AI-primarily based drug interaction prediction technologies analyzes the interaction among Paxlovid components
Mar 16 2023
KAIST (President Kwang Hyung Lee) announced on the 16th that an sophisticated AI-primarily based drug interaction prediction technologies created by the Distinguished Professor Sang Yup Lee’s investigation group in the Division of Biochemical Engineering that analyzed the interaction among the PaxlovidTM components that are employed as COVID-19 remedy and other prescription drugs was published as a thesis. This paper was published in the on the net edition of 「Proceedings of the National Academy of Sciences of America」(PNAS), an internationally renowned academic journal, on the 13th of March.
In this study, the investigation group created DeepDDI2, an sophisticated version of DeepDDI, an AI-primarily based drug interaction prediction model they created in 2018. DeepDDI2 is in a position to compute for and procedure a total of 113 drug-drug interaction (DDI) sorts, additional than the 86 DDI sorts covered by the current DeepDDI.
The investigation group employed DeepDDI2 to predict attainable interactions among the components (ritonavir, nirmatrelvir) of Paxlovid, a COVID-19 remedy, and other prescription drugs. The investigation group mentioned that although amongst COVID-19 sufferers, higher-threat sufferers with chronic ailments such as higher blood stress and diabetes are probably to be taking other drugs, drug-drug interactions and adverse drug reactions for Paxlovid have not been sufficiently analyzed, however. This study was pursued in light of seeing how continued usage of the drug might lead to severe and undesirable complications.
The investigation group employed DeepDDI2 to predict how Paxrovid’s elements, ritonavir and nirmatrelvir, would interact with two,248 prescription drugs. As a outcome of the prediction, ritonavir was predicted to interact with 1,403 prescription drugs and nirmatrelvir with 673 drugs.
Making use of the prediction outcomes, the investigation group proposed option drugs with the similar mechanism but low drug interaction possible for prescription drugs with higher adverse drug events (ADEs). Accordingly, 124 option drugs that could lessen the attainable adverse DDI with ritonavir and 239 option drugs for nirmatrelvir have been identified.
By means of this investigation achievement, it became attainable to use an deep understanding technologies to accurately predict drug-drug interactions (DDIs), and this is anticipated to play an crucial function in the digital healthcare, precision medicine and pharmaceutical industries by giving beneficial information and facts in the procedure of creating new drugs and creating prescriptions.
Distinguished Professor Sang Yup Lee mentioned, “The outcomes of this study are meaningful at occasions like when we would have to resort to making use of drugs that are created in a hurry in the face of an urgent circumstances like the COVID-19 pandemic, that it is now attainable to determine and take needed actions against adverse drug reactions brought on by drug-drug interactions really speedily.”
This investigation was carried out with the assistance of the KAIST New-Deal Project for COVID-19 Science and Technologies and the Bio·Medical Technologies Improvement Project supported by the Ministry of Science and ICT.
KAIST (Korea Sophisticated Institute of Science and Technologies)