Use of big data in drug development for precision medicine: an update

Abstract

Introduction: Big-data-driven drug development resources and methodologies have been evolving with ever-expanding data from large-scale biological experiments, clinical trials, and medical records from participants in data collection initiatives. The enrichment of biological-and clinical-context-specific large-scale data has enabled computational inference more relevant to real-world biomedical research, particularly identification of therapeutic targets and drugs for specific diseases and clinical scenarios. Areas covered: Here we overview recent progresses made in the fields: new big-data-driven approach to therapeutic target discovery, candidate drug prioritization, inference of clinical toxicity, and machine-learning methods in drug discovery. Expert opinion: In the near future, much larger volumes and complex datasets for precision medicine will be generated, e.g., individual and longitudinal multi-omic, and direct-to-consumer datasets. Closer collaborations between experts with different backgrounds would also be required to better translate analytic results into prognosis and treatment in the clinical practice. Meanwhile, cloud computing with protected patient privacy would become more routine analytic practice to fill the gaps within data integration along with the advent of big-data. To conclude, integration of multitudes of data generated for each individual along with techniques tailored for big-data analytics may eventually enable us to achieve precision medicine.

Electronic Medical Records and Machine Learning in Approaches to Drug Development

“…In 2016, laboratories were still physically mailing or faxing genomic reports in PDFs, which is a format that is extremely difficult for machines to read and interpret [12]. This clinical hurdle aside, in biomedical research this genomic inclusion in EHRs shows potential in secondary use as raw data from which to draw medically meaningful results [2,12,13]. Assuming that the EMR has adequate phenomic and genomic data on an individual, algorithms can translate raw data in EMRs to phenotype data, which in turn can be associated with the genomic data.…”

“…Successful examples have shown that EMR mining for potential recruitment are more cost efficient and less time consuming than traditional methods [35,36]. As a quantitative example, a study done in the US studied 31 EHR-driven analysis on drug-to-genome interactions and concluded that EHRs helped decrease the trial cost by 72% per subject and reduced the duration of the studies [13].…”

Precision Medicine in Interventional Cardiology

“…The beauty of in silico trials is that they are able to evaluate positive effects and drug toxicity precluding animal testing and reducing cost and time. 8 VPH models can incorporate numerous patient-specific variables, such as lifestyle, medical history, physical examination, diagnostic tests and genetics to make reliable predictions. 2 VPH might be used to predict the risk of developing certain conditions and determine which treatment should be used and when it should be started to prevent diseases on an individual level.…”

Genome-wide investigation of gene-cancer associations for the prediction of novel therapeutic targets in oncology

“…A landmark study has highlighted the value of genetic evidence linking a target and disease for drug discovery (3), estimating that selecting targets supported by genetic data could double the success rate in the clinical development pipeline. Experts routinely consult large biomedical and genomic data resources (4) to guide target identification and validation. Examples for the field of oncology include The Cancer Genome Atlas (TCGA) (5) or the Cancer Dependency Map (DepMap) (6).…”