Data testing over animal testing

Is animal testing still necessary in this day and age? According to some industry experts, they may not be so prevalent in the near future. During Elsevier’s webinar series “Successful alternatives to animal testing,” different methods to replace or at least diminish the use of animal testing were discussed. One of those alternatives is the use of artificial intelligence and data from past animal studies, an approach that was presented by Dr. Weida Tong.

“My field is, by default, trying to replace animal testing,” Weida explains. Since achieving his PhD in polymer chemistry from Shangai, Dr. Weida has become Director of the?Division of Bioinformatics and Biostatistics?at the?National Center for Toxicological Research (NCTR)?— the only dedicated research facility for the US Food & Drug Administration (FDA). With over 300 peer-reviewed papers and book chapters, Weida has become an industry expert in data-driven alternatives to animal testing — making him the perfect guest for Elsevier’s?Successful Alternatives to Animal Testing?webinar series.

In 1994, a new director at NCTR noticed that all these toxicology studies that were done would disappear into a mass of literature, essentially going to waste. In 1996, Weida was brought in to create a toxicological knowledge base. This was so we would be able to capture all this generated knowledge and then use it to guide future research. One disadvantage to Weida’s tasks was the power of the machines as well as the amount of data available. “But now the machines are powerful enough to deal with all these tremendous resources of data, such as?PharmaPendium. We are now getting unprecedented results and these results are being evaluated and considered by regulatory agencies.”

Examples that were given of applications of such technology included the?Liver Toxicity Knowledge Base (LTKB). Liver damage is a top reason why a drug is withdrawn from the market. With the high cost of bringing a drug to market, about $2.6 billion, you really want to flag these drugs and withdraw them at an early stage. The model aims at asking the right questions during the review process to help determine if a drug is safe or not. A key success for Weida and his team came when they proved they could?derive new animal results from existing animal studies. This framework, which they call Tox-GAN, resulted in over 87% agreement between their results and the real data.

These results have started to blow a wind of change. With the?FDA Modernization Act, Congress asked the FDA to study and establish alternative methodologies as part of the regulatory process. For Weida: “All these efforts just make sense. Conventional animal studies are expensive, time-consuming, labour-intensive, and there are also ethical concerns. Above all, these tests are not fail-safe for human safety. But with the FDA Modernization Act, the train has now left the station, and over the next few years, we will see tremendous progress.”

While animal testing may not be completely obsolete yet, there are effective methods out there to reduce the need for it. The machines are powerful enough and the data is available. The word just needs to get out there. If you would like to know more about how Weida and how his work and artificial intelligence can reduce animal testing, head over to the Elsevier blog post.