Deep Learning, Deeper Relief: Pipeline towards tailored analgesia for experimental animal models

Luisa Barleben¹Mareike Simon²Lisa Drees¹Christoph Jochum³Michela Di Virgilio²Frank Tacke¹Sonja Bröer⁴Jana Wolf²Marina Kolesnichenko^1*

• ¹Charité University Medicine Berlin, Berlin, Germany
• ²Max-Delbruck-Centrum fur Molekulare Medizin in der Helmholtz-Gemeinschaft, Buch, Germany
• ³Charite - Universitatsmedizin Berlin, Berlin, Germany
• ⁴Freie Universitat Berlin, Berlin, Germany

Effective pain management in animal models is crucial for maintaining ethical and scientific integrity. However, commonly used analgesics may affect immune responses and disturb signaling pathways, thereby potentially confounding experimental outcomes. In colitis models in mice, opioids and non-steroidal anti-inflammatory drugs have been shown to interfere with immune responses and the activation of the central regulator of inflammation, the transcription factor NF-κB. Here we propose a tailored pipeline for identifying and validating analgesics with minimal off-target effects. This approach combines protein-centered relation extraction using deep language models and distant supervision via Protein-centered association Extraction with Deep Language (PEDL+) together with an in vivo experimental validation with a NF-κB reporter mouse model that enables unambiguous visualization of direct NF-κB activity across different tissues. Our findings indicate that commonly used analgesics, such as tramadol and acetaminophen, not only interfere with immune cell recruitment and NF-κB activation but also skew the differentiation of epithelial stem cells into goblet cells, affecting epithelial functions even after short exposures. Conversely, analgesics selected by our PEDL+ based workflow such as piritramide demonstrated no significant interference with NF-κB signaling. To validate our findings in vivo we treated our NF-κB reporter mice with analgesics selected by our computational pipeline and demonstrated that amantadine had the least impact on inflammatory responses and NF-κB activation. We then predicted and identified signaling pathways that are impacted by amantadine treatment. In summary, our proposed pipeline facilitates a shift from one-size-fits-all analgesics to a precision medicine approach that considers the unique molecular interactions associated with each model.