A systematic approach to identify novel cancer drug targets using machine learning, inhibitor design and...

Area of Science:

• Oncology
• Genomics
• Drug Discovery

Background:

• Identifying effective anti-cancer drug targets is crucial for developing novel cancer therapies.
• Existing methods for drug target prioritization often lack integration of diverse genomic and systematic datasets.
• Specific challenges exist in identifying targets for challenging cancers like pancreatic and ovarian cancer.

Purpose of the Study:

• To develop and validate a novel, integrated approach for predicting and prioritizing anti-cancer drug targets.
• To identify drug targets specific to breast, pancreatic, and ovarian cancers.
• To select and validate targets amenable to inhibition by various therapeutic modalities.

Main Methods:

• A classifier was developed integrating multiple genomic and systematic datasets for target prioritization.
• Strategies for inhibiting prioritized anti-cancer drug targets were devised.
• Targets suitable for inhibition by small molecules, antibodies, and synthetic peptides were selected.
• In vitro validation using synthetic peptide and small molecule inhibitors against predicted targets was performed.

Main Results:

• The integrated approach successfully prioritized drug targets specific for breast, pancreatic, and ovarian cancers.
• A subset of prioritized targets amenable to inhibition by small molecules, antibodies, and synthetic peptides was identified.
• Synthetic peptide and small molecule inhibitors targeting the predicted drug targets exhibited strong anti-proliferative effects in vitro.
• The study validated the identified targets as promising for anti-cancer drug development.

Conclusions:

• The integrated computational approach effectively predicts and validates novel anti-cancer drug targets.
• The identified targets represent promising candidates for the development of new therapeutics against breast, pancreatic, and ovarian cancers.
• The validation using diverse inhibitors confirms the potential of these targets for clinical translation.