Stochastic Combinatorial Optimization Approach to Biopharmaceutical Portfolio Management Edmund D. George and Suzanne S. Farid* The AdVanced Centre for Biochemical Engineering, Department of Biochemical Engineering, UniVersity College London, Torrington Place, London WC1E 7JE, U.K. Key strategic decisions in biopharmaceutical portfolio management include drug selection, activity scheduling, and third party involvement. Optimizing strategies is complicated by uncertainty, dependency relationships between decisions, and multiple objectives that may conflict. This paper presents the development of a stochastic combinatorial multiobjective optimization framework designed to address these issues. The framework simulates portfolio management strategies while harnessing Bayesian networks and evolutionary computation concertedly to characterize the probabilistic structure of superior decisions and evolve strategies to multiobjective optimality. This formulation is applied to a case study entailing a portfolio of five therapeutic antibody projects. Optimization was driven by two objectives that conflicted here: maximizing profitability and maximizing the probability of being profitable. Initial analysis of competing strategies along the Pareto optimal front indicated that strategies with clear differences in comprising decisions can compete with similar reward-risk profiles. Hence optimization yielded results that were not intuitive but instead suggested that flexibility between strategies can exist in such large-scale problems. A cluster analysis was used to identify the prevalence of broad and superior building blocks along the Pareto front. In-house development of drugs generally emerged as a preferred constituent of superior strategies which suggested a drive toward minimizing contracting fees, premiums, royalty charges, and losses in sales revenue to third parties; no budgetary constraints were imposed in this case study. It appeared that strategies for scheduling activities had the most overarching impact on performance. Strategies for portfolio structure appeared to have the greatest degree of flexibility relative to other strategic components. 1. Introduction Biopharmaceutical drug development is expensive, lengthy, risky, and complex. The literature has seen published figures in excess of $800 million for developing a single drug, 1,2 with 6-10 years as a typical development time. 3-6 Developmental uncertainties complicate the development process by introducing the possibility that it may be necessary to terminate development of a drug before a return can ever be realized. Market-related uncertainties introduce the risk that a marketed product may not meet the revenue expectations of the developer. Hence, a major and ubiquitous problem confronting biopharmaceutical drug developers is how and when to best make and implement critical business decisions so that important rewards such as profitability are optimized. Yet more expensive, risky, and complex is the development of a portfolio of drug candidates. Within a company’s pipeline, valuing one drug at a time is not sufficient and drug developers must consider the entire portfolio under technological and market uncertainties and resource constraints. 7 Here the developer must also make decisions to best construct the portfolio to optimize the management of resources and reward related trade-offs that each drug develop- ment project may introduce. Decisions made on the portfolio will include deciding the number of comprising projects subject to those that are most promising given resource constraints. Also included is the scheduling of critical development activities subject to a prioritized order of development based on considerations such as the identification of the most promising projects and accounting for strategic windows of opportunity in targeted drug markets. Portfolio selection problems pertaining to drug devel- opment have been addressed in the literature and cover a variety of methodological features, technical problems, and scenarios. For example, see Subramanian et al., 8,9 Blau et al., 10,11 Rogers et al., 12 and Jain and Grossmann. 13 In addition to decisions made on portfolio structure, drug developers must also address acquisition of or access to infrastructure for capacity-related decisions in drug development and manufacturing endeavors. These will include important strategic decisions such as whether to integrate activities within the company, to outsource them to a contract researcher (CRO) or manufacturer (CMO), or to partner with a company that has complementary developmental, manufacturing, and marketing resources. For example, strategic outsourcing to a contractor has become a vital component of the research and development process 14 and plays an increasingly important role in the operations of established and emerging pharmaceutical com- panies. 15 There are contributions that address the issue of capacity planning in the pharmaceutical industry using optimi- zation-based approaches of which the majority pertains to drug developers who have or plan to have integrated in-house development and manufacturing infrastructures. There are some who develop frameworks for wider settings which consider third party developers and manufacturers. These include Rogers and Maranas, 12 Oh and Karimi, 16 and Rajapakse et al. 17,18 Approaches have been reported for the development of frameworks that incorporate both the problems of portfolio management and manufacturing capacity planning simulta- neously, representing an important advancement. These present more challenging and realistic large-scale optimization problems that offer vast extensions to the lines of inquiry for either of the two problems in isolation. Such approaches include those by Levis and Papageorgiou, 19 Maravelias and Grossman, 20 and Papageorgiou et al. 21 * To whom correspondence should be addressed. Tel.: +44 (0)20 7679 4415. Fax: +44 (0)20 7916 3943. E-mail: s.farid@ucl.ac.uk. Ind. Eng. Chem. Res. 2008, 47, 8762–8774 8762 10.1021/ie8003144 CCC: $40.75  2008 American Chemical Society Published on Web 10/28/2008