Machine Learning Approach to Enhance the Performance of MNP-Labeled Lateral Flow Immunoassay.
Ontology highlight
ABSTRACT:
SUBMITTER: Yan W
PROVIDER: S-EPMC7770769 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The nitrocellulose (NC) membrane based lateral flow immunoassay device (LFID) is one of the most important and widely used biosensor platforms for point-of-care (PoC) diagnostics. However, the analytical performance of LFID has limitations and its optimization is restricted to the bioassay chemistry, the membrane porosity, and the choice of biolabel system. These bottom neck technical issues resulted from the fact that the conventional LFID design principle has not evolved for many years, which limited the LFID for advanced biosensor applications. Here we introduce a new dimension for LFID design and optimization based on geometric flow control (GFC) of NC membranes, leading to highly sensitive GFC-LFID. This novel approach enables comprehensive flow control via different membrane geometric features such as the width (w) and the length (l) of a constriction, as well as its input angle (θ 1) and output angle (θ 2). The GFC-LFID (w=0.5 mm, l=7 mm, θ 1 = 60°, θ 2 = 45°) attained a 10-fold increase in sensitivity for detection of interleukin-6 (IL-6), compared with conventional LFID, whereas reducing by 10-fold the antibody consumption. The GFC-LFID detects IL-6 over a linear range of 0.1-10 ng/mL with a limit of detection (LoD) of 29 pg/mL, which even outperforms some commercial IL-6 LFIDs. Such significant improvement is attained by pure geometric control of the NC membrane, without additives, that only relaying on a simple high throughput laser ablation procedure suitable for integration on regular large-scale manufacturing of GFC-LFIDs. Our new development on GFC-LFID with the combination of facile scalable fabrication process, tailored flow control, improved analytical performance, and reduced antibodies consumption is likely to have a significant impact on new design concept for the LFID industry.
| S-EPMC6750055 | biostudies-literature
Project description:BackgroundLateral flow immunoassays (LFIAs) are being used worldwide for COVID-19 mass testing and antibody prevalence studies. Relatively simple to use and low cost, these tests can be self-administered at home, but rely on subjective interpretation of a test line by eye, risking false positives and false negatives. Here, we report on the development of ALFA (Automated Lateral Flow Analysis) to improve reported sensitivity and specificity.MethodsOur computational pipeline uses machine learning, computer vision techniques and signal processing algorithms to analyse images of the Fortress LFIA SARS-CoV-2 antibody self-test, and subsequently classify results as invalid, IgG negative and IgG positive. A large image library of 595,339 participant-submitted test photographs was created as part of the REACT-2 community SARS-CoV-2 antibody prevalence study in England, UK. Alongside ALFA, we developed an analysis toolkit which could also detect device blood leakage issues.ResultsAutomated analysis showed substantial agreement with human experts (Cohen's kappa 0.90-0.97) and performed consistently better than study participants, particularly for weak positive IgG results. Specificity (98.7-99.4%) and sensitivity (90.1-97.1%) were high compared with visual interpretation by human experts (ranges due to the varying prevalence of weak positive IgG tests in datasets).ConclusionsGiven the potential for LFIAs to be used at scale in the COVID-19 response (for both antibody and antigen testing), even a small improvement in the accuracy of the algorithms could impact the lives of millions of people by reducing the risk of false-positive and false-negative result read-outs by members of the public. Our findings support the use of machine learning-enabled automated reading of at-home antibody lateral flow tests as a tool for improved accuracy for population-level community surveillance.
| S-EPMC9259560 | biostudies-literature
Project description:The level of anti-SARS-CoV-2 neutralizing antibodies (NAb) is an indispensable reference for evaluating the acquired protective immunity against SARS-CoV-2. Here, we established an ultrabright nanoparticles-based lateral flow immunoassay (LFIA) for one-step rapid semi-quantitative detection of anti-SARS-CoV-2 NAb in vaccinee's serum. Once embedded in polystyrene (PS) nanoparticles, the aggregation-induced emission (AIE) luminogen, AIE490, exhibited ultrabright fluorescence due to the rigidity of PS and severe inhibition of intramolecular motions. The ultrabright AIE490-PS nanoparticle was used as a fluorescent marker of LFIA. Upon optimized conditions including incubation time, concentrations of coated proteins and conjugated nanoparticles, amounts of antigens modified on the surface of nanoparticles, dilution rate of serum samples, and so on, the ultrabright nanoparticles-based LFIA could accurately identify 70 negative samples and 63 positive samples from human serum (p < 0.0001). The intra- and inter-assay precisions of the established method are above 13% and 16%, respectively. The established LFIA has tremendous practical value of generalization as a rapid semi-quantitative detection method of anti-SARS-CoV-2 NAb. Meanwhile, the AIE490-PS nanoparticle is also promising to detect many other analytes by altering the protein on the surface.
| S-EPMC9360774 | biostudies-literature
Project description:An outbreak of coronavirus disease (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) poses great threats to human health and the international economy. To reduce large-scale infection and transmission risk of SARS-CoV-2, a simple, rapid, and sensitive serological diagnostic method is urgently needed. Herein, an aggregation-induced emission (AIE) nanoparticle (AIE810NP, λem = 810 nm)-labeled lateral flow immunoassay was designed for early detection of immunoglobulin M (IgM) and immunoglobulin G (IgG) against SARS-CoV-2 in clinical serum samples. Using a near-infrared (NIR) AIE nanoparticle as the fluorescent reporter (△λ = 145 nm), the autofluorescence from the nitrocellulose membrane and biosample and the excitation background noise were effectively eliminated. After optimization, the limit of detection of IgM and IgG is 0.236 and 0.125 μg mL-1, respectively, commensurate with that of the enzyme-linked immunosorbent assay (ELISA) (0.040 and 0.039 μg mL-1). The sensitivity of the proposed AIE810NP-based test strip for detecting IgM and IgG is 78 and 95% (172 serum samples), commensurate with that of ELISA (85 and 95%) and better than that of a commercial colloidal gold nanoparticle (AuNP)-based test strip (41 and 85%). Importantly, the time of detecting IgM or IgG with an AIE810NP-based test strip in sequential clinical samples is 1-7 days after symptom onset, which is significantly earlier than that with a AuNP-based test strip (8-15 days). Therefore, the NIR-emissive AIE nanoparticle-labeled lateral flow immunoassay holds great potential for early detection of IgM and IgG in a seroconversion window period.
| S-EPMC8098771 | biostudies-literature
Project description:The authors describe a gold nanocage-based lateral flow strip biosensor (LFSB) for low-cost and sensitive detection of IgG. This protein was used as a model analyte to demonstrate the proof-of-concept. The method combines the unique optical properties of gold nanocages (GNCs) with highly efficient chromatographic separation. A sandwich-type of immunoreactions occurs on the GNC-based LFSB which has the attractive features of avoiding multiple incubation, separation, and washing steps. The captured GNCs on the purple test zone and control zone of the biosensor are producing characteristic purple bands, and this enables IgG even to be visually detected. Quantitatation was accomplished by reading the intensities of the bands with a portable strip reader. The LFSB fabrication and assay parameters were optimized. The biosensor displays a linear response in the 0.5 to 50 ng·mL-1 IgG concentration range, and it has a 15 min assay time. The detection limit is 0.1 ng·mL-1 of IgG, which is 2.5 times lower than that when using a gold nanoparticle-based LFSB. In our perception, this assay has a wide potential for the detection of other proteins and species for which respective antibodies are available.
| S-EPMC5703415 | biostudies-literature
Project description:The parasitic disease onchocerciasis is the second leading cause of preventable blindness, afflicting more than 18 million people worldwide. Despite an available treatment, ivermectin, and control efforts by the World Health Organization, onchocerciasis remains a burden in many regions. With an estimated 120 million people living in areas at risk of infection, efforts are now shifting from prevention to surveillance and elimination. The lack of a robust, point-of-care diagnostic for an active Onchocerca infection has been a limiting factor in these efforts. Previously, we reported the discovery of the biomarker N-acetyl-tyramine- O-glucuronide (NATOG) in human urine samples and its ability to track treatment progression between medicated patients relative to placebo; we also established its capability to monitor disease burden in a jird model. NATOG is a human-produced metabolite of tyramine, which itself is produced as a nematode neurotransmitter. The ability of NATOG to distinguish between active and past infection overcomes the limitations of antibody biomarkers and PCR methodologies. Lateral flow immunoassay (LFIA) diagnostics offer the versatility and simplicity to be employed in the field and are inexpensive enough to be utilized in large-scale screening efforts. Herein, we report the development and assessment of a NATOG-based urine LFIA for onchocerciasis, which accurately identified 85% of analyzed patient samples ( N = 27).
| S-EPMC6189908 | biostudies-literature
Project description:Aminoglycosides belong to a class of antibiotics now widely used in agriculture and veterinary medicine and expected to contaminate food products. In this study, a sensitive lateral flow immunoassay (LFIA) of an aminoglycoside neomycin (NEO) was developed. Two methods of immunochromatographic detection based on various techniques of gold nanoparticles (AuNPs) introduction as a label were compared. It was demonstrated that the indirect labeling (a conjugation of anti-species antibodies with a marker) allowed for an increase in assay sensitivity by 80 times. The test system was characterized by an instrumental limit of detection of 0.1 ng/mL and the cutoff level of 10 ng/mL; the assay duration was 15 min. Specificity only toward NEO was demonstrated. The developed LFIA has been tested to detect NEO in different foodstuffs. It has been demonstrated that 70-119% of NEO (coefficients of variations < 10%) can be determined in milk, turkey meat, honey, and eggs using simple procedures of preliminary sample preparation. Testing the samples showed the coincidence of the results for the developed lateral flow assay and for commercial ELISA kit.
| S-EPMC7813914 | biostudies-literature
Project description:Recent developments in smartphone-based strip readers have further improved the performances of lateral flow test kits. Most smartphone cameras encode an unaltered and nonlinear power-law transfer function that maps the light intensity to a pixel value; this poses some limitations for camera-based strip readers. For faint-color test lines which are almost as white such as with nitrocellulose pads, the slope of the transfer function is low. Therefore, it is difficult to differentiate between the faint test lines and the white background. We show that by manually setting the camera exposure time-instead of using the automatic settings-to the high-slope region of the transfer function, the reader's sensitivity can be improved. We found that the sensitivity and the limit of detection of the Acidovorax avenae subsp. citrulli (Aac) test kit were enhanced up to 3-fold and 5-fold, respectively, when using the readers at the optimal camera settings, compared to the automatic mode settings. This simple technique can be readily applied to any existing camera-based colorimetric strip reader to significantly improve its performance.
| S-EPMC6263405 | biostudies-literature
Project description:ObjectivesWe validate the use of a lateral flow immunoassay (LFI) intended for rapid screening and qualitative detection of anti-SARS-CoV-2 IgM and IgG in serum, plasma, and whole blood, and compare results with ELISA. We also seek to establish the value of LFI testing on blood obtained from a capillary blood sample.MethodsSamples collected by venous blood draw and finger stick were obtained from patients with SARS-CoV-2 detected by RT-qPCR and control patients. Samples were tested with Biolidics 2019-nCoV IgG/IgM Detection Kit lateral flow immunoassay, and antibody calls were compared with ELISA.ResultsBiolidics LFI showed clinical sensitivity of 92% with venous blood at 7 days after PCR diagnosis of SARS-CoV-2. Test specificity was 92% for IgM and 100% for IgG. There was no significant difference in detecting IgM and IgG with Biolidics LFI and ELISA at D0 and D7 (p = 1.00), except for detection of IgM at D7 (p = 0.04). Capillary blood of SARS-CoV-2 patients showed 93% sensitivity for antibody detection.ConclusionsClinical performance of Biolidics 2019-nCoV IgG/IgM Detection Kit is comparable to ELISA and was consistent across sample types. This provides an opportunity for decentralized rapid testing and may allow point-of-care and longitudinal self-testing for the presence of anti-SARS-CoV-2 antibodies.
| S-EPMC7647890 | biostudies-literature
Project description:The modulation of protein-protein interactions (PPIs) by small chemical compounds is challenging. PPIs play a critical role in most cellular processes and are involved in numerous disease pathways. As such, novel strategies that assist the design of PPI inhibitors are of major importance. We previously reported that the knowledge-based DLIGAND2 scoring tool was the best-rescoring function for improving receptor-based virtual screening (VS) performed with the Surflex docking engine applied to several PPI targets with experimentally known active and inactive compounds. Here, we extend our investigation by assessing the vs. potential of other types of scoring functions with an emphasis on docking-pose derived solvent accessible surface area (SASA) descriptors, with or without the use of machine learning (ML) classifiers. First, we explored rescoring strategies of Surflex-generated docking poses with five GOLD scoring functions (GoldScore, ChemScore, ASP, ChemPLP, ChemScore with Receptor Depth Scaling) and with consensus scoring. The top-ranked poses were post-processed to derive a set of protein and ligand SASA descriptors in the bound and unbound states, which were combined to derive descriptors of the docked protein-ligand complexes. Further, eight ML models (tree, bagged forest, random forest, Bayesian, support vector machine, logistic regression, neural network, and neural network with bagging) were trained using the derivatized SASA descriptors and validated on test sets. The results show that many SASA descriptors are better than Surflex and GOLD scoring functions in terms of overall performance and early recovery success on the used dataset. The ML models were superior to all scoring functions and rescoring approaches for most targets yielding up to a seven-fold increase in enrichment factors at 1% of the screened collections. In particular, the neural networks and random forest-based ML emerged as the best techniques for this PPI dataset, making them robust and attractive vs. tools for hit-finding efforts. The presented results suggest that exploring further docking-pose derived SASA descriptors could be valuable for structure-based virtual screening projects, and in the present case, to assist the rational design of small-molecule PPI inhibitors.
| S-EPMC9694378 | biostudies-literature