Autonomous Nucleic Acid and Protein Nanocomputing Agents Engineered to Operate in Living Cells

Abstract

In recent years, the rapid development and employment of autonomous technology have been observed in many areas of human activity. Autonomous technology can readily adjust its function to environmental conditions and enable an efficient operation without human control. While applying the same concept to designing advanced biomolecular therapies would revolutionize nanomedicine, the design approaches to engineering biological nanocomputing agents for predefined operations within living cells remain a challenge. Autonomous nanocomputing agents made of nucleic acids and proteins are an appealing idea, and two decades of research has shown that the engineered agents act under real physical and biochemical constraints in a logical manner. Throughout all domains of life, nucleic acids and proteins perform a variety of vital functions, where the sequence-defined structures of these biopolymers either operate on their own or efficiently function together. This programmability and synergy inspire massive research efforts that utilize the versatility of nucleic and amino acids to encode functions and properties that otherwise do not exist in nature. This Perspective covers the key concepts used in the design and application of nanocomputing agents and discusses potential limitations and paths forward.

Keywords: directed evolution; nanocomputing agents; nucleic acid nanoparticles; proteins; rational design.

Figure 1

Schematic comparison of informational flow: from building blocks to functional output. In silico operations rely on machine language composed of two distinct abstract symbols: ON (1) and OFF (0), represented by physical states of low and high voltage. All information processing, interpretation, and execution are carried out by the central processing unit (CPU). In contrast, biological NCAs use two different chemical codes, either separately or in combination. The sequences of nucleic acids or amino acids result in higher-order architectures with unique autonomous functions that can be executed in vivo.

Figure 2

Schematics depicting basic strategies of functionality modulation. Two interdependent, individually nonactive split NCAs (blue) interact inside the cells, and strands are rearranged leading to functional molecules, e.g., transcription factor decoys, FRET signal, and RNAi inducers. Alternatively, NCA is activated upon sensing and binding endogenous triggers (orange). The presence of cell-specific receptors allows the binding of cognate aptamers displayed in complex DNA origami structures. Recognition of the receptors triggers a change in the NCA’s 3D shape, thus exposing therapeutic cargo. The kill switch on the other hand represents a reversible system to modulate blood coagulation. If necessary, the aptamer-fiber complex limits thrombin availability for a certain time, while injecting the kill switch releases thrombin from the bound state.

Figure 3

Protein-based NCAs are input-process-output modules. The core of an NCA is the target (T) protein which, when allosterically coupled to the sensor domain (S), yields a quantifiable output (activation/inactivation, dimerization, trimerization) in response to input cues, such as light, ligand, RNA, temperature or pH. The processing unit comprises of Boolean logic gates, featuring two-tiered regulation in the form of an OR gate or noncommutativity in the combinatorial NOT and AND gates. The output signal may be blue light induced rapid reversible inactivation of the target (T) protein, resulting in dissociation of its downstream effectors (D) or ligand induced irreversible activation. Light induced dimerization and ligand induced trimerization readouts, experimentally demonstrated in different target proteins, are schematized. FKBP: FK506 binding protein, FRB: FKBP12–rapamycin binding protein.

Figure 4

Two-tiered regulation and noncommutativity in circuits constructed using protein-based NCAs. (a) Domain organization of the target protein, focal adhesion kinase (FAK) and insertion sites of the sensor domains: LOV2 and uniRapR. An OR logic gate is fabricated using the chemogenetically activated uniRapR and the optogenetically activated LOV2 domains. The fold change in the size of focal adhesions (FA) in FAK–/– cells expressing the engineered FAK protein is significantly higher in the presence of either or both stimuli, i.e., rapamycin and blue light. Source data obtained from Vishweshwaraiah et al. (b) Focal adhesions form upon rapamycin addition, as seen by confocal imaging of fixed MDA-MB-231 cells transfected with “dark” or “lit” mutants of an engineered Src kinase containing the uniRapR and LOV2 sensor domains. Modified from Chen et al. (c) A combination of NOT and AND logic gates can describe the functioning of the chimeric Src kinase-based NCA, under dual regulation by blue light and ligand, when the ligand (rapamycin) is added first, (d) whereas a combination of AND and OR logic gates can explain its logical operations, when blue light is the first signal. Live-cell imaging shows changes in the orientation of the cell upon exposure to input cues. Modified from Chen et al. Source data for (a) are adapted with permission under a Creative Commons Attribution CC BY 4.0 International License from ref (101). Copyright 2021, The Author(s) (https://creativecommons.org/licenses/by/4.0/). Panels (b–c) reprinted (Adapted or Reprinted in part) with permission under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC) from ref (102). Copyright 2023, The Authors, some rights reserved, exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works.

Figure 5

Hypothetical activity of NCA-virus-like aptamer-targeted cell specific vesicle. After cell specific binding mediated through DNA/RNA aptamer-receptor, the vesicle is internalized (not shown) and based on the presence or absence of endogenous molecular triggers modulate activities of encoded NCAs. Depicted NCA carry on CRISPR-Cas protein and guide RNA (gRNA) that result in genome editing controlled by RNAi. Embedded aptamer in central region can stimulate or inhibit cellular immune response to NCA. Distal part of the RNA contains pre-miRNA fused to gRNA. The pre-miRNA can be processed by Dicer and subsequently loaded to RISC complex and regulate expression of targeted gene. Dicer processing of pre-miRNA also liberates gRNA, which could be loaded into CRISPR-Cas protein if expressed. Suggested systems could be enriched with other functional moieties or advanced logic interactions with cellular components.