Few weeks ago, the Hong Kong–based company Insilico Medicine announced the beginning of a phase 1 clinical trial concerning a potential therapy for idiopathic pulmonary fibrosis. The event might have gone unnoticed but the way to find this drug was exceptional: it was designed “from scratch” by a combination of several artificial intelligence algorithms. The whole process took only 18 months for less than 3 million dollars, a small fraction of the classical cost in drug development.

The use of algorithms is obvioulsy not new in the selection of drug candidates and many ways to do so exist today, as explained in the review of Malathi et al. (2018). As in all applications of AI, the quality of the results depends strongly on the quality and veracity of data used to feed it. This quality is also important to improve the interpretability of IA results [Bertossi et al. (2020)]. It is know that many results in the medical literature and research papers are based on 2D in vitro assays and do not represent the true behavior of compounds in a real human body. This is precisely why we have been developing BIOMIMESYS® technology.

BIOMIMESYS® better correlation with in vivo results
BIOMIMESYS®-based in vitro results better correlate with in vivo results. For more information, see the presentation webinar.

As you see, the in silico approach based on AI might provide a complementary technology to 3D in vitro models based on BIOMIMESYS® because both aim at dramatically decreasing the time and cost of drug development. The benefit would lie in the identification of new successful drug candidates, against complex diseases in particular.

If you work in the domain of in silico drug development, do not hesitate to contact us. Together we could: (i) find or create more relevant 3D in vitro assays to feed your algorithms with high quality data, (ii) build 3D in vitro assays to test your candidate drugs “as in a real body”.


Bertossi, L., Geerts, F., 2020. Data Quality and Explainable AI. J. Data Inf. Qual. 12, 11:1-11:9. https://doi.org/10.1145/3386687

Malathi, K., Ramaiah, S., 2018. Bioinformatics approaches for new drug discovery: a review. Biotechnol. Genet. Eng. Rev. 34, 243–260. https://doi.org/10.1080/02648725.2018.1502984

Grégory MAUBON

Grégory MAUBON is Chief Data Officer and digital coordinator at HCS Pharma, a biotech startup focused in high content screening and complex diseases. He manages IT missions and leads digital usages linked to company needs. He is also a Augmented Reality Evangelist (presenter and lecturer) since 2008, where he created www.augmented-reality.fr and founded in 2010 RA'pro (the augmented reality promotion association). He helped many companies (in several domains) to define precisely their augmented reality needs and supported them in the implementation.


Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.