Drug Development in the Pharmaceutical Industry

A marketplace is a very complex entity, like a stock market, with its unpredictable dynamics, bubbles and crashes. Such emergent properties result from the behaviors and interactions of millions of investors. The best way to understand these interactions is to simulate the marketplace from the bottom up, simulating the behaviors of the players to capture the emergent properties.

A stock market is obviously not the only marketplace. For example, there are thousands of specialized marketplaces where companies in a particular industry can buy and sell goods and services from and to each other. Such marketplaces have been made easier to implement by the Internet, but many have failed. Reasons for failure include low liquidity (not enough participants willing to play), unsuitable trading and clearing mechanisms - different industries require different clearing mechanisms - or simply low or even negative reward to participants.

In order to be successful, a marketplace must be designed to attract and retain a sufficient number of participants while operating profitably. The offering, the way it is presented to the participants, and the clearing or allocation mechanism are levers that will influence the number and satisfaction of the participants. Icosystem uses a combination of agent-based modeling and evolutionary computation to design the marketplace that is the best adapted to a specific purpose.

In the pharmaceutical industry, the cost of developing new drugs has surged, forcing many companies to rethink their R&D operations. Part of the problem is the so-called "selfish-team syndrome," in which a group that is developing a particular drug makes biased decisions. For example, a team may try to save a project when it should be terminated because the team's reputation is tied to the drug's success or because the team members become attached to the project. Such counterproductive behavior can slow drug development and increases its cost.

Concerned by such issues, a major pharmaceutical company came up with a possible solution--creating a marketplace to subcontract some of the drug development in the early phases of human clinical trials. To explore that and other alternatives, Icosystem developed an agent-based model of the various players--the company's employees as well as potential contractors, including contract research organizations (companies that specialize in managing clinical trials), academics who do consulting work, and even experts at competing firms.

We found that because of the diversity of the players (their different motivations, aversions to risk, cost structures, and so on), the pharmaceutical company could not predictably coordinate all of the activity profitably in an open marketplace, even though it was theoretically possible. In collaboration with the company we then explored alternative options and ended up creating a completely new design for outsourcing drug development. The new design involved a different sort of marketplace, a network of participants, both internal and external, using incentives that encourage better decision making (such as a bonuses tied to the success of the entire portfolio of drug molecules). Through further modeling, we found that this solution could help our client more than double the risk-adjusted value of its portfolio of recently discovered molecules. Based on these results, the company has decided to test this new way of organizing early clinical development in the real world.