dataset is challenging and needs to be developed well for novel anti-TB drug
discovery.
The traditional drug discovery and development process takes up to 10–15 years.
It involves identification of right protein target in a disease, designing new inhibitors,
optimizing the activity of the molecule and further preclinical and toxicity analyses.
The enormous amount of scientific data is being reported, and analysis of this “big
data” is one of the hurdles in the target identification process. In this data-driven
process, the application of artificial intelligence (AI) plays a pivotal role nowadays.
AI and machine learning have a crucial part in the first analysis of the massive
scientific data to form essential new knowledge for the drug development process
[166]. This digital electronic field is emerging and has an immense potential toward
cost, speed, and efficiency in the drug discovery program. In drug discovery and
clinical diagnostics, AI can outperform humans on certain tasks, and machine
learning toward identifying the spot patterns and its relationship within big data
provide guidance in this aspect, which is beyond our reach. There are different case
studies of AI in the area of target identification and validation as well as in medicinal
and synthetic chemistry [167–169]. These new data-driven technologies are proving
to be tremendously promising when it reveals new mechanistic insights to disease,
thereby helping to identify promising targets. In the context of computer-aided drug
design, AI and machine learning techniques can process broader and varied chemical
space in a much faster manner to identify the potential molecules from the bigger
dataset for disease cure [170].
7 Conclusions
Current anti-TB drug regimens require better understanding of the drug–target
relationships in order to decipher the structure–function relationships and its
molecular mechanism of action with the drugs. Review of the literature surveys and
studies on the basis of bioinformatics, structure-based TB drug discovery,
computer-aided drug design, and drug repurposing study was promising for TB
diagnostics, therapeutics, and molecular mechanism of action toward MDR-TB and
XDR-TB. The proper selection of druggable TB target and its molecular mechanism of inhibition are essential to understand the TB drug resistance at the fundamental level in which the structure-based anti-TB drug design will play a pivotal
role. The present crisis toward antibiotic resistance and the discovery of bedaquiline, delamanid, and recently eravacycline drugs has promised a sigh of relief for
TB patients.
Drug repurposing or repositioning is an alternative step in the anti-TB drug
discovery program addressing the drug resistance. The synergistic effect of the
repurposed/combination drugs linezolid, clofazimine, benzoxaboroles, fluoroquinolones, trimethoprim, thioridazine, sulfamethoxazole, sulfadiazine, minocycline, amoxicillin/clavulanic acid, and carbapenems like Meropenem along with the
new FDA-approved drugs bedaquiline, delamanid, and eravacycline can be
336
A. C. Pushkaran et al.
discovery.
The traditional drug discovery and development process takes up to 10–15 years.
It involves identification of right protein target in a disease, designing new inhibitors,
optimizing the activity of the molecule and further preclinical and toxicity analyses.
The enormous amount of scientific data is being reported, and analysis of this “big
data” is one of the hurdles in the target identification process. In this data-driven
process, the application of artificial intelligence (AI) plays a pivotal role nowadays.
AI and machine learning have a crucial part in the first analysis of the massive
scientific data to form essential new knowledge for the drug development process
[166]. This digital electronic field is emerging and has an immense potential toward
cost, speed, and efficiency in the drug discovery program. In drug discovery and
clinical diagnostics, AI can outperform humans on certain tasks, and machine
learning toward identifying the spot patterns and its relationship within big data
provide guidance in this aspect, which is beyond our reach. There are different case
studies of AI in the area of target identification and validation as well as in medicinal
and synthetic chemistry [167–169]. These new data-driven technologies are proving
to be tremendously promising when it reveals new mechanistic insights to disease,
thereby helping to identify promising targets. In the context of computer-aided drug
design, AI and machine learning techniques can process broader and varied chemical
space in a much faster manner to identify the potential molecules from the bigger
dataset for disease cure [170].
7 Conclusions
Current anti-TB drug regimens require better understanding of the drug–target
relationships in order to decipher the structure–function relationships and its
molecular mechanism of action with the drugs. Review of the literature surveys and
studies on the basis of bioinformatics, structure-based TB drug discovery,
computer-aided drug design, and drug repurposing study was promising for TB
diagnostics, therapeutics, and molecular mechanism of action toward MDR-TB and
XDR-TB. The proper selection of druggable TB target and its molecular mechanism of inhibition are essential to understand the TB drug resistance at the fundamental level in which the structure-based anti-TB drug design will play a pivotal
role. The present crisis toward antibiotic resistance and the discovery of bedaquiline, delamanid, and recently eravacycline drugs has promised a sigh of relief for
TB patients.
Drug repurposing or repositioning is an alternative step in the anti-TB drug
discovery program addressing the drug resistance. The synergistic effect of the
repurposed/combination drugs linezolid, clofazimine, benzoxaboroles, fluoroquinolones, trimethoprim, thioridazine, sulfamethoxazole, sulfadiazine, minocycline, amoxicillin/clavulanic acid, and carbapenems like Meropenem along with the
new FDA-approved drugs bedaquiline, delamanid, and eravacycline can be
336
A. C. Pushkaran et al.