Using machine learning approaches for multi-omics data analysis: A review

Biotechnology Advances, Год журнала: 2021, Номер 49, С. 107739 - 107739

Опубликована: Март 29, 2021

Язык: Английский

---

Integration strategies of multi-omics data for machine learning analysis

Computational and Structural Biotechnology Journal, Год журнала: 2021, Номер 19, С. 3735 - 3746

Опубликована: Янв. 1, 2021

Increased availability of high-throughput technologies has generated an ever-growing number omics data that seek to portray many different but complementary biological layers including genomics, epigenomics, transcriptomics, proteomics, and metabolomics. New insight from these have been obtained by machine learning algorithms produced diagnostic classification biomarkers. Most biomarkers date however only include one omic measurement at a time thus do not take full advantage recent multi-omics experiments now capture the entire complexity systems. Multi-omics integration strategies are needed combine knowledge brought each layer. We summarized most methods/ frameworks into five strategies: early, mixed, intermediate, late hierarchical. In this mini-review, we focus on challenges existing paying special attention applications.

Язык: Английский

---

Multimodal deep learning for biomedical data fusion: a review

Briefings in Bioinformatics, Год журнала: 2021, Номер 23(2)

Опубликована: Дек. 14, 2021

Biomedical data are becoming increasingly multimodal and thereby capture the underlying complex relationships among biological processes. Deep learning (DL)-based fusion strategies a popular approach for modeling these nonlinear relationships. Therefore, we review current state-of-the-art of such methods propose detailed taxonomy that facilitates more informed choices biomedical applications, as well research on novel methods. By doing so, find deep often outperform unimodal shallow approaches. Additionally, proposed subcategories show different advantages drawbacks. The has shown that, especially intermediate strategies, joint representation is preferred it effectively models interactions levels organization. Finally, note gradual fusion, based prior knowledge or search promising future path. Similarly, utilizing transfer might overcome sample size limitations sets. As sets become available, DL approaches present opportunity to train holistic can learn regulatory dynamics behind health disease.

Язык: Английский

---

State of the Field in Multi-Omics Research: From Computational Needs to Data Mining and Sharing

Frontiers in Genetics, Год журнала: 2020, Номер 11

Опубликована: Дек. 10, 2020

Multi-omics, variously called integrated omics, pan-omics, and trans-omics, aims to combine two or more omics data sets aid in analysis, visualization interpretation determine the mechanism of a biological process. Multi-omics efforts have taken center stage biomedical research leading development new insights into events processes. However, mushrooming myriad tools, datasets, approaches tends inundate literature overwhelm researchers field. The this review are provide an overview current state field, inform on available reliable resources, discuss application statistics machine/deep learning multi-omics analyses, findable, accessible, interoperable, reusable (FAIR) research, point best practices benchmarking. Thus, we guidance interested users domain by addressing challenges underlying biology, giving toolset, common pitfalls, acknowledging methods’ limitations. We conclude with practical advice recommendations software engineering reproducibility share comprehensive awareness for end-to-end workflow.

Язык: Английский

---

Artificial intelligence and machine learning‐aided drug discovery in central nervous system diseases: State‐of‐the‐arts and future directions

Medicinal Research Reviews, Год журнала: 2020, Номер 41(3), С. 1427 - 1473

Опубликована: Дек. 9, 2020

Abstract Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) remains the most challenging area drug discovery, accompanied with long timelines and high attrition rates. With rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) machine learning (ML) have emerged as an indispensable tool to draw meaningful insights improve decision making discovery. Thanks advancements AI ML algorithms, now AI/ML‐driven solutions unprecedented potential accelerate process CNS discovery better success rate. In this review, we comprehensively summarize AI/ML‐powered pharmaceutical efforts their implementations area. After introducing AI/ML models well conceptualization preparation, outline applications technologies several key procedures including target identification, compound screening, hit/lead generation optimization, response synergy prediction, de novo design, repurposing. We review current state‐of‐the‐art AI/ML‐guided focusing on blood–brain barrier permeability prediction implementation into neurological diseases. Finally, discuss major challenges limitations approaches possible future directions that may provide resolutions these difficulties.

Язык: Английский

---

Ensemble deep learning in bioinformatics

Nature Machine Intelligence, Год журнала: 2020, Номер 2(9), С. 500 - 508

Опубликована: Авг. 17, 2020

Язык: Английский

---

Current progress and open challenges for applying deep learning across the biosciences

Nature Communications, Год журнала: 2022, Номер 13(1)

Опубликована: Апрель 1, 2022

Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges computational biology: half-century-old problem protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives DL on five broad areas: prediction, function genome engineering, systems biology data integration, phylogenetic inference. We each application area cover main bottlenecks approaches, such as training data, scope, ability to leverage existing architectures new contexts. To conclude, provide a summary subject-specific general for across biosciences.

Язык: Английский

---

Integrated Multi-Omics Analyses in Oncology: A Review of Machine Learning Methods and Tools

Frontiers in Oncology, Год журнала: 2020, Номер 10

Опубликована: Июнь 30, 2020

In recent years, high-throughput sequencing technologies provide unprecedented opportunity to depict cancer samples at multiple molecular levels. The integration and analysis of these multi-omics datasets is a crucial critical step gain actionable knowledge in precision medicine framework. This paper explores data-driven methodologies that have been developed applied respond major challenges stratified oncology, including patients’ phenotyping, biomarker discovery drug repurposing. We systematically retrieved peer-reviewed journals published from 2014 2019, select thoroughly describe the tools presenting most promising innovations regarding heterogeneous data, machine learning successfully tackled complexity frameworks deliver results for clinical practice. review organized according methods: Deep learning, Network-based methods, Clustering, Features Extraction Transformation, Factorization. an overview available each methodological group underline relationship among different categories. Our revealed how could be exploited drive but also current limitations development data integration.

Язык: Английский

---

A roadmap for multi-omics data integration using deep learning

Briefings in Bioinformatics, Год журнала: 2021, Номер 23(1)

Опубликована: Окт. 7, 2021

Abstract High-throughput next-generation sequencing now makes it possible to generate a vast amount of multi-omics data for various applications. These have revolutionized biomedical research by providing more comprehensive understanding the biological systems and molecular mechanisms disease development. Recently, deep learning (DL) algorithms become one most promising methods in analysis, due their predictive performance capability capturing nonlinear hierarchical features. While integrating translating into useful functional insights remain biggest bottleneck, there is clear trend towards incorporating analysis help explain complex relationships between layers. Multi-omics role improve prevention, early detection prediction; monitor progression; interpret patterns endotyping; design personalized treatments. In this review, we outline roadmap integration using DL offer practical perspective advantages, challenges barriers implementation data.

Язык: Английский

---

Deep learning in drug discovery: an integrative review and future challenges

Artificial Intelligence Review, Год журнала: 2022, Номер 56(7), С. 5975 - 6037

Опубликована: Ноя. 17, 2022

Recently, using artificial intelligence (AI) in drug discovery has received much attention since it significantly shortens the time and cost of developing new drugs. Deep learning (DL)-based approaches are increasingly being used all stages development as DL technology advances, drug-related data grows. Therefore, this paper presents a systematic Literature review (SLR) that integrates recent technologies applications Including, drug-target interactions (DTIs), drug-drug similarity (DDIs), sensitivity responsiveness, drug-side effect predictions. We present more than 300 articles between 2000 2022. The benchmark sets, databases, evaluation measures also presented. In addition, provides an overview how explainable AI (XAI) supports problems. dosing optimization success stories discussed well. Finally, digital twining (DT) open issues suggested future research challenges for Challenges to be addressed, directions identified, extensive bibliography is included.

Язык: Английский

---