Dr. Sarah Cavanaugh discusses biomedical research in her talk, "Homo sapiens: the ideal animal model"

Biology and preclinical medicine rely heavily upon research in animal models such as rodents, dogs, and chimps. But how translatable are the findings from these animal models to humans? And what alternative systems are being developed to provide more applicable results while reducing the number of research animals?
Image courtesy of PCRM


Last Thursday, PSPG invited Dr. Sarah Cavanaugh from the Physicians Committee for Responsible Medicine to discuss these issues. In her talk entitled, “Homo sapiens: the ideal animal model,” she emphasized that we are not particularly good at translating results from animal models into human patients. Data from the FDA says that 90% of drugs that perform well in animal studies fail when tested in clinical trials.  It may seem obvious, but it is important to point out that the biology of mice is not identical to human biology. Scientific publications have demonstrated important dissimilarities in regards to the pathology of inflammation, diabetes, cancer, Alzheimer’s, and heart disease.

All scientists understand that model systems have limitations, yet they have played an integral role in shaping our understanding of biology. But is it possible to avoid using experimental models entirely and just study human biology?

The ethics of studying biology in people are different from those of studying biology in animals.  The “do no harm” code of medical ethics dictates that we can’t perform experiments that have no conceivable benefit for the patient, so unnecessarily invasive procedures can not be undertaken just to obtain data. This limitation restricts the relative amount of information we can obtain about human biology as compared to animal biology.  Regardless, medical researchers do uncover important findings from human populations. Dr. Cavanaugh points out that studies of risk factors (both genetic and environmental) and biomarkers are important for understanding diseases, and non-invasive brain-imaging has increased our understanding of neurodegenerative diseases like Alzheimer’s.

Yet these are all correlative measures. They show that factor X correlates with a higher risk of a certain disease. But in order to develop effective therapies, we need to understand cause and effect relationships - in other words, the mechanism. To uncover mechanisms researchers need to be able to perturb the system and measure physiological changes or observe how a disease progresses. Performing these studies in humans is often hard, impossible, or unethical. For that reason, researchers turn to model systems in order to properly control experimental variables to understand biological mechanisms. We have learned a great deal about biology from animal models, but moving forward, can we develop models that better reflect human biology and pathology?

Using human post-mortem samples and stem cell lines is one way to avoid species differences between animals and humans, but studying isolated cells in culture does not reflect the complex systems-level biology of a living organism. To tackle this problem, researchers have started designing ways to model 3D human organs in vitro, such as the brain-on-a-chip system. Researchers also have envisioned using chips to model a functioning body using 10 interconnected tissues representing organs such as the heart, lungs, skin, kidneys, and liver.
Image from: http://nanoscience.ucf.edu/hickman/bodyonachip.php

Dr. Cavanaugh explained that toxicology is currently a field where chip-based screening shows promise. It makes sense that organs-on-a-chip technology could be useful for screening drug compounds before testing in animals. Chip-screening could filter out many molecules with toxic effects, thus reducing the number of compounds that are tested in animals before being investigated clinically.

A major counterpoint raised during the discussion was whether replacing animal models with human organs on a chip was simply replacing one imperfect, contrived model with another. Every model has limitations, so outside of directly testing therapeutics in humans, it is unlikely that we will be able to create a system that perfectly reflects the biological response in patients. The question then becomes, which models are more accurate? While ample data shows the limitations of animal models, very little is available showing that alternatives to animal-free models perform better than existing animal models. Dr Cavanaugh argues, however, that there is an opportunity to develop these models instead of continuing to pursue research in flawed animal models. “I don’t advocate that we end all animal research right now, rather that we invest in finding alternatives to replace the use of animals with technologies that are more relevant to human biology.”

This topic can ignite a passionate debate within the medical research community. Animal models are the status quo in research, and they are the gatekeepers in bench-to-bedside translation of scientific discoveries into therapeutics. In the absence of any shift in ethical standards for research, replacing animal models with alternatives will require mountains of strong data demonstrating better predictive performance. The incentives exist, though. Drug companies spend roughly $2.6 billion to gain market approval for a new prescription drug. Taking a drug into human trials and watching it fail is a huge waste of money. If researchers could develop new models for testing drugs that were more reliable than animal models at predicting efficacy in humans, it’s safe to say that Big Pharma would be interested. Very interested.


-Mike Allegrezza

"Wistar rat" by Janet Stephens via Wikimedia Commons