DNA-FLASHa DNAzyme Walker-Based Nanosensor for Digital Biosensing at the Point of Care

ACS Nano American Chemical Society (ACS) 20:30 (2026) 21201-21214

Authors:

Seppe Driesen, Dries Vloemans, Gangamallaiah Velpula, Céline Van Leemput, Mirjam Kümmerlin, Achillefs N Kapanidis, Cláudio Pinheiro, An Hendrix, Steven De Feyter, Karen Leirs, Jeroen Lammertyn

Abstract:

The convergence of biosensing and nucleic acid (NA) nanotechnology represents an opportunity for the development of diagnostic technologies. By harnessing the programmability of nucleic acids, we can design biosensors that offer advantages in stability, scalability, versatility and sensitivity, compared to protein-based systems. In this work we introduce DNA-FLASH (DNA-based FLuorescence Amplification upon Single-target Hybridization), a DNA nanosensor concept for digital biosensing. DNA-FLASH leverages fluorescence amplification by a multicomponent NA enzyme (MNAzyme)-driven DNA walker mechanism on a DNA origami disk. Using super-resolution microscopy and single-molecule photobleaching, we demonstrate reproducible fabrication of DNA-FLASH nanosensors with 12 fluorophore-quencher substrates on a ring-shaped track, surrounding a single MNAzyme walker. This nanoarchitecture enables single-molecule detection of DNA targets down to picomolar concentrations. Through precise patterning of DNA-FLASH nanosensors in arrays on glass, we facilitate high-throughput single-molecule readout. We successfully demonstrate DNA-FLASH in human plasma samples and on an in-house developed, fully integrated, self-powered, disposable microfluidic chip, highlighting its potential use in point-of-care settings. Altogether, DNA-FLASH may support the development of next-generation biosensors capable of addressing pressing global challenges, including rapid disease detection, environmental sustainability, and personalized healthcare.

From statistics to deep learning in single-molecule fluorescence resonance energy transfer analysis

Current Opinion in Structural Biology Elsevier 98 (2026) 103268

Authors:

Maryam Beigzadeh, Jagadish P Hazra, Achillefs N Kapanidis

Abstract:

Single-molecule fluorescence resonance energy transfer (smFRET) is a versatile technique for studying biomolecular dynamics and function by detecting nanoscale movements as fluorescence signals. Analysing such signals is a complex exercise, which has recently been the focus of approaches relying on deep learning. Here, we survey such artificial-intelligence-based approaches and compare them with classical methods for smFRET analysis. The use of deep learning has shown potential to enhance precision, accuracy, and speed in analysing massive smFRET datasets.

DeepTRACE brings flexible machine learning to single-molecule track analysis

Communications Biology Nature Research 9:1 (2026) 812

Authors:

Oliver J Pambos, Jacob AR Wright, Achillefs N Kapanidis

Abstract:

Single-molecule imaging was developed to resolve behaviours obscured by ensemble averaging, but early tracking experiments typically captured only brief temporal windows, restricting analysis to individual states rather than the progression between them. Observation times now extend to minutes, revealing complete multi-stage biological processes that require new analytical approaches to capture sequences of events. Here we present DeepTRACE, a flexible tool for analysing single-molecule tracks in living cells that learns sequences of molecular events using past and future context from subcellular location, mobility, and photometric properties. It learns any molecular behaviour that can be annotated with natural-language labels, enabling users to tailor models themselves to specific biological questions without ML expertise. DeepTRACE generalises rapidly from very small datasets, training in minutes on a few hundred tracks, and supports extensive downstream analysis, including discovery of relationships absent from the training data. As DeepTRACE natively handles any numerical feature outside of its standard feature set, it incorporates photometric readouts, including measurements of internal conformation that reflect molecular action, alongside motion, temporal context, and subcellular location. We anticipate that researchers will use DeepTRACE to define biological states by molecular behaviour rather than mobility alone in complex multi-stage processes.

From sequence to function: bridging single-molecule kinetics and molecular diversity

Science American Association for the Advancement of Science 391:6784 (2026) 458-465

Authors:

An Kapanidis, L Muras, K Sreenivasa, Jp Hazra, J van Noort, C Joo, S Deindl

Abstract:

Biological function is fundamentally determined by nucleic acid and protein sequence. Beyond encoding genetic information, nucleic acids also display complex physicochemical parameters that shape structure, dynamics, and interactions. Understanding how sequence variation sculpts the energetic landscapes underlying these properties requires methods that capture both molecular diversity and dynamic behavior. Single-molecule techniques are ideally suited to this task, but conventional formats remain time and cost intensive. Recent breakthroughs have enabled highly multiplexed approaches for observing molecular dynamics across millions of individual molecules representing thousands of sequences or barcoded entities. Though still in development, these methods have begun to bridge sequence, structure, dynamics, and function at scale, opening new opportunities in drug discovery, molecular diagnostics, and functional genomics.

SC-MAPS: a multichannel single-cell microscopy dataset for deep learning-based bacterial species identification and antimicrobial susceptibility testing routing

University of Oxford (2026)

Authors:

Anuj Tiwari, Piers Turner, Christoffer Nellaker, Nicole Stoesser, Achillefs Kapanidis, Conor Feehily

Abstract:

This repository contains the SC-MAPS (Single-Cell Microscopy for Antimicrobial Prediction and Species identification) dataset, a large-scale, multichannel bacterial microscopy resource developed to support deep learning-based bacterial species identification, phenotypic characterisation and classification into antimicrobial susceptibility testing (AST)-routing groups. The dataset is provided as two separate ZIP archives: 1. SC-MAPS Primary Dataset (13 bacterial species) The primary dataset comprises 916,435 segmented single bacterial cells representing 13 clinically relevant bacterial species, collected across 49 species–strain biological replicates. The dataset includes multiple independent strains per species, enabling evaluation of model generalisation to previously unseen strains. Individual bacterial cells were segmented from microscopy images and extracted as standardised 96 × 96-pixel image crops while preserving their native imaging scale. Images were acquired using complementary bright-field, phase-contrast and fluorescence microscopy channels, including DAPI (nucleic acids), WGA-AF647 (cell-envelope-associated structures) and FM1-43 (membrane staining). Multichannel images are stored as NumPy (.npy) arrays for computational analysis. The dataset was used to develop and evaluate convolutional neural network classifiers for bacterial species identification and classification into eight clinically informed AST-routing groups. Training and validation were performed using development strains, while independent strains were reserved for holdout evaluation. 2. SC-MAPS Additional Species Dataset (5 previously unseen species) The second archive contains single-cell microscopy data from five additional bacterial species excluded from the original 13-species model training dataset. These images were processed using the SC-MAPS single-cell extraction workflow and provide an independent resource for investigating model behaviour when encountering organisms outside the training classes. The dataset supports investigations of learned phenotypic representations, cross-species relationships, classification uncertainty and out-of-distribution detection. Dataset Applications Together, these archives provide a resource for developing and benchmarking computational approaches to bacterial identification, multichannel image classification, phenotypic feature extraction, strain-level generalisation, population-level prediction aggregation and open-set recognition. The accompanying SC-MAPS analysis and model-training code is maintained separately on GitHub to facilitate reproducibility and further development of microscopy-based bacterial classification approaches.