Unblocking Blockbusters: Using Boolean Text-Mining to Optimise Clinical Trial Design and Timeline for Novel Anticancer Drugs

Two problems now threaten the future of anticancer drug development: (i) the information explosion has made research into new target-specific drugs more duplication-prone, and hence less cost-efficient; and (ii) high-throughput genomic technologies have failed to deliver the anticipated early windfall of novel first-in-class drugs. Here it is argued that the resulting crisis of blockbuster drug development may be remedied in part by innovative exploitation of informatic power. Using scenarios relating to oncology, it is shown that rapid data-mining of the scientific literature can refine therapeutic hypotheses and thus reduce empirical reliance on preclinical model development and early-phase clinical trials. Moreover, as personalised medicine evolves, this approach may inform biomarker-guided phase III trial strategies for noncytotoxic (antimetastatic) drugs that prolong patient survival without necessarily inducing tumor shrinkage. Though not replacing conventional gold standards, these findings suggest that this computational research approach could reduce costly 'blue skies' R&D investment and time to market for new biological drugs, thereby helping to reverse unsustainable drug price inflation.