Agent-based modeling: a systematic assessment of use cases and requirements for enhancing pharmaceutical research and development productivity

Abstract

A crisis continues to brew within the pharmaceutical research and development (R&D) enterprise: productivity continues declining as costs rise, despite ongoing, often dramatic scientific and technical advances. To reverse this trend, we offer various suggestions for both the expansion and broader adoption of modeling and simulation (M&S) methods. We suggest strategies and scenarios intended to enable new M&S use cases that directly engage R&D knowledge generation and build actionable mechanistic insight, thereby opening the door to enhanced productivity. What M&S requirements must be satisfied to access and open the door, and begin reversing the productivity decline? Can current methods and tools fulfill the requirements, or are new methods necessary? We draw on the relevant, recent literature to provide and explore answers. In so doing, we identify essential, key roles for agent-based and other methods. We assemble a list of requirements necessary for M&S to meet the diverse needs distilled from a collection of research, review, and opinion articles. We argue that to realize its full potential, M&S should be actualized within a larger information technology framework--a dynamic knowledge repository--wherein models of various types execute, evolve, and increase in accuracy over time. We offer some details of the issues that must be addressed for such a repository to accrue the capabilities needed to reverse the productivity decline.

FIGURE 1

A particular analog use case can be characterized by an approximate location on each of the four lower spectra. Spectrum location along with specifics about how and for what the simulation model will be used within the larger R&D context, determine which M&S methods are most appropriate for a given use case. Within a pharmaceutical R&D context, a use case includes details of the specific, biology-focused wet-lab experiment that analog execution is intended to model in some way. Depending on use case location on the spectra, an analog can be located anywhere along a spectrum of software devices (models) ranging from synthetic (all components designed to be plugged together and are thus replaceable) to purely inductive models. System Information includes current conceptual knowledge about the mechanisms on which wet-lab experiments focused. As the R&D process advances, evidence will shrink the space of possible mechanisms. The result will be a set of plausible analog mechanisms supported by validation evidence. Later, that set too will shrink. The result will be a smaller set of likely mechanisms (those that have survived several falsification experiments). An R&D project's product can be successful without being able to designate key mechanisms as either actual or likely. Actual mechanisms are typically known for engineered systems, but are typically lacking in therapeutics. Grounding is discussed in Box 2; additional information is provided as Supporting Information. Conditions on the far right of the bottom four spectra are supportive of models (typically, continuous equations) that rely exclusively on absolute grounding. Hunt at al. make the case that when left of center on one or more of the bottom three spectra, models should rely more on relational grounding. When on the far left, early stage, purely qualitative M&S is still useful and productive: it facilitates goal-oriented research efforts by clarifying (unifying) current thinking about referent phenomena. Such models would typically be coarse grain and use relational grounding. Spectra colors were selected arbitrarily.