In the high-stakes world of drug development, structural biology has long been the gatekeeper of progress. For decades, researchers have relied on cryo-electron microscopy (cryo-EM) and X-ray crystallography to visualize the molecular machinery of life. While these technologies have yielded Nobel Prize-winning insights, they are notorious for their bottlenecks. The preparation of samples, the optimization of grids, and the sheer technical demand of the equipment often result in workflows that span weeks or even months.
Enter Immuto Scientific, a biotechnology firm co-founded by electrical engineers Faraz A. Choudhury, Ph.D., and Daniel Benjamin, Ph.D. By marrying the precision of mass spectrometry with the predictive power of artificial intelligence, Immuto is carving out a new, faster path to protein structure determination—one that promises to disrupt the traditional timelines of antibody-antigen analysis.
The Bottleneck of Conventional Structural Biology
Cryo-EM remains the gold standard for achieving near-atomic or atomic-resolution snapshots of protein structures. However, as Daniel Benjamin, CTO of Immuto Scientific, points out, the "barrier to entry" for such high-resolution work is significant.
“Cryo-EM is always going to be a relevant tool, especially for proteins that haven’t been solved yet,” Benjamin said in an interview. “But it requires a massive investment in specialized equipment and highly trained expertise. Furthermore, the iterative nature of grid screening and sample preparation creates a notorious bottleneck.”
When a drug discovery program relies on understanding the exact orientation of an antibody binding to an antigen, every week spent in a cryo-EM queue represents a delay in reaching the clinic. Immuto’s proposition is not to replace cryo-EM, but to offer a high-throughput alternative that provides residue-level structural data with significantly reduced lead times.
Chronology: From Engineering Roots to Clinical Ambitions
Immuto Scientific was established in 2018, born from the unconventional intersection of electrical engineering and biology. Choudhury and Benjamin, leveraging their technical backgrounds, sought to apply signal processing and system-level optimization to the messy, high-dimensional world of proteomics.
- 2018: Immuto Scientific is founded with a mission to streamline structural biology through advanced mass spectrometry.
- Early Development: The team begins by validating their platform using standard human cell lines, gradually scaling to more complex biological environments.
- Expansion of Capability: The platform evolves to handle single-cell suspensions, 2D and 3D cell cultures, tumors, and eventually patient-derived organoids and tissue resections.
- 2025 (Last Year): The company announces a strategic partnership with Daiichi Sankyo, focusing on novel target discovery and antibody development within the oncology space.
- 2026 (Current): Immuto prepares to unveil its v1 antibody-antigen model at the PEGS conference, signaling a shift from a platform-focused company to a dual-pronged business model encompassing both internal pipeline development and external collaborations.
- 2027 (Projected): Immuto’s lead oncology program is slated to enter clinical trials.
Supporting Data: Scaling Throughput and Accuracy
The core of Immuto’s competitive advantage lies in the throughput of its platform. While a standard cryo-EM workflow might produce a handful of structural insights over several weeks, Immuto’s system is capable of processing approximately 1,000 samples per week.
“We can get data on about 1,000 samples per week with our platform, so that roughly translates to something like 100 structures per week,” Benjamin explains.
This throughput is augmented by an AI-driven computational framework that addresses the limitations of current protein-folding models. Since the advent of AlphaFold, tools like Boltz, Chai, and ByteDance’s Protenix have democratized the generation of protein structures. However, these tools are inherently predictive rather than empirical; they can generate thousands of plausible structures for an antibody-antigen complex, but they often struggle to rank the correct configuration among the top results.
Immuto’s mass spectrometry data serves as an empirical "tie-breaker." By providing physical constraints from the lab, the platform allows the AI to filter through the vast library of generated models, identifying the structure that aligns with experimental reality. Benjamin describes the resulting accuracy as “almost dead on with what you would see with cryo-EM.”
The Shift Toward "In Vivo" Structural Biology
One of the most compelling aspects of Immuto’s approach is its ability to probe proteins within their natural, complex environments. Unlike traditional methods that often require purified proteins in a lab-altered state, Immuto’s technology can function within living cells.
“For target discovery, we want patient-derived models that capture native biology and heterogeneity, rather than immortalized cell lines,” Benjamin notes. By moving from simple cell cultures to complex 3D organoids and actual tissue resections, the company aims to understand how protein behavior changes in the presence of the tumor microenvironment—a level of contextual detail that is difficult to capture via static structural methods.
This capability is particularly vital for identifying "conformational targets"—structures that are highly dynamic and often transient, making them elusive for traditional crystallization techniques.
Official Responses and Strategic Vision
At the upcoming PEGS conference, Immuto plans to share its first public performance data for its v1 antibody-antigen model. The model was trained and validated on a curated set of 30 to 40 structures, specifically engineered to solve the "ranking problem" in antibody-antigen interaction.
The company’s philosophy on antibody discovery is intentionally contrarian. Rather than hunting for high-affinity binders from the outset, Immuto prioritizes the location of the binding event.
“We intentionally start with medium- or low-affinity binders just to ensure they are binding to the exact right epitope,” Benjamin says. “Once we know it binds to the right site, we can engineer all the binding affinity we need.”
This "epitope-first" strategy, backed by the speed of their mass spectrometry platform, allows them to iterate rapidly through candidate molecules, ensuring that the final drug candidate is not just potent, but also structurally optimized for its specific biological target.
Implications for the Future of Drug Discovery
The integration of AI with empirical mass spectrometry represents a significant shift in how the pharmaceutical industry approaches structural biology. By lowering the barrier to entry, Immuto is enabling smaller biotech firms and large pharmaceutical partners alike to explore more targets in shorter timeframes.
1. The Death of the "Bottleneck"
If Immuto can consistently achieve 100 structures per week, the traditional "structural bottleneck" in drug discovery may soon become a relic of the past. This would allow researchers to perform structural screens early in the funnel, rather than waiting for the lead optimization phase.
2. Democratizing Structural Insights
The reliance on massive, expensive, and scarce cryo-EM facilities has centralized structural expertise. By contrast, mass spectrometry is a staple of almost every modern biology laboratory. Immuto’s platform could effectively democratize high-level structural biology, allowing a broader range of researchers to gain insights that were previously locked away behind massive capital expenditures.
3. Precision Engineering of Antibodies
The focus on epitope mapping over initial binding strength suggests a more rational approach to drug design. If a developer can confirm the binding site with high confidence in a matter of days, they can use protein engineering to "tune" the affinity, effectively de-risking the development process long before a drug reaches the clinic.
Conclusion
Immuto Scientific sits at a critical junction of modern medicine. By combining the raw, empirical power of mass spectrometry with the predictive, generative capabilities of artificial intelligence, they have created a platform that is not only faster than traditional methods but also more capable of reflecting the true, messy, and heterogeneous nature of human disease.
As the company moves toward its first clinical trials in 2027 and continues to expand its partnerships with industry leaders like Daiichi Sankyo, the industry will be watching closely. If Immuto can prove that its "1,000 samples per week" claim holds up across diverse clinical programs, it will likely force a industry-wide reevaluation of the structural biology pipeline. In the quest to treat complex oncology targets, the ability to see exactly where a drug lands—and to do so at scale—may prove to be the most valuable asset in the modern drug hunter’s toolkit.
About the Author
