The Bundibugyo Ebola virus, first identified in Uganda in 2007, is part of the Filoviridae family, which encompasses other lethal viruses such as Zaire, Sudan, and Marburg. These viruses cause severe hemorrhagic fever characterized by systemic bleeding, septic shock, metabolic acidosis, and multi-organ failure. Given the high fatality and limited treatment options, the urgency of finding effective antiviral agents is paramount. Traditional antiviral discovery pipelines have been slow, but SwRI is leveraging breakthroughs in molecular docking and machine learning to transform this landscape.

SwRI’s proprietary Rhodium™ molecular docking software combines physics-based modeling with advanced computational algorithms to predict how candidate drug molecules interact with viral proteins. This software enables rapid virtual screening of vast chemical libraries by simulating molecular binding affinities and pharmacokinetic properties. The integration of Rhodium™ with large language model (LLM) artificial intelligence tools represents a groundbreaking convergence of computational chemistry and natural language processing, which substantially reduces the time from compound ideation to experimental validation.

This collaborative effort is part of a sustained partnership between SwRI and Texas Biomedical Research Institute, a leading institution specializing in high-containment virus research. Texas Biomed operates one of the world’s few Biosafety Level 4 (BSL-4) laboratories, where it conducts live-virus testing under stringent biocontainment protocols. SwRI’s rapid identification of candidate drugs is uniquely complemented by Texas Biomed’s capability to assess antiviral efficacy and safety against live Bundibugyo virus, given the enhanced biosafety and technical expertise available at their cutting-edge facilities.

The motivation behind this collaboration is clear: while existing antivirals have shown some efficacy against other Ebola strains, none are approved specifically for Bundibugyo Ebola virus to date. SwRI and Texas Biomed’s decade-spanning alliance commenced with work funded by the Defense Threat Reduction Agency (DTRA), focusing initially on combinatorial therapies targeting the Zaire Ebola virus. A small molecule known as “M7” emerged from this research, functioning as a host-directed antiviral that potentially interferes with pathways common across multiple Ebola species. However, despite M7’s potent antiviral activity, its pharmacological profile limited scalability toward approved drug manufacturing.

To overcome these limitations, SwRI initiated internally funded research to identify more chemically stable analogs of M7 using their GAMES (Generative Approaches for Molecular Encodings) language model. The GAMES system generates Simplified Molecular Input Line Entry System (SMILES) strings, a standardized notation representing chemical structures as text, enabling rapid virtual compound generation and prioritization. By leveraging this AI-driven platform, SwRI synthesized 18 novel analogs optimized not only for biological activity but also for synthetic accessibility and supply chain robustness, considering the urgency of outbreak response.

This artificial intelligence-aided approach marks a paradigm shift from traditional high-throughput screening to intelligent, targeted compound design. The model’s ability to generate molecular candidates that meet multiple criteria — including potency, stability, and manufacturability — allows researchers to bypass the conventional trial-and-error method, accelerating the preclinical pipeline significantly. More importantly, focusing on readily available chemical precursors ensures that promising candidates can move swiftly into laboratory synthesis and in vitro evaluation without delays associated with supply bottlenecks.

Texas Biomed’s upcoming screening of these AI-designed compounds in their BSL-4 laboratory represents a critical step toward validating their antiviral potential. Live-virus efficacy testing will determine whether these molecules inhibit viral replication effectively and if they demonstrate tolerance in a biological system. Positive results could swiftly lead to advance preclinical studies and eventual clinical trials, bridging the gap between computational predictions and real-world therapeutic applications.

Beyond immediate therapeutic development, this research underscores the strategic importance of continuous investment in infectious disease research infrastructure. As articulated by Texas Biomed’s leadership, sustained financial and scientific commitments are essential to not only manage current outbreaks but also to build resilience against future viral threats worldwide. The integration of AI and biosafety expertise exemplifies how interdisciplinary collaboration can drive innovation and public health preparedness at an unprecedented pace.

Ebola virus infections, though geographically limited to certain regions of equatorial Africa, pose a global threat due to their high mortality and pandemic potential. Natural reservoirs, such as fruit bats, maintain these viruses in the wild, making spillover events unpredictable. Advancing antiviral capabilities specifically tailored to various Ebola species, including the less-studied Bundibugyo virus, is thus a crucial component of global epidemic prevention and response strategies.

SwRI’s application of machine learning and large language models in drug discovery is a testament to how artificial intelligence is revolutionizing biomedical research. By harnessing computational power to explore chemical space more judiciously, researchers can identify candidates that are both innovative and pragmatically suited for rapid deployment. The success of this approach in targeting the Bundibugyo virus could establish a framework for combating other emerging infectious diseases with similarly urgent therapeutic needs.

The synergy between SwRI’s technological innovations and Texas Biomed’s virological expertise is a model for future partnerships aiming to accelerate antiviral development pipelines. As the Bundibugyo outbreak evolves, these joint efforts provide hope for effective interventions that can reduce mortality and mitigate the public health impact. Moreover, the research sets a precedent for employing AI tools not only as supportive technologies but as active drivers of discovery in high-risk pathogen contexts.

This project fortifies the biomedical innovation environment in San Antonio, Texas, positioning the region as a critical hub for infectious disease research. With SwRI’s broad technical capabilities spanning multiple industries and Texas Biomed’s specialized virology focus, the collaboration epitomizes the multidisciplinary approach required for timely and impactful global health solutions. The ongoing work heralds a new era in which computational and experimental research converge to fight some of the world’s deadliest viruses with unprecedented speed and precision.

For more detailed information about SwRI’s drug discovery initiatives, interested parties can visit their dedicated page on structure-based drug design, outlining the advanced methodologies and tools employed to accelerate pharmaceutical development.

Subject of Research: Bundibugyo Ebola virus; antiviral drug discovery using AI-driven molecular docking and machine learning techniques.

Article Title: AI-Driven Discovery of Novel Antiviral Compounds Targets Deadly Bundibugyo Ebola Virus

News Publication Date: May 26, 2026

Web References: https://www.swri.org/markets/biomedical-health/pharmaceutical-development/drug-discovery-research/structure-based-drug-design?&utm_medium=referral&utm_source=eurekalert!&utm_campaign=ebola-research-pr

Image Credits: Southwest Research Institute

Keywords: Ebola virus, Bundibugyo virus, antiviral drug discovery, machine learning, molecular docking, Biosafety Level 4, Filoviridae, artificial intelligence, GAMES language model, SMILES, SwRI, Texas Biomed

The significance of this development cannot be overstated. Traditional methods of drug design often involve an immense amount of trial and error, compounded by the intricate and time-consuming processes of molecular validation and comparison. By training the GAMES model to produce valid SMILES strings from a diverse array of molecular structures, the researchers at SwRI have introduced a systematic approach to building extensive databases and networks of molecules sat for informed analysis by artificial intelligence. This opens up new avenues for efficiency in drug discovery, allowing researchers to identify promising compounds faster than ever before.

Dr. Jonathan Bohmann, the lead developer of SwRI’s Rhodium™ molecular docking software, articulated the transformative potential of such technological advancements. He pointed out that the integration of the GAMES model into existing workflows allows for a generalized and more expedited method of exploring large chemical libraries for novel drug candidates. This is pivotal in an industry where speed and accuracy are paramount, especially given the competitive nature of pharmaceutical development where the journey from discovery to market can span over a decade.

What sets GAMES apart from other models is its training methodology, which involved a meticulous focus on carbon-based molecules and a suite of reference compounds to ensure the accuracy of the SMILES strings produced. As Dr. Bohmann aptly noted, LLMs allow researchers to approach molecular data in a manner akin to handling natural language, thus leveraging the text-based integrity inherent to SMILES strings without necessitating convoluted transformations into abstracts that could obscure valuable information.

Moreover, the researchers’ use of advanced techniques like Low-Rank Adaptation (LoRA) and Quantized LoRA (QLoRA), which are designed to fine-tune LLMs with efficiency, further enhances the model’s performance. This is especially critical, given the vast computational power typically required to process complex molecular data. By reducing the hardware and energy demands associated with running their models, the team is not only ensuring sustainability but also paving the way for broader applications across different domains beyond drug discovery.

The implications of GAMES reach beyond mere efficiency; they touch upon the qualitative aspects of drug development. With GAMES, researchers envision a future where the accurate generation of SMILES could radically reshape how drug candidates are evaluated for “drug-likeness,” a term referring to a set of characteristics that predict the likelihood of a compound receiving regulatory approval and being effective in clinical settings. By leveraging structured datasets and employing rigorous training techniques, the SwRI team has successfully heightened the number of validated SMILES strings while concurrently minimizing errors from invalid outputs.

As GAMES continues to evolve, the exploration of chemical landscapes systematically through rigorous testing will be a primary focus. Both Dr. Bohmann and his colleague, Research Scientist Daniel Hinojosa, are intending to seek further funding to expand the project’s scope, aiming for enhancements that could substantially benefit the drug discovery domain. In its nascent stages, the GAMES initiative has already begun to influence ongoing research at SwRI, showcasing the immediate practical impact of such cutting-edge development.

Funding for GAMES was made possible through the SwRI Internal Research and Development Program, aligning perfectly with SwRI’s mission of continually investing in future technologies. Over the past year, the institute allocated upwards of $11 million to expand its scientific repertoire and enhance its status as a leader in research and technology, all while fostering the professional growth of its talented workforce. This proactive approach to innovation signifies an unwavering commitment to pushing the boundaries of what is currently achievable in scientific research.

In conclusion, the creation of the GAMES model stands as a testament to the efficacy of integrating machine learning techniques into scientific inquiry. As it becomes more entrenched in the drug development landscape, it is poised to not only accelerate the identification of new therapeutic agents but also substantially augment the precision and adaptability with which molecular properties are assessed. This evolution heralds a new chapter in the quest for effective pharmacological solutions, establishing an essential bridge between artificial intelligence and biochemistry—a relationship undoubtedly destined for further exploration and growth.

Subject of Research: Development of a large language model for drug discovery
Article Title: Southwest Research Institute Develops AI Model to Accelerate Drug Design
News Publication Date: August 14, 2025
Web References: https://www.swri.org/markets/biomedical-health/pharmaceutical-development/drug-discovery/structure-based-virtual-screening
References: Funding provided by SwRI Internal Research and Development Program
Image Credits: Southwest Research Institute

Keywords

Drug development, Generative AI, Machine learning, Medical technology