelligence approaches to medicine. A number of challenges arise in the design of successful designs to medical data analytics under currently demanding conditions of performance in personalized medicine, while also subject to time, computational power, and bioethical constraints. Here, we will review some of these constraints and discuss possible avenues to overcome current challenges.

Scaling computational genomics to millions of individuals with GPUs

Current genomics methods are designed to handle tens to thousands of samples but will need to scale to millions to match the pace of data and hypothesis generation in biomedical science. Here, we show that high efficiency at low cost can be achieved by leveraging general-purpose libraries for computing using graphics processing units (GPUs), such as PyTorch and TensorFlow. We demonstrate > 200-fold decreases in runtime and ~ 5–10-fold reductions in cost relative to CPUs. We anticipate that the accessibility of these libraries will lead to a widespread adoption of GPUs in computational genomics.

Connectivity Mapping: Methods and Applications

Connectivity mapping resources consist of signatures representing changes in cellular state following systematic small-molecule, disease, gene, or other form of perturbations. Such resources enable the characterization of signatures from novel perturbations based on similarity; provide a global view of the space of many themed perturbations; and allow the ability to predict cellular, tissue, and organismal phenotypes for perturbagens. A signature search engine enables hypothesis generation by finding connections between query signatures and the database of signatures. This framework has been used to identify connections between small molecules and their targets, to discover cell-specific responses to perturbations and ways to reverse disease expression states with small molecules, and to predict small-molecule mimickers for existing drugs. This review provides a historical perspective and the current state of connectivity mapping resources with a focus on both methodology and community implementations.

Advances in distributed computing with modern drug discovery

INTRODUCTION

Computational chemistry dramatically accelerates the drug discovery process and high-performance computing (HPC) can be used to speed up the most expensive calculations. Supporting a local HPC infrastructure is both costly and time-consuming, and, therefore, many research groups are moving from in-house solutions to remote-distributed computing platforms. Areas covered: The authors focus on the use of distributed technologies, solutions, and infrastructures to gain access to HPC capabilities, software tools, and datasets to run the complex simulations required in computational drug discovery (CDD). Expert opinion: The use of computational tools can decrease the time to market of new drugs. HPC has a crucial role in handling the complex algorithms and large volumes of data required to achieve specificity and avoid undesirable side-effects. Distributed computing environments have clear advantages over in-house solutions in terms of cost and sustainability. The use of infrastructures relying on virtualization reduces set-up costs. Distributed computing resources can be difficult to access, although web-based solutions are becoming increasingly available. There is a trade-off between cost-effectiveness and accessibility in using on-demand computing resources rather than free/academic resources. Graphics processing unit computing, with its outstanding parallel computing power, is becoming increasingly important.

A review of connectivity map and computational approaches in pharmacogenomics

Large-scale perturbation databases, such as Connectivity Map (CMap) or Library of Integrated Network-based Cellular Signatures (LINCS), provide enormous opportunities for computational pharmacogenomics and drug design. A reason for this is that in contrast to classical pharmacology focusing at one target at a time, the transcriptomics profiles provided by CMap and LINCS open the door for systems biology approaches on the pathway and network level. In this article, we provide a review of recent developments in computational pharmacogenomics with respect to CMap and LINCS and related applications.

A review of connectivity map and computational approaches in pharmacogenomics

Large-scale perturbation databases, such as Connectivity Map (CMap) or Library of Integrated Network-based Cellular Signatures (LINCS), provide enormous opportunities for computational pharmacogenomics and drug design. A reason for this is that in contrast to classical pharmacology focusing at one target at a time, the transcriptomics profiles provided by CMap and LINCS open the door for systems biology approaches on the pathway and network level. In this article, we provide a review of recent developments in computational pharmacogenomics with respect to CMap and LINCS and related applications.

KRAS mutant colorectal cancer gene signatures identified angiotensin II receptor blockers as potential therapies

Colorectal cancer (CRC) is a life-threatening disease with high prevalence and mortality worldwide. The KRAS oncogene is mutated in approximately 40% of CRCs. While antibody based EGFR inhibitors (cetuximab and panitumumab) represent a major treatment strategy for advanced KRAS wild type (KRAS-WT) CRCs, there still remains no effective therapeutic course for advanced KRAS mutant (KRAS-MT) CRC patients.In this study, we employed a novel and comprehensive approach of gene expression connectivity mapping (GECM) to identify candidate compounds to target KRAS-MT tumors. We first created a combined KRAS-MT gene signature with 248 ranked significant genes using 677 CRC clinical samples. A series of 248 sub-signatures was then created containing an increasing number of the top ranked genes. As an input to GECM analysis, each sub-signature was translated into a statistically significant therapeutic drugs list, which was finally combined to obtain a single list of significant drugs.We identify four antihypertensive angiotensin II receptor blockers (ARBs) within the top 30 significant drugs indicating that these drugs have a mechanism of action that can alter the KRAS-MT CRC oncogenic signaling. A hypergeometric test (p-value = 6.57 × 10-6) confirmed that ARBs are significantly enriched in our results. These findings support the hypothesis that ARB antihypertensive drugs may directly block KRAS signaling resulting in improvement in patient outcome or, through a reversion to a KRAS wild-type phenotype, improve the response to anti-EGFR treatment. Antihypertensive angiotensin II receptor blockers are therefore worth further investigation as potential therapeutic candidates in this difficult category of advanced colorectal cancers.

QUADrATiC: scalable gene expression connectivity mapping for repurposing FDA-approved therapeutics

Background

Gene expression connectivity mapping has proven to be a powerful and flexible tool for research. Its application has been shown in a broad range of research topics, most commonly as a means of identifying potential small molecule compounds, which may be further investigated as candidates for repurposing to treat diseases. The public release of voluminous data from the Library of Integrated Cellular Signatures (LINCS) programme further enhanced the utilities and potentials of gene expression connectivity mapping in biomedicine.

Results

We describe QUADrATiC (http://go.qub.ac.uk/QUADrATiC), a user-friendly tool for the exploration of gene expression connectivity on the subset of the LINCS data set corresponding to FDA-approved small molecule compounds. It enables the identification of compounds for repurposing therapeutic potentials. The software is designed to cope with the increased volume of data over existing tools, by taking advantage of multicore computing architectures to provide a scalable solution, which may be installed and operated on a range of computers, from laptops to servers. This scalability is provided by the use of the modern concurrent programming paradigm provided by the Akka framework. The QUADrATiC Graphical User Interface (GUI) has been developed using advanced Javascript frameworks, providing novel visualization capabilities for further analysis of connections. There is also a web services interface, allowing integration with other programs or scripts.

Conclusions

QUADrATiC has been shown to provide an improvement over existing connectivity map software, in terms of scope (based on the LINCS data set), applicability (using FDA-approved compounds), usability and speed. It offers potential to biological researchers to analyze transcriptional data and generate potential therapeutics for focussed study in the lab. QUADrATiC represents a step change in the process of investigating gene expression connectivity and provides more biologically-relevant results than previous alternative solutions.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1062-1) contains supplementary material, which is available to authorized users.

Connectivity mapping using a combined gene signature from multiple colorectal cancer datasets identified candidate drugs including existing chemotherapies

BACKGROUND

While the discovery of new drugs is a complex, lengthy and costly process, identifying new uses for existing drugs is a cost-effective approach to therapeutic discovery. Connectivity mapping integrates gene expression profiling with advanced algorithms to connect genes, diseases and small molecule compounds and has been applied in a large number of studies to identify potential drugs, particularly to facilitate drug repurposing. Colorectal cancer (CRC) is a commonly diagnosed cancer with high mortality rates, presenting a worldwide health problem. With the advancement of high throughput omics technologies, a number of large scale gene expression profiling studies have been conducted on CRCs, providing multiple datasets in gene expression data repositories. In this work, we systematically apply gene expression connectivity mapping to multiple CRC datasets to identify candidate therapeutics to this disease.

RESULTS

We developed a robust method to compile a combined gene signature for colorectal cancer across multiple datasets. Connectivity mapping analysis with this signature of 148 genes identified 10 candidate compounds, including irinotecan and etoposide, which are chemotherapy drugs currently used to treat CRCs. These results indicate that we have discovered high quality connections between the CRC disease state and the candidate compounds, and that the gene signature we created may be used as a potential therapeutic target in treating the disease. The method we proposed is highly effective in generating quality gene signature through multiple datasets; the publication of the combined CRC gene signature and the list of candidate compounds from this work will benefit both cancer and systems biology research communities for further development and investigations.

From big data analysis to personalized medicine for all: challenges and opportunities

Recent advances in high-throughput technologies have led to the emergence of systems biology as a holistic science to achieve more precise modeling of complex diseases. Many predict the emergence of personalized medicine in the near future. We are, however, moving from two-tiered health systems to a two-tiered personalized medicine. Omics facilities are restricted to affluent regions, and personalized medicine is likely to widen the growing gap in health systems between high and low-income countries. This is mirrored by an increasing lag between our ability to generate and analyze big data. Several bottlenecks slow-down the transition from conventional to personalized medicine: generation of cost-effective high-throughput data; hybrid education and multidisciplinary teams; data storage and processing; data integration and interpretation; and individual and global economic relevance. This review provides an update of important developments in the analysis of big data and forward strategies to accelerate the global transition to personalized medicine.

Monocyte-macrophage differentiation of acute myeloid leukemia cell lines by small molecules identified through interrogation of the Connectivity Map database

The transcription factor C/EBPα is required for granulocytic differentiation of normal myeloid progenitors and is frequently inactivated in acute myeloid leukemia (AML) cells. Ectopic expression of C/EBPα in AML cells suppresses proliferation and induces differentiation suggesting that restoring C/EBPα expression/activity in AML cells could be therapeutically useful. Unfortunately, current approaches of gene or protein delivery in leukemic cells are unsatisfactory. However, "drug repurposing" is becoming a very attractive strategy to identify potential new uses for existing drugs. In this study, we assessed the biological effects of candidate C/EBPα-mimetics identified by interrogation of the Connectivity Map database. We found that amantadine, an antiviral and anti-Parkinson agent, induced a monocyte-macrophage-like differentiation of HL60, U937, Kasumi-1 myeloid leukemia cell lines, as indicated by morphology and differentiation antigen expression, when used in combination with suboptimal concentration of all trans retinoic acid (ATRA) or Vit D3. The effect of amantadine depends, in part, on increased activity of the vitamin D receptor (VDR), since it induced VDR expression and amantadine-dependent monocyte-macrophage differentiation of HL60 cells was blocked by expression of dominant-negative VDR. These results reveal a new function for amantadine and support the concept that screening of the Connectivity Map database can identify small molecules that mimic the effect of transcription factors required for myelo-monocytic differentiation.

NMF-mGPU: non-negative matrix factorization on multi-GPU systems

BACKGROUND

In the last few years, the Non-negative Matrix Factorization ( NMF ) technique has gained a great interest among the Bioinformatics community, since it is able to extract interpretable parts from high-dimensional datasets. However, the computing time required to process large data matrices may become impractical, even for a parallel application running on a multiprocessors cluster. In this paper, we present NMF-mGPU, an efficient and easy-to-use implementation of the NMF algorithm that takes advantage of the high computing performance delivered by Graphics-Processing Units ( GPUs ). Driven by the ever-growing demands from the video-games industry, graphics cards usually provided in PCs and laptops have evolved from simple graphics-drawing platforms into high-performance programmable systems that can be used as coprocessors for linear-algebra operations. However, these devices may have a limited amount of on-board memory, which is not considered by other NMF implementations on GPU.

RESULTS

NMF-mGPU is based on CUDA ( Compute Unified Device Architecture ), the NVIDIA's framework for GPU computing. On devices with low memory available, large input matrices are blockwise transferred from the system's main memory to the GPU's memory, and processed accordingly. In addition, NMF-mGPU has been explicitly optimized for the different CUDA architectures. Finally, platforms with multiple GPUs can be synchronized through MPI ( Message Passing Interface ). In a four-GPU system, this implementation is about 120 times faster than a single conventional processor, and more than four times faster than a single GPU device (i.e., a super-linear speedup).

CONCLUSIONS

Applications of GPUs in Bioinformatics are getting more and more attention due to their outstanding performance when compared to traditional processors. In addition, their relatively low price represents a highly cost-effective alternative to conventional clusters. In life sciences, this results in an excellent opportunity to facilitate the daily work of bioinformaticians that are trying to extract biological meaning out of hundreds of gigabytes of experimental information. NMF-mGPU can be used "out of the box" by researchers with little or no expertise in GPU programming in a variety of platforms, such as PCs, laptops, or high-end GPU clusters. NMF-mGPU is freely available at https://github.com/bioinfo-cnb/bionmf-gpu .

FastGCN: a GPU accelerated tool for fast gene co-expression networks

Gene co-expression networks comprise one type of valuable biological networks. Many methods and tools have been published to construct gene co-expression networks; however, most of these tools and methods are inconvenient and time consuming for large datasets. We have developed a user-friendly, accelerated and optimized tool for constructing gene co-expression networks that can fully harness the parallel nature of GPU (Graphic Processing Unit) architectures. Genetic entropies were exploited to filter out genes with no or small expression changes in the raw data preprocessing step. Pearson correlation coefficients were then calculated. After that, we normalized these coefficients and employed the False Discovery Rate to control the multiple tests. At last, modules identification was conducted to construct the co-expression networks. All of these calculations were implemented on a GPU. We also compressed the coefficient matrix to save space. We compared the performance of the GPU implementation with those of multi-core CPU implementations with 16 CPU threads, single-thread C/C++ implementation and single-thread R implementation. Our results show that GPU implementation largely outperforms single-thread C/C++ implementation and single-thread R implementation, and GPU implementation outperforms multi-core CPU implementation when the number of genes increases. With the test dataset containing 16,000 genes and 590 individuals, we can achieve greater than 63 times the speed using a GPU implementation compared with a single-thread R implementation when 50 percent of genes were filtered out and about 80 times the speed when no genes were filtered out.