1
|
Yoshikawa AM, Rangel AE, Zheng L, Wan L, Hein LA, Hariri AA, Eisenstein M, Soh HT. A massively parallel screening platform for converting aptamers into molecular switches. Nat Commun 2023; 14:2336. [PMID: 37095144 PMCID: PMC10126150 DOI: 10.1038/s41467-023-38105-4] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2022] [Accepted: 04/14/2023] [Indexed: 04/26/2023] Open
Abstract
Aptamer-based molecular switches that undergo a binding-induced conformational change have proven valuable for a wide range of applications, such as imaging metabolites in cells, targeted drug delivery, and real-time detection of biomolecules. Since conventional aptamer selection methods do not typically produce aptamers with inherent structure-switching functionality, the aptamers must be converted to molecular switches in a post-selection process. Efforts to engineer such aptamer switches often use rational design approaches based on in silico secondary structure predictions. Unfortunately, existing software cannot accurately model three-dimensional oligonucleotide structures or non-canonical base-pairing, limiting the ability to identify appropriate sequence elements for targeted modification. Here, we describe a massively parallel screening-based strategy that enables the conversion of virtually any aptamer into a molecular switch without requiring any prior knowledge of aptamer structure. Using this approach, we generate multiple switches from a previously published ATP aptamer as well as a newly-selected boronic acid base-modified aptamer for glucose, which respectively undergo signal-on and signal-off switching upon binding their molecular targets with second-scale kinetics. Notably, our glucose-responsive switch achieves ~30-fold greater sensitivity than a previously-reported natural DNA-based switch. We believe our approach could offer a generalizable strategy for producing target-specific switches from a wide range of aptamers.
Collapse
Affiliation(s)
- Alex M Yoshikawa
- Department of Chemical Engineering, Stanford University, Stanford, CA, 94305, USA
| | | | - Liwei Zheng
- Department of Radiology, Stanford University, Stanford, CA, 94305, USA
| | - Leighton Wan
- Department of Bioengineering, Stanford University, Stanford, CA, 94305, USA
| | - Linus A Hein
- Department of Electrical Engineering, Stanford University, Stanford, CA, 94305, USA
| | - Amani A Hariri
- Department of Radiology, Stanford University, Stanford, CA, 94305, USA
| | - Michael Eisenstein
- Department of Radiology, Stanford University, Stanford, CA, 94305, USA
- Department of Electrical Engineering, Stanford University, Stanford, CA, 94305, USA
| | - H Tom Soh
- Department of Radiology, Stanford University, Stanford, CA, 94305, USA.
- Department of Electrical Engineering, Stanford University, Stanford, CA, 94305, USA.
- Chan Zuckerberg Biohub, San Francisco, CA, 94158, USA.
| |
Collapse
|
2
|
Shashikumar SP, Wardi G, Malhotra A, Nemati S. Artificial intelligence sepsis prediction algorithm learns to say "I don't know". NPJ Digit Med 2021; 4:134. [PMID: 34504260 PMCID: PMC8429719 DOI: 10.1038/s41746-021-00504-6] [Citation(s) in RCA: 25] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2021] [Accepted: 08/09/2021] [Indexed: 01/07/2023] Open
Abstract
Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as indeterminate rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925-0.953; ED: 0.938-0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as indeterminate amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.
Collapse
Affiliation(s)
| | - Gabriel Wardi
- Department of Emergency Medicine, University of California San Diego, San Diego, USA
- Division of Pulmonary, Critical Care and Sleep Medicine, University of California San Diego, San Diego, USA
| | - Atul Malhotra
- Division of Pulmonary, Critical Care and Sleep Medicine, University of California San Diego, San Diego, USA
| | - Shamim Nemati
- Division of Biomedical Informatics, University of California San Diego, San Diego, USA.
| |
Collapse
|