You are here

AI-accelerated Biosensor Design


TECHNOLOGY AREA(S): Bio Medical, Chem Bio Defense

OBJECTIVE: Apply artificial intelligence (AI) to accelerate the design of highly specific, engineered biomarkers for rapid virus detection.

DESCRIPTION: This SBIR seeks to leverage AI technologies to accelerate the development of aptamer-based biosensors that specifically bind to biomolecular structures. Aptamers are short single-stranded nucleic acid sequences capable of binding three-dimensional biomolecular structures in a way similar to antibodies. Aptamers have several advantages as compared to antibodies, including long shelf-life, stability at room temperature, low/no immunogenicity, and low-cost. The current state-of-the-art aptamer designs rely heavily on in vitro approaches such as SELEX (Systematic Evolution of Ligands by Exponential Enrichment) and its advanced variations. SELEX is a cyclic process that involves multiple rounds of selection and amplification over a very large number of candidates (>10^15). The iterative and experimental nature of SELEX makes it time consuming (weeks to months) to obtain aptamer candidates, and the overall probability of ultimately obtaining a useful aptamer is low (30%-50%).Attempts to improve the performance of the original SELEX process generally result in increased system complexity and system cost as well as increased demand on special domain expertise for their use. Furthermore, a large number of parameters can influence the SELEX process. Therefore, this is a domain that is ripe for AI. Recent AI research has demonstrated the potential for machine learning technologies to encode domain knowledge to significantly constrain the solution space of optimization search problems such as solving the biomolecular inverse problems. Such in silico techniques consequently offer the potential to provide a cost-effective alternative to make aptamer design process more dependable, thereby, more efficient. This SBIR seeks to leverage emerging AI technologies to develop a desktop-based AI-assisted aptamer design capability that accelerates the identification of high-performance aptamers for detecting new biological antigens.

PHASE I: This SBO is accepting Direct to Phase II proposals ONLY. Proposers must show the feasibility of an algorithm prototype that can assist in vitro design of apatmers with improved binding potential over the baseline in vitro approaches. Such algorithm prototype should demonstrate the capability of an aptamer designed for detection of a unique protein/peptide with high affinity (the equilibrium dissociation constant, K_d <10 nM). Furthermore, Phase I must demonstrate that the computation complexity of the algorithm can be scaled to large search spaces (number of sequence candidates>1015) and can achieve the Phase II time efficient objective.


Phase II effort will focus on enhancing the computational algorithm performance and improving computational efficiency to be implementable with desktop computing resources and scalable to very large search spaces (number of sequence candidates >1015). Phase II will also develop an integration process that combines the in silico algorithms with in vitro processes that significantly improve the design consistency and autonomy. Collaboration with an in vitro aptamer designer is required. The combined approach will demonstrate rapid identification of promising aptamer biosensors (in days vs. weeks/months required for in vitro approaches alone) for detection of biological agents across classes of target proteins/peptides, with the probability of successfully identifying high-affinity (KD <1 nM) aptamer sequences greater than 90%. Phase II will demonstrate the design of two separate aptamers, each for unique proteins/peptides that achieve the performance metrics. Target classes of interest include pathogenic antigens (e.g., spike and/or coat proteins of new coronavirus or influenza) and secreted toxins (e.g., botulinum neurotoxins which are single polypeptide chains). Proposers may propose other biomolecular structure targets of interest. In the optional phase, the performer is also expected to improve the automation and demonstrate increased efficiency over Phase II performance objectives over additional targets.

i. Schedule/Milestones/Deliverables

  • Month 1: Report describing the algorithms approaches, detailed experiment plan, data plan, targeted in vitro process for integration
  • Month 3: Report on enhancement of algorithms and approaches' expanded capabilities, updated performance of the prototype algorithms
  • Month 6: Interim report providing preliminary analysis of the algorithms, analysis of the potential for further improvement, and computation resource requirements
  • Month 9: Report on initial integration of the in silico algorithms with the in vitro aptamer design process
  • Month 12: Mid-term report updating the algorithms approach, comprehensive performance analysis, description of the integrated process and the advantages over the state-of-the-art; delivery of the first aptamer biosensor design with lab validation
  • Month 15: Report describing the updated implementation of the application software prototype, integration enhancement, and revised quantification of the performance
  • Month 18: On-site demonstration of the integrated design process
  • Month 21: Report providing updated description of the integrated design process and the advanced features of the integration process
  • Month 24: Final Phase II report documenting the algorithm approach, integrated design process, experimental results and performance analysis, comparison against state-of-the art, and plan for optional phase development; delivery of the second aptamer biosensor design with lab validation
  • Month 27: Demonstration that the integration process exceeds Phase II performance objectives
  • Month 30: Report documenting the final integrated design process and performance

PHASE III: Phase III focuses on improving in vivo performance of the aptamer sensors and developing both commercial and DoD applications. A commercially focused Phase III application could include the development of low-cost, home-use, lateral flow detection test kits for new strains of viral infections. The Phase III effort for DoD applications should result in the development of field tools that can accurately, effectively, and rapidly identify high-performance aptamer sequences for detecting novel pathogens in combat environments and biomarkers for biological weapons.

KEYWORDS: Biosensor design, Aptamer, SELEX, virus screening


[1] Song, Yanling, et al. "Discovery of Aptamers Targeting Receptor-Binding Domain of the SARS-CoV-2 Spike Glycoprotein." (2020)

[2] Tuerk, Craig, and Larry Gold. "Systematic evolution of ligands by exponential enrichment: RNA ligands to bacteriophage T4 DNA polymerase." science 249.4968 (1990): 505-510

[3] Gotrik, Michael R., et al. "Advancements in aptamer discovery technologies." Accounts of chemical research 49.9 (2016): 1903-1910

[4] Wang, Tao, et al. "Three decades of nucleic acid aptamer technologies: Lessons learned, progress and opportunities on aptamer development." Biotechnology advances 37.1 (2019): 28-50

[5] Gold, Larry, et al. "Aptamer-based multiplexed proteomic technology for biomarker discovery." Nature Proceedings (2010): 1-1

US Flag An Official Website of the United States Government