Why Life Sciences?
Quantum machine learning is especially fit to address classical computing limitations across many life science areas such as drug discovery, clinical research, and diagnostics.
Drug Discovery
A long, expensive process limited by high complexity.
Contributing Factors: High dimensionality, Accuracy vs speed trade-off, High cost of computational resources
Tasks: Binding affinity prediction, RNA structure prediction, Protein docking, Target validation
Clinical Trials
A costly, high-failure industry due to suboptimal trial design.
Contributing Factors: High dimensionality, Limited interpretability, High cost of computational resources
Tasks: Patient stratification, Biomarker selection, Cohort identification, Site selection
Diagnostics
Where high dimensionality is creating life-threatening delays.
In 2022, breast cancer caused over 670,000 deaths [6]
Early cancer diagnosis saves lives, cuts treatment costs [7]
Contributing Factors: Unstructured data, High complexity of data, Low scalability, Accuracy vs speed trade-off, High cost of computational resources
Tasks: Medical imaging, Personalized medicine, Accurate diagnostics
Our Research
Drug Discovery
Our own hybrid quantum-classical neural network for binding affinity prediction.
40% reduction in training times and costs
6% improvement in accuracy
Clinical Trials
Quantum-enhanced solution for optimizing patient stratification.
100x faster than classical algorithms
Mitigates biases in stratification
Diagnostics
Our own unsupervised method for detection of breast cancer in medical images.
10x faster than classical algorithms
Maintains accuracy of supervised methods
Sources
[1] Estimated Research and Development Investment Needed to Bring a New Medicine to Market, 2009-2018
[2] Fast to first-in-human: Getting new medicines to patients more quickly
[3] How Much Does a Day of Delay in a Clinical Trial Really Cost?
[4] Step 3: Clinical Research
[5] Why 90% of clinical drug development fails and how to improve it?
[6] Breast cancer fact sheet
[7] Early cancer diagnosis saves lives, cuts treatment costs