The antibody agreement

CARLSBAD, Calif.—Today Thermo Fisher Scientific, the world leader in serving science, announced it has signed an agreement with BenchSci to utilize its proprietary machine learning platform to mine antibody data published in peer-reviewed scientific journals. The data and associated application information will be displayed on product-specific webpages to help scientists make informed decisions about the optimal antibodies to use in their experiments.

According to BenchSci’s website, “As a team of former bench scientists, we experienced challenges finding commercial antibodies. So we spent two years building machine learning software to extract antibody usage data in the form of published figures, decoding millions of papers and making the data easily discoverable for scientists. The result: BenchSci.

“For biomedical researchers who are starting experiments, BenchSci is a reagent intelligence platform that transforms published data into experiment-specific recommendations to reduce time, money and uncertainty in planning materials and methods. Unlike PubMed, Google Scholar, reagent directories and vendors, BenchSci uses machine learning to decode open- and closed-access data and present published figures with actionable insights.”

Prior to the availability of the platform on Thermo Fisher’s site, researchers needed to rely on scientific search engines, sift through numerous papers, and tab back and forth between the published studies and product websites. The process could take hours or even days, but is now significantly reduced to minutes by extracting key information and figures from both open- and closed-access papers.

An image gallery on Thermo Fisher’s relevant antibody product pages will incorporate data generated by BenchSci’s platform so that visitors on the website can review both internal product development data and figures from peer-reviewed journals in one location. Additional published figures covering more antibodies will be added over time.

Poor antibody specificity or application performance can significantly hinder the ability to obtain good results, which can cause critical research delays. Choosing wrong or underperforming antibodies result in a lack of reproducibility, wasted time and wasted resources. Researchers need antibodies that bind to the right target and work in their applications every time.

“Data is absolutely critical to ensuring that scientists can make high confidence decisions about what antibody reagent is likely to be most appropriate for their application of interest,” said Dara Wright, vice president and general manager of protein and cell analysis, Thermo Fisher Scientific. “Far too much time and money is wasted on the use of antibodies which don't meet expectations. This new capability, coupled with our internal validation initiatives, is a meaningful step forward.”