KEYWORDS: Machine learning, Proteins, Data modeling, Deep learning, Genetics, Performance modeling, Ion channels, Education and training, Matrices, Signal processing
Machine learning is a powerful technique for analysing large-scale data and learning patterns, which provides high accuracy and shorter processing times. In this work, a machine learning algorithm (multinomial logistic regression) is used to predict the gene families from a human DNA sequence. 4380 sequences were converted into overlapping k-mers of length 6 to produce 232 414 k-mers. The data set was split into 80/20 train and test datasets, and the multinomial logistic regression model achieved a 93.9% accuracy in predicting 6 gene families within 0.24 seconds. The model was 94.8% precise, 93.9% sensitive, and had an f1-score of 94%. The developed model in this study offers an alternative approach for medical professionals to gain insights into genetic information carried within DNA segments. By leveraging machine learning techniques, accurate and efficient predictions of gene families can aid in understanding genetic characteristics and contribute to advancements in personalised medicine, diagnostics and genetic research.
The rapid and accurate detection of infectious diseases like HIV, COVID-19, and TB is crucial for effective public health initiatives. We demonstrate a transformative approach in TB detection through a simulated Loop-Mediated Isothermal Amplification (LAMP) assay. This computational model was trained using established LAMP protocols and evaluated under varying conditions, including template and primer concentrations and cycling conditions, showing robust performance. Simulated results were used to optimise the LAMP protocol, reducing the time and resources required. The study opens avenues for cost-effective, rapid, and precise diagnosis of infectious diseases. Future work will focus on expanding the model to other infectious diseases and integrating it into real-world diagnostic workflows.
Timely and effective detection of COVID-19 continues to be a critical aspect in managing the pandemic and setting the groundwork for future pathogen detection techniques. Present diagnostic technologies, especially those designed for POC (Point of Care) use in resource-constrained settings, must meet the evolving needs for rapidity, accuracy, and affordability. Within this context, preparing for pandemics necessitates the development of swift POC diagnostics. This research investigates the potential of the Arduino-driven LAMP (Loop-Mediated Isothermal Amplification) method for SARS-CoV-2 detection. An inexpensive, accessible, and portable "LAMP box" is proposed in this study, integrating the LAMP assay with an Arduino to create a potentially effective detection system for COVID-19. The device features a wireless technology network connecting all components. The reaction is performed at 65°C on an isothermal heating pad located beneath a solid aluminum base, providing a stable platform for reaction tubes and assays. Control of the entire system, powered via a 5-volt USB source, is provided through a built-in Bluetooth connection linked to an Arduino, facilitating control through a computer. The study concludes that such simple systems can effectively determine the presence or absence of artificial SARS-CoV-2 genetic material in samples. The presented research underscores the promise of Arduino-based LAMP technology, showcasing its specificity and sensitivity compared to the conventional RT-PCR (Reverse Transcription Polymerase Chain Reaction).
Surface plasmon resonance (SPR) is an optical phenomenon used for detecting various biological substances and disease diagnostics due to its high sensitivity. SPR-based biosensors are highly sensitive optical devices and rapid detection devices, and they also have the added advantage of being label-free biosensors. Sensitivity and limit of detection are critical parameters in studying the performance of any biosensor. In plasmonic biosensors, the sensitivity and limit of detection are dependent on several parameters and a sensitivity analysis is critical to determine these parameters which can optimize our biosensor performance. Sensitivity analyses of SPR-based biosensors are important for enhancing the limit of detection (LoD), comparing performance, optimizing biosensor design, ensuring quality control, and advancing biosensing technology. In this study, we theoretically perform a sensitivity analysis on an SPR-based biosensor and consider different ways to enhance the LoD of the biosensor. The interaction we study is that of different proteins binding to gold (Au) surfaces via an electrostatic mechanism. In this study, we vary a wide range of parameters ranging from metal film thickness, and wavelengths of light incident on the biosensor and show how these parameters can be used to optimize our plasmonic biosensor in terms of sensitivity and LoD. The development of optimal biosensors is ever more critical, particularly considering recurring pandemics and disease outbreaks. Good sensitivity analysis can lead to high quality and highly effective biosensors which can be useful in the fight against disease outbreaks and pandemics.
Human immunodeficiency virus type 1 (HIV-1) is the causative agent of acquired immunodeficiency syndrome (AIDS), a severe infectious disease that has resulted in millions of deaths worldwide. Timely and accurate diagnosis of HIV-1 is crucial in reducing mortality rates associated with AIDS. In this study, we propose a real-time detection method for HIV-1 using an absorbance technique. Specifically, we compare the absorbance properties of three different biosensor surfaces: one coated with 10 nm titanium (Ti) the other coated with 50 nm gold (Au), and the other consisting of an uncoated glass slide. The gold-coated slide is preferred over the silver-coated slide because gold metal is considerably stable under testing conditions. In a quest to detect HIV-1, the glass, gold-coated and titanium-coated slides were successfully functionalized with relevant silanes (GMBS/3MPTS). To study the absorbance kinetics of the optical biosensor, we employ low-power light. As HIV-1 binds to the antibody on the surface, the binding interaction influences the absorbance of light as the sample passes through the functionalized surface. By monitoring the absorbance, we can deduce the capabilities of either Au, Ti, or Glass to detect the HIV-1 virus. By conducting this research, we aim to evaluate the efficacy of the Ti and Au-coated biosensor surface and consequently compare it to the uncoated glass slide on performance in detecting HIV-1 virus. The results provide insights into the performance of the biosensor with a specific metal for HIV-1 detection. This study contributes to the development of improved diagnostic tools for early HIV-1 diagnosis, ultimately aiding in the reduction of mortality rates associated with AIDS.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.