الوصف: |
Introduction: Artificial intelligence (AI) is exhibiting tremendous potential to reduce the massive costs and long timescales of drug discovery. There are however important challenges currently limiting the impact and scope of AI models. Areas covered: Such models excel on benchmarks unlikely to anticipate their prospective performance, which inadvertently misguides their development. In practice, only a few are ever reported to have prospective value (e.g. by discovering potent and innovative drug leads for a therapeutic target). Here we discuss a range of data issues (bias, inconsistency, skewness, irrelevance, small size, high dimensionality), how they challenge AI models and which issue-specific mitigations have been effective. Next, we point out the challenges faced by uncertainty quantification techniques aimed at enhancing these AI models. We also discuss how conceptual errors, unrealistic benchmarks and performance misestimation can confound the evaluation of models and thus their development. Lastly, we explain how human bias, whether from AI experts or drug discovery experts, constitutes another challenge that can be alleviated with prospective studies. Expert opinion: We have discussed what can go wrong in practice with AI for drug discovery. We hope that this will help inform the decisions of editors, funders investors and researchers working in this area. |