It acknowledged the existing systems and pushed work towards further improvement

that eventually helped the rapid translation of in vitro diagnostics and the positive

outcome (Kurani et al. 2017; Shakhnovich 2018).

9.6

Challenges and Future Prospects of Reverse Translational

Approach in Drug Discovery

The reverse translation is the technique of deep learning and large data mining,

which is helpful for generating data and evaluating the testingparameters for new

drug development within all probable therapeutic areas. The large data collation and

its availability may be a challenge at this time. The main challenge is the cost

associated with data collection through genome sequencing and to adequately

transform data to information to knowledge for researchers and clinicians.

Reverse translational approach is helpful in providing and collating the large

available data either in the form of a published literature or study and analysis of

patents and from the information available in the regulatory domain and clinical

registry. This may be helpful in getting requisite information from multiple sources

and compiling the required information with adoption of statistical measures. More-

over, the sophisticated algorithms along with the prediction of collated information

lead to the probability of providing an accurate result with the help of multiple

variances in treating and analysing a specific diseases or condition which is under

question for evaluation. For example, a hypothetical drug that undergoes preclinical

testing and experiments considering the potential of suitable candidate for pancreatic

cancer, however, due to failure in clinical trials might be an alternative for selection

of the said drug for treatment of brain tumour such as glioblastoma multiforme. This

in turn is effective for many biotechnology and pharmaceutical companies which can

utilise such data to reduce the cost and investment before initiating a new project for

drug discovery.

Additionally, various methods have been earlier discussed for reverse transla-

tional research, which includes but are not limited to the molecular medicine

approach. It is helpful in new drug development by understanding the mechanism

of the pathophysiology of the disease, which can be identified and targeted with an

expected outcome. The knowledge gained from the collected clinical data may be

applied to both development of biomarkers and drug discovery processes. Therefore,

shifting the conventional paradigm of drug screening from the existing rigorous

methods to preclinical and clinical experiments could be helpful in identifying the

successful targets and possible mechanisms to get the desired output. This should

allow better predictive capability and decision-making on the part of scientists and

managers in the drug discovery process.

For translational research, it is required to have more public–private partnerships,

essential for providing the extension of the precompetitive space among the acade-

mia, industry and government to identify priority research areas and additional

funding. This is required for the development of technologies such as artificial

intelligence, machine learning and change in business model.

9

Biomarker-Based Drug Discovery with Reverse Translational Approach

137