In this article, Lauris Kemp explores what is going on with bioinformatics patent filings and the application of AI to solve the knotty problem of protein structures.
Biological data is renowned for being complex. Take Diseases. Diseases are often not the result of one mutation in one gene but rather a pattern of mutations across various genes. Detecting cancer in slide or radiology images depends on a myriad of features in these images. Often in these fields, researchers and diagnosticians are looking to find patterns in biological data which are too complex for our human brains. Enter bioinformatics, the field of research in which biological data meets maths and computation. This field is currently enjoying a boost as AI tools – highly suited to identifying incredibly complex patterns – become more readily available.
Unsurprisingly, we are in the midst of a surge in patent applications in bioinformatics at patent offices around the world. This includes “classical” bioinformatics, where the maths is derived by humans, and AI bioinformatics where the maths is inferred or developed by AI. The graph below shows this surge, which includes the related disciplines of cheminformatics (computational chemistry, e.g. software for identifying transition points in chemical reactions) and health informatics (which is more device-related, e.g. software and devices for patient monitoring).
Source: Espacenet
*Includes up until end of 2023 only due to 18 mth delay between filing and publication for patents
So what are in the applications in this surge? What are biotech and pharma companies protecting?
All sorts is the answer, including protein structure determination; ligand building for drug design; prognosis or diagnosis based on microbiome patterns or DNA patterns; estimation of drug-like properties for biologics; detection of DNA modifications in NGS; normalisation of microbiome sequencing; prediction of what a cancer cell displays on its surface to inform cancer cell vaccines; in silico brains (like children, you aren’t supposed to have favourite patent applications but this was one of ours).
The companies filing these applications have different business models: some are service providers, e.g. drug hunter companies providing platform tech. Others are large pharma or biotech and they are protecting their digital innovation as well as their main commercial products. For example, drug companies are protecting their drug discovery platforms, and sequencing companies are protecting clever software too. There is also interestingly a middle-ground for pharma: companies which not only have drug discovery pipelines but also sell their AI tech (e.g. Schrӧdinger and Insilico Medicine). This makes sense given the expertise they have built and the revenue they generate though tech sales can be put to good use fuelling their own clinical pipelines.
Drug discovery is a hard and expensive game, but the new pharma companies, built around using AI, are starting to make headway. Insilico Medicine recently announced positive early clinical trials for rentosertib, a drug designed using generative AI which binds to a target also discovered by AI.
In terms of IP protection for all this brilliant tech, the EPO is very friendly to clever maths/computing/bio applications with experienced examiners (who, like us, love this technology). EPO case law is still developing but oppositions are building, particularly in areas such as sequencing technology and cancer vaccines.
If you are interested in this topic, we have an upcoming series of webinars given by the bioinformatics and digital healthcare experts in our AI team. The first of these will discuss not only how to protect your innovations in this area but why commercially it is very useful to do so. Sign up for the webinar here.
This is for general information only and does not constitute legal advice. Should you require advice on this or any other topic then please contact hlk@hlk-ip.com or your usual HLK advisor.
Stay connected with HLK
Keep up-to-date with the latest IP insights and updates as well as upcoming webinars and seminars via HLK’s LinkedIn page, or simply subscribe to our updates.