Artificial intelligence-enabled quantitative phase imaging methods for life sciences

Nature Methods, Journal Year: 2023, Volume and Issue: 20(11), P. 1645 - 1660

Published: Oct. 23, 2023

Language: Английский

---

Generalized and scalable trajectory inference in single-cell omics data with VIA

Nature Communications, Journal Year: 2021, Volume and Issue: 12(1)

Published: Sept. 20, 2021

Inferring cellular trajectories using a variety of omic data is critical task in single-cell science. However, accurate prediction cell fates, and thereby biologically meaningful discovery, challenged by the sheer size data, diversity types, complexity their topologies. We present VIA, scalable trajectory inference algorithm that overcomes these limitations lazy-teleporting random walks to accurately reconstruct complex beyond tree-like pathways (e.g., cyclic or disconnected structures). show VIA robustly efficiently unravels fine-grained sub-trajectories 1.3-million-cell transcriptomic mouse atlas without losing global connectivity at such high count. further apply discovering elusive lineages less populous fates missed other methods across including proteomic, epigenomic, multi-omics datasets, new in-house morphological dataset.

Language: Английский

---

Microsystem Advances through Integration with Artificial Intelligence

Micromachines, Journal Year: 2023, Volume and Issue: 14(4), P. 826 - 826

Published: April 8, 2023

Microfluidics is a rapidly growing discipline that involves studying and manipulating fluids at reduced length scale volume, typically on the of micro- or nanoliters. Under larger surface-to-volume ratio, advantages low reagent consumption, faster reaction kinetics, more compact systems are evident in microfluidics. However, miniaturization microfluidic chips introduces challenges stricter tolerances designing controlling them for interdisciplinary applications. Recent advances artificial intelligence (AI) have brought innovation to microfluidics from design, simulation, automation, optimization bioanalysis data analytics. In microfluidics, Navier-Stokes equations, which partial differential equations describing viscous fluid motion complete form known not general analytical solution, can be simplified fair performance through numerical approximation due inertia laminar flow. Approximation using neural networks trained by rules physical knowledge new possibility predict physicochemical nature. The combination automation produce large amounts data, where features patterns difficult discern human extracted machine learning. Therefore, integration with AI potential revolutionize workflow enabling precision control analysis. Deployment smart may tremendously beneficial various applications future, including high-throughput drug discovery, rapid point-of-care-testing (POCT), personalized medicine. this review, we summarize key integrated discuss outlook possibilities combining

Language: Английский

---

AI-Powered Microfluidics: Shaping the Future of Phenotypic Drug Discovery

ACS Applied Materials & Interfaces, Journal Year: 2024, Volume and Issue: 16(30), P. 38832 - 38851

Published: July 17, 2024

Phenotypic drug discovery (PDD), which involves harnessing biological systems directly to uncover effective drugs, has undergone a resurgence in recent years. The rapid advancement of artificial intelligence (AI) over the past few years presents numerous opportunities for augmenting phenotypic screening on microfluidic platforms, leveraging its predictive capabilities, data analysis, efficient processing, etc. Microfluidics coupled with AI is poised revolutionize landscape discovery. By integrating advanced platforms algorithms, researchers can rapidly screen large libraries compounds, identify novel candidates, and elucidate complex pathways unprecedented speed efficiency. This review provides an overview advances challenges AI-based microfluidics their applications We discuss synergistic combination high-throughput AI-driven analysis phenotype characterization, drug-target interactions, modeling. In addition, we highlight potential AI-powered achieve automated system. Overall, represents promising approach shaping future by enabling rapid, cost-effective, accurate identification therapeutically relevant compounds.

Language: Английский

---

Morphological profiling by high-throughput single-cell biophysical fractometry

Communications Biology, Journal Year: 2023, Volume and Issue: 6(1)

Published: April 24, 2023

Abstract Complex and irregular cell architecture is known to statistically exhibit fractal geometry, i.e., a pattern resembles smaller part of itself. Although variations in cells are proven be closely associated with the disease-related phenotypes that otherwise obscured standard cell-based assays, analysis single-cell precision remains largely unexplored. To close this gap, here we develop an image-based approach quantifies multitude biophysical fractal-related properties at subcellular resolution. Taking together its high-throughput imaging performance (~10,000 cells/sec), technique, termed fractometry, offers sufficient statistical power for delineating cellular heterogeneity, context lung-cancer subtype classification, drug response assays cell-cycle progression tracking. Further correlative shows fractometry can enrich morphological profiling depth spearhead systematic how morphology encodes health pathological conditions.

Language: Английский

---

Light Scattering Imaging Modal Expansion Cytometry for Label-free Single-cell Analysis with Deep Learning

Computer Methods and Programs in Biomedicine, Journal Year: 2025, Volume and Issue: 264, P. 108726 - 108726

Published: March 15, 2025

Language: Английский

---

Information‐Distilled Generative Label‐Free Morphological Profiling Encodes Cellular Heterogeneity

Advanced Science, Journal Year: 2024, Volume and Issue: 11(29)

Published: June 12, 2024

Abstract Image‐based cytometry faces challenges due to technical variations arising from different experimental batches and conditions, such as differences in instrument configurations or image acquisition protocols, impeding genuine biological interpretation of cell morphology. Existing solutions, often necessitating extensive pre‐existing data knowledge control samples across batches, have proved limited, especially with complex data. To overcome this, “Cyto‐Morphology Adversarial Distillation” (CytoMAD), a self‐supervised multi‐task learning strategy that distills biologically relevant cellular morphological information batch variations, is introduced enable integrated analysis multiple without assumptions manual annotation. Unique CytoMAD its “morphology distillation”, symbiotically paired deep‐learning image‐contrast translation—offering additional interpretable insights into label‐free The versatile efficacy demonstrated augmenting the power biophysical imaging cytometry. It allows classification human lung cancer types accurately recapitulates their progressive drug responses, even when trained concentration information. also joint tumor heterogeneity, linked epithelial‐mesenchymal plasticity, standard fluorescence markers overlook. can substantiate wide adoption for cost‐effective diagnosis screening.

Language: Английский

---

Automated Classification of Breast Cancer Cells Using High-Throughput Holographic Cytometry

Frontiers in Physics, Journal Year: 2021, Volume and Issue: 9

Published: Nov. 30, 2021

Holographic cytometry is an ultra-high throughput quantitative phase imaging modality that capable of extracting subcellular information from millions cells flowing through parallel microfluidic channels. In this study, we present our findings on the application holographic to distinguishing carcinogen-exposed normal and cancer cells. This has potential for environmental monitoring detection by analysis cytology samples acquired via brushing or fine needle aspiration. By leveraging vast amount cell data, are able build single-cell-analysis-based biophysical phenotype profiles examined lines. Multiple physical characteristics these show observable distinct traits between three types. Logistic regression provides insight which more useful classification. Additionally, demonstrate deep learning a powerful tool can potentially identify phenotypic differences reconstructed single-cell images. The high classification accuracy levels platform’s in being developed into diagnostic abnormal screening.

Language: Английский

---

Label‐free multiphoton imaging flow cytometry

Cytometry Part A, Journal Year: 2023, Volume and Issue: 103(7), P. 584 - 592

Published: Feb. 17, 2023

Abstract Label‐free imaging flow cytometry is a powerful tool for biological and medical research as it overcomes technical challenges in conventional fluorescence‐based that predominantly relies on fluorescent labeling. To date, two distinct types of label‐free have been developed, namely optofluidic time‐stretch quantitative phase stimulated Raman scattering (SRS) cytometry. Unfortunately, these methods are incapable probing some important molecules such starch collagen. Here, we present another type cytometry, multiphoton visualizing collagen live cells with high throughput. Our cytometer based nonlinear optical whose image contrast provided by effects: four‐wave mixing (FWM) second‐harmonic generation (SHG). It composed microfluidic chip an acoustic focuser, lab‐made laser scanning SHG‐FWM microscope, high‐speed acquisition circuit to simultaneously acquire FWM SHG images flowing cells. As result, acquires (100 × 100 pixels) spatial resolution 500 nm field view 50 μm at event rate four five events per second, corresponding throughput 560–700 kb/s, where the defined passage cell or cell‐like particle. show utility our cytometer, used characterize Chromochloris zofingiensis (NIES‐2175), unicellular green alga has recently attracted attention from industrial sector its ability efficiently produce valuable materials bioplastics, food, biofuel. statistical analysis found was distributed center early cycle stage became delocalized later stage. Multiphoton expected be effective high‐content studies functions optimizing evolution highly productive strains.

Language: Английский

---

Biophysical Profiling of Sickle Cell Disease Using Holographic Cytometry and Deep Learning

International Journal of Molecular Sciences, Journal Year: 2023, Volume and Issue: 24(15), P. 11885 - 11885

Published: July 25, 2023

Sickle cell disease (SCD) is an inherited hematological disorder associated with high mortality rates, particularly in sub-Saharan Africa. SCD arises due to the polymerization of sickle hemoglobin, which reduces flexibility red blood cells (RBCs), causing vessel occlusion and leading severe morbidity early rates if untreated. While solubility tests are available African population as a means for detecting hemoglobin (HbS), test falls short assessing severity visualizing degree cellular deformation. Here, we propose use holographic cytometry (HC), throughput, label-free imaging modality, comprehensive morphological profiling RBCs detect SCD. For this study, more than 2.5 million single-cell images from normal patient samples were collected using HC system. We have developed approach specially defining training data improve machine learning classification. demonstrate deep classifier can produce highly accurate classification, even on unknown samples.

Language: Английский

---