Data-Driven Discovery Of Innate Immunomodulators Via Machine Learning-Guided High Throughput Screening

SUMMARY

Novel machine learning-enable platform to guide in vitro experimental screening and discovery of small molecule immunomodulators to improve immune responses

The unmet need: Platform to resolve unregulated immune potentiator enhancement and suppression of inflammatory and stimulatory responses

• The innate immune response is vital for the success of prophylactic vaccines and immunotherapies. Control of signaling in innate immune pathways can improve prophylactic vaccines by inhibiting unfavorable systemic inflammation and immunotherapies by enhancing immune stimulation.

• In vaccination, for example, helper molecules known as adjuvants are often required to stimulate innate pathways involved in antigen presentation and processing that are critical in invoking a productive adaptive immune response. Despite the necessity of such signaling events to maximize potency, excessive activation of signaling pathways by adjuvants can cause undesirable systemic inflammation, and limit tolerability and dosage in a clinical setting. Conversely in immunotherapy, it is often essential to have strong stimulation to improve the immunogenicity and mitigate suppression from a tumor micro-environment.

• Although these adjuvants can be potent activators of immune responses, a well-known limitation of current popular adjuvants is excessive and uncontrolled inflammation. This has motivated efforts to discover novel adjuvants with reduced inflammation profiles but it has proved challenging to develop novel pattern recognition receptor (PRR) agonists capable of specifically tuning the level of stimulation in inflammatory pathways without disrupting the desired stimulation along immune activation pathways.

• An alternative approach to regulating the innate immune response is through immunomodulators – molecules co-delivered with PRR agonists to reduce inflammation or otherwise modulate innate immune stimulation by enhancing or suppressing innate immune signaling pathways.

The proposed solution: Machine learning-enabled screening approach for efficient small molecule immunomodulators

• The faculty inventor, Aaron Esser-Kahn, developed a machine learning-enabled active learning pipeline to guide in vitro experimental screening and discovery of small molecule immunomodulators that improve immune responses by altering the signaling activity of innate immune responses stimulated by traditional pattern recognition receptor agonists.

• The machine learning-enabled screening approach presents an efficient immunomodulator discovery pipeline that has furnished a library of novel small molecules with a strong capacity to enhance or suppress innate immune signaling pathways to shape and improve prophylactic vaccination and immunotherapies.

FIGURE

Combination of high-throughput wet lab experimentation and data-driven computation in a closely coupled active learning loop in order to identify novel molecules with exceptional properties.

ADVANTAGES

ADVANTAGES

• Novel data-driven high throughput screening framework for small molecule immunomodulatory discovery

• Unprecedented immunomodulatory capacity- enhance and suppress immune signaling pathways with a greater magnitude

APPLICATIONS

• Drug discovery
• Vaccine Development
• Immunotherapy

PUBLICATIONS

• Chem. Sci., 2023,14, 12747-12766

April 2, 2024

Proof of concept

Patent Pending

Licensing,Co-development

Aaron Esser-Kahn