At the core of this initiative lies the lead compound, SBI-810, a second-generation drug candidate derived from meticulous medicinal chemistry optimization, reinforced by receptor signaling analyses and efficacy testing. These efforts leverage state-of-the-art cryo-electron microscopy structural insights alongside artificial intelligence algorithms, creating a feedback loop of molecular refinement intended to maximize therapeutic efficacy while enhancing safety profiles. This iterative approach exemplifies a sophisticated leap forward in drug design, promising a new class of pain therapeutics that avoid the pitfalls of addiction and severe side effects characteristic of opioid analgesics.

The pressing need for such innovation arises from staggering clinical statistics: each year, nearly 80% of 19 million Americans undergoing major surgeries endure postoperative pain, while over 25 million individuals suffer chronic pain worldwide. Despite the prevalence, current analgesic regimens are often insufficient or fraught with complications, notably opioid-based treatments which carry profound risks such as dependence, overdose, and myriad side effects. SBI-810 targets this unmet medical need by engaging neurotensin receptor 1 (NTR1), a G protein-coupled receptor implicated in pain signaling pathways, yet does so via an unprecedented molecular mechanism.

Unlike traditional receptor agonists that bind centrally to active sites, SBI-810 acts as a biased allosteric modulator (BAM) by attaching to a cryptic intracellular pocket within NTR1. This mode of binding selectively promotes β-arrestin-2 pathway activation while suppressing G-protein mediated signaling linked to pain propagation and deleterious physiological responses. The selective modulation offers potent analgesia without inducing hypotension or hypothermia, adverse effects that historically limited the clinical advancement of NTR1-targeting compounds. This molecular precision heralds a paradigm shift in receptor pharmacology, focusing on signal bias to uncouple therapeutic effects from side effects.

The foundational science underpinning SBI-810 builds on seminal work revealing the potent analgesic properties of neurotensin, the natural ligand for NTR1. Decades ago, neurotensin was found to surpass morphine in antinociceptive potency; however, its clinical utility was hindered by systemic side effects. Dr. Ru-Rong Ji articulates this challenge: harnessing neurotensin’s analgesic power safely required novel strategies. Using structural biology and drug design, the research team has designed compounds that selectively funnel receptor signaling into beneficial routes, overcoming this historical barrier.

Recent high-impact publications underpin the grant’s rationale. A 2025 study in Cell unveiled the multifaceted efficacy of SBI-810 across diverse rodent pain models, including postoperative, inflammatory, and neuropathic conditions. Notably, the compound modulated pain signaling in human sensory neurons, an essential translational milestone. Crucially, SBI-810 reduced opioid-induced side effects, which may enable combination therapies that enhance analgesia while mitigating opioid-related harm. Complementing this, another 2025 Nature publication elucidated the molecular architecture governing biased signaling by the parent molecule SBI-553, revealing how intracellular binding pockets redirect receptor-protein interactions. These insights lay the structural groundwork for precision drug design within the largest receptor family: G protein-coupled receptors (GPCRs).

GPCRs constitute the most extensive and versatile family of membrane receptors, orchestrating cellular responses to extracellular signals such as neurotransmitters, hormones, and environmental stimuli. Their ubiquitous role in physiology renders GPCRs prime pharmacological targets, with approximately one-third of all marketed drugs acting on these receptors. This new class of biased allosteric modulators introduces a transformative approach to modulating GPCR function, emphasizing specificity in downstream signaling cascades rather than wholesale receptor activation.

Dr. Lauren M. Slosky emphasizes the transformative potential of integrating detailed structural understanding with computational methodologies. This fusion facilitates rational drug design by predicting how structural changes in compounds translate to altered receptor behavior and clinical outcomes. Such an approach mitigates the inefficiencies and uncertainties inherent in traditional empirical drug discovery, increasing the probability of clinical success.

The grant’s structure is designed to expedite the transition from laboratory discovery to clinical application through a phased strategy. The initial two-year phase concentrates on refining lead molecules by optimizing efficacy and eliminating cardiac safety liabilities detected in preliminary evaluations. Preclinical validation will employ well-established rodent pain models, with careful incorporation of sex as a biological variable to ensure broad therapeutic applicability. Subsequent phases hinge on success milestones, culminating in Investigational New Drug (IND) applications and phase 1 human safety and pharmacokinetic trials.

Underlying this endeavor is a multidisciplinary consortium that synergizes medicinal chemistry, GPCR structural biology, neurobiology, and translational pharmacology. Besides Olson, Ji, and Slosky, the team includes notable scientists such as Lawrence S. Barak, PhD, William C. Wetsel, PhD, Changlu Liu, PhD, and Michael R. Jackson, PhD. This collaborative framework exemplifies the NIH HEAL Initiative’s mission to harness interdisciplinary expertise to combat opioid addiction and chronic pain through innovative therapeutics.

Steven H. Olson reflects on the broader implications of this work, highlighting the grant’s enabling role in transforming a promising preclinical molecule into a potential new medicine. The integration of chemistry, structural biology, and rigorous in vivo pharmacology across multiple institutions provides a robust platform to tackle one of medicine’s most daunting challenges: effective, non-addictive pain relief. This initiative not only aims to alleviate suffering for millions worldwide but also to set a blueprint for future GPCR-targeted drug discovery efforts.

The NIH HEAL Initiative, which funds this research, launched in 2018 with the goal of accelerating solutions to the opioid crisis, spanning prevention, treatment of addiction, and improved pain management strategies. By fostering bold, collaborative science projects such as this one, HEAL is catalyzing the development of innovative drugs designed to diminish reliance on opioids while addressing chronic and acute pain safely and effectively.

Sanford Burnham Prebys Medical Discovery Institute, now celebrating its 50th anniversary, continues to be at the forefront of biomedical research focused on fundamental human biology and translational science. The institute’s strength lies in its integrated centers of excellence across cancer, neuroscience, cardiovascular, metabolic, and liver diseases, complemented by cutting-edge capabilities in data science, artificial intelligence, and drug discovery. This environment fuels transformative discoveries with the potential to revolutionize health care globally.

Subject of Research: Development of a non-opioid pain therapeutic targeting neurotensin receptor 1 using biased allosteric modulation and structure-guided drug design.

Article Title: NIH HEAL Initiative Funds $3.9 Million to Propel Non-Addictive Pain Therapeutic Toward Clinical Trials

News Publication Date: 2025

Web References:
– NIH HEAL Initiative: https://heal.nih.gov/
– Cell Publication on SBI-810: https://www.cell.com/cell/abstract/S0092-8674(25)00508-2
– Nature Publication on SBI-553: https://www.nature.com/articles/s41586-025-09643-2

References: Research supported by NIH/NINDS Award Number UG3NS141745.

Image Credits: Sanford Burnham Prebys Medical Discovery Institute.

Keywords: Non-opioid pain treatment, neurotensin receptor 1, biased allosteric modulator, SBI-810, GPCR drug discovery, cryo-electron microscopy, artificial intelligence, medicinal chemistry, opioid epidemic, translational pharmacology, NIH HEAL Initiative, chronic pain.

The core of their methodology leverages graph neural networks, a class of deep learning models that excel at interpreting complex relational data. Unlike traditional machine learning frameworks that treat each data point independently, GNNs understand and process information structured as graphs — networks of interconnected nodes and edges. This structure perfectly mirrors biological systems such as neural pathways, molecular interaction networks, and genetic profiles, thus allowing the researchers to integrate multifaceted biological knowledge into their predictive algorithms. By embedding this intricate biological context, the model gains a biologically grounded interpretability that is essential for clinical adoption.

Central nervous system drug side effects represent some of the most challenging and unpredictable aspects of pharmacotherapy. Many psychotropic and neurological medications, while therapeutically beneficial, carry risks of unintended cognitive, behavioral, or neurological complications. Traditionally, side effect prediction has hinged on limited clinical trial data, post-market surveillance, and indirect biomarkers, often resulting in delayed recognition of adverse events. The novel approach outlined by Huang and colleagues circumvents these constraints by creating a model that directly simulates the biological underpinnings of drug effects on the CNS, offering a detailed mechanistic view of potential side effects before they manifest clinically.

The investigators meticulously integrated diverse biological datasets encompassing drug molecular structures, protein-protein interaction networks, neurotransmitter pathways, and even gene expression profiles related to CNS function. This comprehensive data integration facilitated the construction of a biologically informed graph representing the complex interplay between pharmacological agents and neural biochemistry. The graph acts as a scaffold upon which the neural network operates, systematically analyzing pathways and molecular interactions to predict how specific drug compounds might disrupt or modulate CNS processes in adverse ways.

Beyond predictive capacity, a hallmark of this research is its emphasis on explainability — a critical feature given the often black-box nature of deep learning models. Traditional AI methods have been criticized for their opacity, making clinical decision-making fraught with uncertainty. Here, the researchers adeptly designed their GNN to output interpretable maps indicating which biological interactions or pathways contribute most significantly to predicted side effects. This transparency not only fosters clinician trust but also offers mechanistic insights that could guide mitigation strategies, such as molecular modification of the drug or patient stratification based on genetic risk factors.

The model demonstrated remarkable performance in validation studies, consistently outperforming conventional machine learning frameworks and rule-based prediction systems. It accurately anticipated side effect profiles across a diverse array of CNS-active drugs, including antidepressants, antipsychotics, and novel neuroprotective agents. Moreover, the model was sensitive enough to detect subtle off-target effects mediated through secondary receptor pathways, a notoriously elusive aspect of drug side effect prediction. Such sensitivity paves the way for refining existing medications and personalizing therapy to minimize patient risk.

A particularly striking aspect of this research is its potential to transform drug development paradigms. Many candidate compounds fail in late-stage trials due to unforeseen CNS toxicity. By applying this graph neural network early in the drug design pipeline, pharmaceutical researchers can preemptively identify high-risk molecules, reallocating resources to safer candidates and possibly shortening development timelines. This proactive strategy could save billions annually in drug development costs while bolstering patient safety worldwide.

The researchers also envision broader applications of their model beyond drug side effect prediction. Because the method intricately models CNS biology, it could potentially aid in understanding complex neurological diseases, identifying biomarkers for CNS disorders, and even suggesting combinatorial drug regimens with reduced adverse interactions. This flexibility underscores the transformative potential of biologically informed GNNs in neuroscience and pharmacology.

Clinicians stand to benefit immensely from this advancement. The model’s integration into clinical decision support systems could provide neurologists and psychiatrists with real-time, patient-specific risk assessments for prescribed medications. Such precision could dramatically reduce incidences of hospitalization due to adverse CNS drug reactions, improving quality of life and healthcare outcomes. Furthermore, it aligns with the growing trend toward personalized medicine, where treatments are tailored not just to disease but to individual biological contexts.

From a data science perspective, this work exemplifies the power of marrying domain-specific biological knowledge with cutting-edge AI techniques. It challenges the prevailing notion that deep learning models require purely large-scale, unstructured data by demonstrating how curated, biologically meaningful data structures can amplify model performance and applicability. This represents a paradigm shift in biomedical AI, championing interpretable and biologically coherent models over purely empirical ones.

Despite these promising results, the authors acknowledge challenges ahead. The complexity of the CNS and the variability of individual patient biology necessitate continuous refinement and expansion of biological data inputs. Additionally, the ethical and regulatory frameworks for deploying AI-driven predictive tools in clinical contexts need careful development to ensure patient privacy and safety. Nevertheless, the foundational work presented offers a robust starting point for addressing these hurdles.

This research reflects a significant stride toward deciphering the complicated interplay between pharmacology and human neurobiology. By revealing the molecular and network-level determinants of drug side effects, it charts a path toward safer, more effective CNS therapeutics. The integration of explainable AI into this domain heralds a new era where technology and biology converge to safeguard patients proactively.

The societal impact of accurately predicting CNS drug side effects is immense. Adverse neuropsychiatric drug reactions often lead to treatment discontinuation, patient distress, and increased healthcare costs. Innovations like those from Huang and colleagues hold the promise of reducing these burdens significantly. As the model continues to evolve and undergo clinical validation, it may become a cornerstone technology in neurology, psychiatry, and personalized pharmacotherapy.

In summary, this work epitomizes the cutting-edge intersection of neuroscience, pharmacology, and artificial intelligence. By constructing a biologically informed graph neural network capable of explainable CNS side effect prediction, the research team has not only solved a complex scientific problem but also opened new frontiers for medical innovation. Future investigations will undoubtedly build on this foundation, pushing the boundaries of how we understand and optimize drug safety in the central nervous system.

The publication of these findings in Translational Psychiatry establishes a critical benchmark for future interdisciplinary research, inspiring further collaboration between computational scientists, biologists, and clinicians. As the medical community embraces AI-driven solutions, this study stands out as a beacon exemplifying how transparency, mechanistic insight, and technological sophistication can unite to improve human health comprehensively.

Subject of Research: Explainable drug side effect prediction in the central nervous system using biologically informed graph neural networks.

Article Title: Explainable drug side effect prediction in central neural system via biologically informed graph neural network.

Article References:
Huang, T., Lin, KH., Machado-Vieira, R. et al. Explainable drug side effect prediction in central neural system via biologically informed graph neural network. Transl Psychiatry (2026). https://doi.org/10.1038/s41398-026-03971-1

Image Credits: AI Generated

DOI: https://doi.org/10.1038/s41398-026-03971-1

Estrogen receptor alpha, a nuclear hormone receptor, plays a pivotal role in the development and progression of breast cancer. Its aberrant activation drives tumor growth, making ERα a prime target for therapeutic intervention. Current treatments often involve selective estrogen receptor modulators or degraders; however, resistance mechanisms frequently emerge, limiting their long-term efficacy. This scenario has propelled scientists to seek alternative strategies that can modulate ERα stability and function more effectively. Bufalin, a steroid compound derived from traditional Chinese medicine, emerged as an intriguing candidate through a sophisticated AI-driven discovery pipeline.

The use of artificial intelligence in drug discovery represents a transformative shift in biomedical sciences. Traditional experimental methods are labor-intensive and time-consuming, often involving trial-and-error screening of vast chemical libraries. In contrast, AI algorithms can rapidly analyze complex biological and chemical datasets, identifying promising molecules with desired biological activities. In this study, the research team deployed advanced machine learning models designed to predict molecular glues — small molecules that facilitate protein-protein interactions leading to targeted protein degradation. By leveraging extensive databases of molecular structures and interaction profiles, AI identified Bufalin as a potential mediator capable of inducing ERα degradation.

Molecular glues have garnered significant attention as an innovative class of therapeutic agents. Unlike classical inhibitors that block active sites, molecular glues facilitate new interactions between target proteins and the cellular degradation machinery, effectively tagging the protein for destruction. This mechanism allows for highly selective modulation of protein levels within the cell. Bufalin’s identification as a molecular glue is particularly noteworthy because it opens new directions in modulating challenging targets like nuclear receptors, which have traditionally been difficult to drug due to their complex regulation and conformational dynamics.

The researchers employed a multi-layered validation approach to confirm Bufalin’s activity. Initial computational predictions were followed by biophysical and biochemical assays that demonstrated Bufalin’s ability to bridge ERα with E3 ubiquitin ligases, the enzymes responsible for tagging proteins for proteasomal degradation. Structural analyses, including cryo-electron microscopy and mass spectrometry, elucidated the tri-molecular complex formed by Bufalin, ERα, and the ligase, revealing the molecular basis of the induced proximity effect. These findings confirm that Bufalin does not merely inhibit ERα but promotes its active ubiquitination and subsequent degradation.

Beyond the mechanistic insights, cell-based experiments unveiled the functional consequences of Bufalin-induced ERα degradation. Cancer cell lines reliant on ERα signaling exhibited marked decreases in proliferation upon Bufalin treatment. Moreover, transcriptional profiling revealed downstream attenuation of estrogen-responsive genes, corroborating the effective dismantling of ERα-mediated signaling pathways. Importantly, comparative studies indicated that Bufalin’s mode of action differed fundamentally from existing selective estrogen receptor degraders (SERDs), potentially circumventing common resistance pathways.

One of the remarkable aspects of this research is its demonstration of AI’s role in unearthing bioactive natural products with previously unrecognized mechanisms. Bufalin had been studied mainly for its cardiotonic and anti-inflammatory properties; however, its capacity as a molecular glue expands its therapeutic relevance substantially. This finding exemplifies how AI can bridge traditional knowledge with modern molecular pharmacology, offering a new lens through which to explore natural compound libraries for drug discovery.

The study also highlights the importance of integrative approaches combining computational predictions with experimental validations. While AI can prioritize candidates rapidly, empirical evidence remains critical to decipher complex biological interactions and to understand pharmacodynamics and toxicity profiles. The researchers’ comprehensive methodology, encompassing in silico modeling, biochemical assays, and cellular analyses, set a rigorous standard for future work in this rapidly evolving field.

Bufalin’s potential therapeutic application extends into breast cancer treatment paradigms where hormone receptor status is a critical determinant. Since ERα-positive breast cancers constitute a majority of breast cancer diagnoses worldwide, the introduction of a molecular glue degrader offers a desperately needed option, especially for patients who develop resistance to endocrine therapies. Future clinical investigation will be necessary to evaluate Bufalin’s safety, efficacy, and pharmacological characteristics in vivo, but the preclinical results are undeniably promising.

This research also paves the way for the discovery of other molecular glue degraders targeting a broad spectrum of disease-relevant proteins. By refining and expanding AI models, the identification process can be diversified and accelerated, potentially transforming how pharmaceutical companies approach ‘undruggable’ targets. The modular nature of molecular glues allows for tailored interventions designed for selective degradation, reducing off-target effects and improving patient outcomes.

The discovery of Bufalin as an ERα molecular glue degrader exemplifies how blending AI with molecular biology can overcome longstanding drug development hurdles. This paradigm shift in drug design has far-reaching implications beyond oncology, potentially influencing treatments for neurodegenerative diseases, immune disorders, and viral infections, where aberrant protein regulation plays a pathogenic role. By targeting protein stability rather than merely function, clinicians may gain access to a new class of interventions with greater specificity and durability.

Furthermore, the study emphasizes the significance of multidisciplinary collaboration. Chemists, biologists, data scientists, and clinicians joined forces to translate AI-generated hypotheses into tangible experimental evidence. Such collaborative ecosystems are essential for harnessing the full power of AI-enhanced drug discovery, ensuring that computational advances are grounded in biological reality and clinical relevance.

In addition to its scientific merit, this breakthrough carries profound implications for drug affordability and accessibility. Artificial intelligence enables more cost-effective exploration of chemical space, potentially shortening timelines and reducing expenses associated with bringing novel therapeutics to market. This could democratize access to cutting-edge treatments, particularly for diseases with high unmet medical needs like hormone receptor-positive breast cancer.

Looking forward, the integration of AI-driven methods with emerging technologies such as single-cell proteomics, CRISPR screens, and high-throughput structural biology could further revolutionize our understanding of protein interactions and degradation pathways. Bufalin’s identification as a molecular glue may represent just the tip of an iceberg, with many more druggable mechanisms awaiting discovery through sophisticated computational and experimental synergies.

In conclusion, harnessing artificial intelligence to uncover Bufalin as a molecular glue degrader of estrogen receptor alpha represents a landmark achievement in contemporary biomedical research. This study not only sheds light on a novel mechanism to combat hormone-driven cancers but also showcases the transformative power of AI-guided drug discovery. As the pharmaceutical landscape evolves, the fusion of computational ingenuity with biological insight promises to unlock new frontiers in disease treatment, heralding an era of more precise, effective, and personalized medicine.

Subject of Research: Identification of Bufalin as a molecular glue degrader targeting estrogen receptor alpha using artificial intelligence.

Article Title: Harnessing artificial intelligence to identify Bufalin as a molecular glue degrader of estrogen receptor alpha

Article References:
Jiang, S., Liu, K., Jiang, T. et al. Harnessing artificial intelligence to identify Bufalin as a molecular glue degrader of estrogen receptor alpha. Nat Commun 16, 7854 (2025). https://doi.org/10.1038/s41467-025-62288-7

Image Credits: AI Generated