A novel computational architecture for large-scale genomics

Becker, Matthias; Schultze, Hartmut; Bresniker, Kirk; Singhal, Sharad; Ulas, Thomas; Schultze, Joachim L.

doi:10.1038/s41587-020-0699-5

Cited by 4 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, as GPUs, FPGAs and cloud computing become increasingly prevalent in the field, new compiler backends for Seq—including new compiler optimizations pertinent to each computing platform—would enable existing code to run without changes on these backends, and is ongoing work within the Seq project. Indeed, many novel, promising computer architectures such as memory-driven computing [7] require specific optimizations and program transformations to be fully taken advantage of; these can be performed automatically by the Seq compiler. Yet another unique advantage of a framework like Seq lies in its ability to provide domain-specific debugging or visualization support; as the compiler has knowledge of sequences, k -mers and operations involving them, debugging or visualization tools can be seamlessly integrated into the Seq framework, allowing users to track and observe in a meaningful way how data is transferred and manipulated throughout a program.…”

Section: Discussionmentioning

confidence: 99%

A Python-based optimization framework for high-performance genomics

Shajii

Numanagić

et al. 2020

Preprint

View full text Add to dashboard Cite

Exponentially-growing next-generation sequencing data requires high-performance tools and algorithms. Nevertheless, the implementation of high-performance computational genomics software is inaccessible to many scientists because it requires extensive knowledge of low-level software optimization techniques, forcing scientists to resort to high-level software alternatives that are less efficient. Here, we introduce Seq--- a Python-based optimization framework that combines the power and usability of high-level languages like Python with the performance of low-level languages like C or C++. Seq allows for shorter, simpler code, is readily usable by a novice programmer, and obtains significant performance improvements over existing languages and frameworks. We showcase and evaluate Seq by implementing seven standard, widely-used applications from all stages of the genomics analysis pipeline, including genome index construction, finding maximal exact matches, long-read alignment and haplotype phasing, and demonstrate its implementations are up to an order of magnitude faster than existing hand-optimized implementations, with just a fraction of the code. By enabling researchers of all backgrounds to easily implement high-performance analysis tools, Seq further opens the door to the democratization and scalability of computational genomics.

show abstract

Section: Discussionmentioning

confidence: 99%

A Python-based optimization framework for high-performance genomics

Shajii

Numanagić

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…for BC (OncotypeDX ® , MammaPrint ® , Prosigna ® , EndoPredict ® , and Breast Cancer Index SM ) which are included in national and international guidelines (NCCN, ASCO, ESMO, NICE, AGO, and St. Gallen) are representative and have been summarized in a recent review [5]. In particular, Oncotype DX ® has been successful in focusing on the additional benefits of CT for HR+ BC [6][7][8]. However, these tools are not universal, as they are limited to clinical factors such as HRs, menopausal status, and nodular status [9].…”

Section: Takeshita Et Almentioning

confidence: 99%

Development of a Machine Learning-Based Prognostic Model for Hormone Receptor-Positive Breast Cancer Using Nine-Gene Expression Signature

Takeshita,

Iwase,

et al. 2023

World J Oncol

View full text Add to dashboard Cite

Background: Determining the prognosis of hormone receptor positive (HR + ) breast cancer (BC), which accounts for 80% of all BCs, is critical in improving survival outcomes. Stratifying individuals at high risk of BC-related mortality and improving prognosis has been the focus of research for over a decade. However, these tools are not universal as they are limited to clinical factors. We hypothesized that a new framework for predicting prognosis in HR + BC patients can develop using artificial intelligence.Methods: A total of 2,338 HR + human epidermal growth factor receptor 2 negative (HER2 -) BC cases were analyzed from Molecular Taxonomy of Breast Cancer International Consortium (METABRIC), The Cancer Genome Atlas (TCGA), and Gene Expression Omnibus (GEO) cohorts. Groups were then divided into high-and low-risk categories utilizing a recurrence prediction model (RPM). An RPM was created by extracting nine prognosis-related genes from over 18,000 genes using a logistic progression model.Results: Risk classification by RPM was significantly stratified in both the discovery cohort and validation cohort. In the time-dependent area under the curve analysis, there was some variation depending on the cohort, but accuracy was found to decline significantly after about 10 years. Cell cycle related gene sets, MYC, and PI3K-AKT-mTOR signaling were enriched in high-risk tumors by the Gene Set Enrichment Analysis. High-risk tumors were associated with high levels of immune cells from the lymphoid and myeloid lineage and immune cytolytic activity, as well as low levels of stem cells and stromal cells. High-risk tumors were also associated with poor therapeutic effects of chemotherapy and endocrine therapy. Conclusions:This model was able to stratify prognosis in multiple cohorts. This is because the model reflects major BC therapeutic target pathways and tumor immune microenvironment and, further is supported by the therapeutic effect of chemotherapy and endocrine therapy.

show abstract

“…Having large amounts of data is obviously beneficial for computational learning algorithms, the more data you have, the more robust your classifiers, regressions, and mining strategies will be. However, as the tendencies move toward Precision Medicine, we can see how some major sources of primary biomedical information, such as genomics (in particular next generation sequencing) and imaging are becoming progressively cheaper (107-109), hence allowing their widespread use, nevertheless the computational costs of processing and analyzing the data are, for obvious reasons, growing fast (110)(111)(112)(113)(114).…”

Section: Challenges To Computational Learning In Precision Medicinementioning

confidence: 99%

Data Integration Challenges for Machine Learning in Precision Medicine

Martínez-García

Hernández‐Lemus

2022

Front. Med.

View full text Add to dashboard Cite

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.

show abstract

A novel computational architecture for large-scale genomics

Cited by 4 publications

References 12 publications

A Python-based optimization framework for high-performance genomics

A Python-based optimization framework for high-performance genomics

Development of a Machine Learning-Based Prognostic Model for Hormone Receptor-Positive Breast Cancer Using Nine-Gene Expression Signature

Data Integration Challenges for Machine Learning in Precision Medicine

Contact Info

Product

Resources

About