AI-driven drug discovery company Insilico Medicine Hong Kong Limited clinches an award at the HKB Technology Excellence Awards
It has been delivering breakthrough solutions to discover and develop innovative drugs for cancer, fibrosis, immunity, central nervous system diseases, and ageing-related diseases.
Insilico Medicine is a clinical-stage end-to-end artificial intelligence (AI)-driven drug discovery company, connecting biology, chemistry, and clinical trials analysis using next-generation AI systems. Its technological innovations clinched an award for the AI - Pharmaceuticals category at the Hong Kong Business Technology Excellence Awards 2022.
Since 2014, Insilico Medicine has been developing PandaOmics – Discovery and Prioritisation of Actionable Therapeutic Targets, one of the successful projects they have, which aims to address the biological aspects of AI-based drug discovery.
PandaOmics’s features come with facilitating systems biology research, focusing on the fundamentals of complex interactions within biological systems to identify disease signatures and actionable targets in a disease-relevant manner.
Through PandaOmics’s comprehensive analyses, not only can novel targets be identified, but established targets can also be prioritised in diseases of interest for further development.
Moreover, PandaOmics has been executing a comprehensive omics data analysis and interpretation workflow, involving omics sample search and selection, sample clustering, comprehensive pathway analyses that can convert a list of seemingly unrelated genes into a connected story using proprietary iPanda algorithm, and natural language-based analyses of publications and grants.
Utilising the workflow allows PandaOmics to propose a list of disease targets including novel targets that may not be unveiled by simple bioinformatics analyses on public databases. It can be customised with an extensive set of filters modulating a variety of parameters, including novelty or prior validation, to prioritise targets based on different target identification strategies and preferences.
The AI models dynamically assess disease targets based on a variety of measures, such as novelty, accessibility by small molecules and biologics, and safety and tissue expression specificity during the target identification process for the purpose of collectively generating hypotheses around their potential druggability profiles.
Aside from the flourishing performance of PandaOmics, Insilico Medicine prides itself on the authenticity of its comprehensive database which is curated specifically to solve target discovery-related problems.
The company also adopted a “time machine” approach that assesses the ability of the AI models to prioritise promising novel targets. This approach involves training the AI models to recognise patterns based on empirical data comparing initial target discovery during a defined time point to the level of pharmaceutical industry interest in a subsequent time period.
Also, the AI models are iteratively trained until the list of predicted targets significantly overlaps with actual “hot” targets in the industry. Otherwise, the AI algorithms are modified and retrained through another “time machine” cycle. This “time machine” cycle is a continuous process until the model reaches robustness.
Lastly, another unique factor about PandaOmics is that it has a dynamic calculation that can calculate target scores in real-time based on the datasets of choice
Insilico has triumphantly created unique approaches to identifying potential therapeutic targets for specified diseases. With its unique software features, clients enjoy the easier analysis of data and target identification which are breakthrough innovations crucial in the field of drug discovery.
The Hong Kong Business Technology Excellence Awards is presented by Hong Kong Business Magazine. To view the full list of winners, click here. If you want to join the 2023 awards programme and be acclaimed for your company's outstanding contributions in pursuit of technological innovation, please contact Julie Anne Nuñez at firstname.lastname@example.org.