Innovations in Genomics and Big Data Analytics for Personalized Medicine and Health Care: A Review

“Machine learning imposes a major societal impact in many computational biology applications [53,54].”

“ExAC, GNOMAD, and the Beacon Network databases provide support in the understanding of genetic variations and identifying variants that are unique within a specific ethnic group [22].”

“Based on these findings, it is possible to perform drug repositioning using connectivity map (CMAP) technologies provided by the Broad Institute [74].”

“Most importantly, the GEM modeling approach is being used in multiple medical domains such as cancer [42] obesity [43], and in Alzheimer’s disease [44].”

“Through digital medicine, big data analysis will prove to be an invaluable tool for health care organizations as it will provide more opportunities for proactive intervention and a more holistic view of the patients’ conditions with consolidated real-time information [109].”

“Translational research is usually focused on collecting data abundantly, for example, clinical data, imaging data, genetic and genomic data, and analysts are usually found to be lacking in skills to interpret such types of data [10,62,92].”

“Among them, there is an FDA approved MammaPrint prognostic test for breast cancer based on 70 gene signatures [56].”

“…models are the best example of constraint-based models that provide a mathematical framework to understand the metabolic capacities of a cell, enabling system wide analysis of genetic perturbations, exploring metabolic diseases, and finding the essential enzymatic reactions and drug targets [41].”

“Various sources of big data in the health care industry and in biomedical research include medical records of patients, results of medical examinations, and hospital records, etc. [16].”

“Electronic health records (EHRs) are most significant application of big data in medicine and health care [115,116].”

“The big data paradigm shift is significantly transforming health care and biomedical research [109,136–139], having the potential to better process clinical and biomolecular information that spans the four dimensions of volume, velocity, variety, and veracity, referring to scale, rate, forms, and content of generated…”

“Although big data analysis promises great advantages and a potential solution to a diverse range of problems, there remain many unique technical, computational, and statistical challenges that must be addressed to fully explore its potential [103].”

“The big data paradigm shift is significantly transforming health care and biomedical research [109,136–139], having the potential to better process clinical and biomolecular information that spans the four dimensions of volume, velocity, variety, and veracity, referring to scale, rate, forms, and…”

“Another significant use of big data is essential for tackling the hospitalization risk for particular patients with chronic diseases [119,120].”

“Precision medicine can be succinctly defined as an approach to provide the right treatments to the right patients at the right time [8].”

“Moreover, earlier research has shown that significant information from a single cell data can provide more details about the biological processes in comparison to the bulk analysis of multiple cell types in a mixed cell population [89].”

“…spurious correlations, incidental endogeneity, noise accumulation, experimental variations, statistical biases, and measurement errors impede progress at all phases of the big data analysis from data collection and analysis to result in elucidation that can create value from the data [105,106].”

“Technical and methodological approaches have been systemically discussed elsewhere and we direct the reader to these excellent reviews [10].”

“Another significant use of big data is essential for tackling the hospitalization risk for particular patients with chronic diseases [119,120].”

“Drug discovery is a very challenging problem due to the high attrition rates in de novo design due to the lack of the efficacity of the new compounds and due to possible development of undesirable side effects [79–81].”

“There are new ways for measuring the single cell genome and transcriptome sequencing (G&T-seq) allowing us to simultaneously obtain both transcriptomic and genomic information from a single cell [90], which can provide clearer information that may be helpful in designing precision medicine [9].”

“Machine learning imposes a major societal impact in many computational biology applications [53,54].”

“Personalized medicine is a practice of medicine that uses an individual’s genetic profile to guide decisions made regarding the prevention, diagnosis, and treatment of disease [3].”

“Moreover, through data-driven analysis of genetic information as well as efficient predictions for patients, big data analytics in health care can play an important role in the development of new ground breaking drugs and innovative, forward-thinking therapies [125].”

“Here, we identify key conceptual and infrastructural challenges and provide a perspective on how advances can be and are being used to arrive at precision medicine strategies with specific examples [9].”

“MIMs actually represent the physical and causal interactions based on knowledge based information among biological species in the form of networks [38].”

“Machine learning approaches have been applied to massive data collected through genome sequencing, with the aim to precisely define what treatment method will work for an individual [55].”

“It is evident from recent advances in the pharmacological and genetic behavior of various drugs that ge-netic variations in a single individual could lead to differences in the response to drugs [28].”

“Personalized medicine refers to the patient’s treatment based on their personal clinical characterization [26].”

“Moreover, by drilling down into insights such as medication type, symptoms, and the frequency of medical visits, among many others, it is possible for health care institutions to provide accurate preventative care and, ultimately, reduce hospital admissions [121].”

“QMs consist of a set of differential equations containing variables and parameters that describe how the system responds to different stimuli or perturbations [48].”

“On the other hand, data-driven approaches (machine learning (ML) and deep learning (DL) use algorithms and artificial intelligence (AI) methodology [36,37].”

“There are so many applications where big data is being implemented to enhance patient care, and, ultimately, can save lives [113].”

“This often results in non-uniform analysis, and indeed, re-analysis of the same data using different pipelines yields different outcomes [24,25].”

“Electronic health records (EHRs) are most significant application of big data in medicine and health care [115,116].”

“Massive accumulation of large-scale molecular and clinical data in recent decades has radically changed personalized medicine and has raised great expectations concerning its impact on biomedical research and health care [1,2].”

“…Commission, big data can be defined as “Big data in health encompasses high volume, high diversity biological, clinical, environmental, and lifestyle information collected from single individuals to large cohorts, in relation to their health and wellness status, at one or several time points” [15].”

“MIMs explore the information about different mechanistic pathways and regulatory modules involved in a disease such as Parkinson’s [39] or signaling in cancer [40], respectively.”

“Translational research is usually focused on collecting data abundantly, for example, clinical data, imaging data, genetic and genomic data, and analysts are usually found to be lacking in skills to interpret such types of data [10,62,92].”

“Recent scientific advancements in high-throughput, high-resolution data-generating technologies enables cost-effective analysis of big datasets on individual health [6].”

“A machine learning echocardiography algorithm proposed by Madani et al. provided an accuracy of greater than 90% for the diagnosis of cardiac disease [61].”

“Machine learning and AI approaches work with different types of data including genetic, genomic [62], epigenomic [63,64], transcriptomic [65], metabolomic data [66], medical images, biobanks data [67], electronic health records (EHR) [68], scientific literature data, etc.”

“Most importantly, the GEM modeling approach is being used in multiple medical domains such as cancer [42] obesity [43], and in Alzheimer’s disease [44].”

“Big data analysis will empower digital health care in a way that will ensure the timely access of clinicians to the entire scope of a patient’s health information while reducing the need for in-person visits and improving patient outcome [108].”

“The computational problem consists of finding a new compound that provides the desirable structure–activity relationships (SAR data) [82,83].”

“Therefore, imperfect standardization has allowed for the sharing of genomic data across institutions into either aggregated databases such as ExAC, GNOMAD [22] or as federated databases such as the Beacon Network [23].”

“Therefore, pharmacokinetic models can be described by compartmental pharmacokinetic (PK) modeling [51] or by physiologically based PK (PBPK) modeling [52].”

“(EMA) [34,35].”

“The big data paradigm shift is significantly transforming health care and biomedical research [109,136–139], having the potential to better process clinical and biomolecular information that spans the four dimensions of volume, velocity, variety, and veracity, referring to scale, rate, forms, and…”

“The computational problem consists of finding a new compound that provides the desirable structure–activity relationships (SAR data) [82,83].”

“(EMA) [34,35].”

“Two other fields of active work are de novo drug design [77] and the optimization of gene therapies [78].”

“In the current situation, large amount of genomics data could be used to address personalized health care issues [104] and can help to propose new drugs for the treatment of gene related disorders.”

“MIMs explore the information about different mechanistic pathways and regulatory modules involved in a disease such as Parkinson’s [39] or signaling in cancer [40], respectively.”

“Algorithms represent the terminal node in the final predictions from big data [85].”

“Two other fields of active work are de novo drug design [77] and the optimization of gene therapies [78].”

“Furthermore, upon overlying expression data, such maps serve as visualization tools for the activity level of regulators and their targets of established disease markers, which provide the simplest mechanistic visualization of data [31].”

“Drug discovery is a very challenging problem due to the high attrition rates in de novo design due to the lack of the efficacity of the new compounds and due to possible development of undesirable side effects [79–81].”

“Temporal data are more often related to clinical studies and mainly depend on time series, with or without a sequence of events (i.e., the time-based quantitative measurements or sequence of temporal events related to particular clinical study) [88].”

“…of data including genetic, genomic [62], epigenomic [63,64], transcriptomic [65], metabolomic data [66], medical images, biobanks data [67], electronic health records (EHR) [68], scientific literature data, etc., and are able to combine all of this information to design optimum classifiers [69].”

“These models are located in flat curvilinear valleys of the cost function landscape [17,18].”

“The added value of such computational odels, sometimes called digital evidence, in medicine is also acceptable by the scientific community [32,33] and the U.”

“In the context of systems medicine, this approach is often applied for cancer research [46,47].”

“Therefore, pharmacokinetic models can be described by compartmental pharmacokinetic (PK) modeling [51] or by physiologically based PK (PBPK) modeling [52].”

“…and AI approaches work with different types of data including genetic, genomic [62], epigenomic [63,64], transcriptomic [65], metabolomic data [66], medical images, biobanks data [67], electronic health records (EHR) [68], scientific literature data, etc., and are able to combine all of this…”

“In the context of systems medicine, this approach is often applied for cancer research [46,47].”

“One of the major problems in the use of big data in medicine is that medical data have been collected across different states, hospitals, and administrative departments using different protocols [127–129].”

“It is known that during online data collection and transmission, health care devices are functional with the help of their MAC addresses and Internet protocol (IP) addresses [97,131].”

“Most importantly, the GEM modeling approach is being used in multiple medical domains such as cancer [42] obesity [43], and in Alzheimer’s disease [44].”

“Moreover, the BluePrint test has also demonstrated the expression data, which could be supportive for personalized medicine in MINDACT and IMPACt trials [59].”

“Moreover, heterogeneity might be terminological, conceptual, syntactic, or semiotic Moreover, heterogeneity might be terminological, conceptual, syntactic, or semiotic in nature [104,107]. in nature [104,107].”

“Drug repurposing, also called drug repositioning, of the already known FDA approved compounds for new therapeutic uses is a very effective methodology to find a cure in rare diseases where the economic constraints for new drug development are very important [75].”

“As a result, specialists would be able to detect previously unidentified pathogens and their strains, which can aid in the development of personalized medicine [87].”

“…of data including genetic, genomic [62], epigenomic [63,64], transcriptomic [65], metabolomic data [66], medical images, biobanks data [67], electronic health records (EHR) [68], scientific literature data, etc., and are able to combine all of this information to design optimum classifiers [69].”

“Therefore, the best way to deal with such problems is by reducing the dimension to perform a robust uncertainty analysis of the corresponding medical decision problem [19,20].”

“Machine learning and AI approaches work with different types of data including genetic, genomic [62], epigenomic [63,64], transcriptomic [65], metabolomic data [66], medical images, biobanks data [67], electronic health records (EHR) [68], scientific literature data, etc., and are able to combine…”

“Every record is comprised of one modifiable file, which means that doctors can implement changes over time with no paperwork and no danger of data replication [117].”

“However, the last decade has seen remarkable progress in the development of standard genomic data formats such as FASTQ, BAM/CRAM, and VCF files [21].”

“By linking together diverse datasets to reveal hitherto-unknown casual pathways and correlations, big data allows for far more precision and tailoring than was ever before possible [4].”

“We will move from standard regression-based methods, which are a subset of supervised machine learning methods, because the standard regression models can be used in the machine learning framework to learn from the data and provide outcome predictions based on the inputs [130].”

“Other successful personalized medicine examples of “treatment–biomarker” combinations are in colon cancer (Erbitux–EFGR) and lung cancer (Xalkori–ALK) [76].”

“Gene therapy is an experimental technique that uses genes to treat or prevent disease [84].”

“Based on such problems, most countries have created legislative principles to secure the personal health care privacy and confidentiality of medical records such as the HIPAA under the Privacy Rule of 2003 in the United States [134,135].”

“There are multiple applications of this methodology in the field of proteomics [95], genomics [96], clinical prognosis [97], cancer treatment [98], aging [99], analysis of defective pathways [100,101], and drug repositioning [102].”

“Additionally, the epigenomic regulation of the transcriptome can be achieved via epigenomics through chemical compounds that bind to the DNA and alter gene expression [73].”

“Personalized or precision medicine is an emerging medical practice based on a data-driven approach that considers relevant medical, genetic, behavioral, and environmental information about an individual to determine patient-specific therapy [2,4,5].”

“Moreover, there are various open software applications that can track cell phone locations and the names of social media users through MAC and GPS big data, which might be used for malicious reasons [132,133].”

“…types of data including genetic, genomic [62], epigenomic [63,64], transcriptomic [65], metabolomic data [66], medical images, biobanks data [67], electronic health records (EHR) [68], scientific literature data, etc., and are able to combine all of this information to design optimum…”

“There is no unique model capable of solving this problem perfectly, so we need to explore different techniques, obtaining a solution with its uncertainty assessment, using a consensus strategy [94].”

“There are multiple applications of this methodology in the field of proteomics [95], genomics [96], clinical prognosis [97], cancer treatment [98], aging [99], analysis of defective pathways [100,101], and drug repositioning [102].”

“There are multiple applications of this methodology in the field of proteomics [95], genomics [96], clinical prognosis [97], cancer treatment [98], aging [99], analysis of defective pathways [100,101], and drug repositioning [102].”

“…data analyses will eventually be beneficial for the patients themselves, especially for those who can utilize telemedicine and remote patient monitoring to their advantage, in order to enjoy more flexible and convenient access to care, which in turn will help them to live healthier lives [110–112].”

“These advancements have led many research groups to investigate different aspects of personalized medicine such as diagnosis, prognosis, and pharmacogenomics through computational approaches [30].”

“Data analytics in health care can streamline, innovate, provide security, save lives, and give confidence and clarity [126].”

“The patient’s individual characteristics are used to modify treatment in a way that might be more intricate compared to the standard course [27].”

“The proposed algorithm can be easily adopted in many other clinical practices for personalized medicine [86].”

“MammaPrint is a microarray-based signature method using formalin-fixed-paraffin-embedded (FFPE) or fresh tissue for microarray analysis [57,58].”

“Most importantly, in personalized medicine, ODE models are applied for individual biomarker discovery [49], drug response, and tailored treatments [50].”

“Data volumes are increasing continuously and beyond comprehension, while there is a shortage of bioinformaticians in the current scenario [91].”

“Therefore, better understating of these data and better strategic plans can cure more patients in the most diverse areas [118].”

“Most importantly, in personalized medicine, ODE models are applied for individual biomarker discovery [49], drug response, and tailored treatments [50].”

“Machine learning and AI approaches work with different types of data including genetic, genomic [62], epigenomic [63,64], transcriptomic [65], metabolomic data [66], medical images, biobanks data [67], electronic health records (EHR) [68], scientific literature data, etc.”

“There are multiple applications of this methodology in the field of proteomics [95], genomics [96], clinical prognosis [97], cancer treatment [98], aging [99], analysis of defective pathways [100,101], and drug repositioning [102].”

“…there is a need for new computational approaches such as faster, more integrated processors, larger computer memories, improved sensors, new much sophisticated algorithms, methodologies and cloud computing, which may guide future clinical practice by providing clinically useful information [6,7].”

“…on genomic, epigenomic profiles, and drug and treatment responses, computational methods can classify the patients into different subtypes that can be helpful in disease prediction, the diagnosis of various cancers, generating disease decision rules, and personalized recommendation systems [29].”

“…data analyses will eventually be beneficial for the patients themselves, especially for those who can utilize telemedicine and remote patient monitoring to their advantage, in order to enjoy more flexible and convenient access to care, which in turn will help them to live healthier lives [110–112].”

“The genetic and epigenetic regulation of the altered pathways in a cell is one of the main topics in pharmacogenomics and consists of understanding how a mutation in the DNA impacts the transcriptome and the proteome downstream [70–72].”

“There are multiple applications of this methodology in the field of proteomics [95], genomics [96], clinical prognosis [97], cancer treatment [98], aging [99], analysis of defective pathways [100,101], and drug repositioning [102].”

“Moreover, there are various open software applications that can track cell phone locations and the names of social media users through MAC and GPS big data, which might be used for malicious reasons [132,133].”

“As we have stated in the conceptualization of big data section, there could be infinite models that solve a biomedical problem due to the huge uncertainty space [93].”

“There are multiple applications of this methodology in the field of proteomics [95], genomics [96], clinical prognosis [97], cancer treatment [98], aging [99], analysis of defective pathways [100,101], and drug repositioning [102].”

“Big data in the health care department has the power to discover new medications [122–124].”

“There are multiple applications of this methodology in the field of proteomics [95], genomics [96], clinical prognosis [97], cancer treatment [98], aging [99], analysis of defective pathways [100,101], and drug repositioning [102].”

“Distinct dimensions are included in the definition of “big data”, namely, volume, velocity, variety, value, variability, visualization, virality, and veracity, which describes the massive volume of structured, semi-structured, and unstructured data (Figure 1) [11–14].”

“These advances not only improve diagnostic accuracy, but also open new avenues for targeted drug development and precision medicine [45].”