Deep Learning for Predicting Gene Regulatory Networks: A Step-by-Step Protocol in R.

Deep learning has emerged as a powerful tool for solving complex problems, including reconstruction of gene regulatory networks within the realm of biology. These networks consist of transcription factors and their associations with genes they regulate. Despite the utility of deep learning methods in studying gene expression and regulation, their accessibility remains limited for biologists,  mainly due to the prerequisites of programming skills and a nuanced grasp of the underlying algorithms. This chapter presents a deep learning protocol that utilize TensorFlow and the Keras API in R/RStudio, with the aim of making deep learning accessible for individuals without specialized expertise. The protocol focuses on the genome-wide prediction of regulatory interactions between transcription factors and genes, leveraging publicly available gene expression data in conjunction with well-established benchmarks. The protocol encompasses pivotal phases including data preprocessing, conceptualization of neural network architectures, iterative processes of model training and validation, as well as forecasting of novel regulatory associations. Furthermore, it provides insights into parameter tuning for deep learning models. By adhering to this protocol, researchers are expected to gain a comprehensive understanding of applying deep learning techniques to predict regulatory interactions. This protocol can be readily modifiable to serve diverse research problems, thereby empowering scientists to effectively harness the capabilities of deep learning in their investigations.

All-in-one nanoflare biosensor combined with catalyzed hairpin assembly amplification for in situ and sensitive exosomal miRNA detection and cancer classification.

Exosomal miRNAs can reflect tumor progression and metastasis, and are effective biomarkers for cancer diagnosis. However, the accuracy of exosomal miRNA-based cancer diagnosis is limited by the low sensitivity and complicated RNA extraction of traditional approaches. Herein, a novel biosensor is developed for in situ, extraction-free, and highly sensitive analysis of exosomal miRNAs via nanoflare combined with catalyzed hairpin assembly (CHA) amplification. Without cumbersome and costly miRNA extraction or transfection agents, nanoflare can directly enter the exosomes to bind target miRNAs and generate a fluorescence signal that can be amplified by the CHA reaction to achieve the in situ and highly sensitive detection of exosomal miRNAs. Under the optimal conditions, the detection limit of 5 aM is obtained for three exosomal miRNAs, which is an order of magnitude lower than quantitative real time polymerase chain reaction (qRT-PCR). In combination with the linear discriminant analysis algorithm, five exosomes are distinguished with 100% accuracy. Importantly, five cancers including breast, lung, liver, cervical, and colon cancer from 64 patients are distinguished with 99% accuracy by testing exosomal miRNAs in clinical plasma. This simple, accurate, and sensitive biosensor holds the potential to be expanded into clinical non-invasive cancer diagnostic tests.

Colorimetric sensor array combined with chemometric methods for the assessment of aroma produced during the drying of tencha.

The aroma produced during drying is an important indicator of tencha and needs to be monitored. This study constructed an olfactory visualization system for assessing tencha aroma using colorimetric sensor array (CSA) combined with chemometric methods. The 16 chemically responsive dyes were selected to obtain aroma information of tencha samples and extracted image data of aroma information by machine vision algorithms. Subsequently, k-nearest neighbor, support vector machine, classification and regression tree, and random forest (RF), four qualitative models were applied to build the mathematical models. The RF model with nine principal components was preferred, with recognition rate of 100.00% and 91.07% for the training and prediction sets, respectively. The experimental results showed that CSA combined with the RF model can be effectively applied to assess tencha aroma. This study provided a scientific and novel method to maintain the stability of tencha quality in the production process.

Computer-Aided Drug Discovery and Design: Recent Advances and Future Prospects.

Computer-aided drug discovery and design involve the use of information technologies to identify and develop, on a rational ground, chemical compounds that align a set of desired physicochemical and biological properties. In its most common form, it involves the identification and/or modification of an active scaffold (or the combination of known active scaffolds), although de novo drug design from scratch is also possible. Traditionally, the drug discovery and design processes have focused on the molecular determinants of the interactions between drug candidates and their known or intended pharmacological target(s). Nevertheless, in modern times, drug discovery and design are conceived as a particularly complex multiparameter optimization task, due to the complicated, often conflicting, property requirements.This chapter provides an updated overview of in silico approaches for identifying active scaffolds and guiding the subsequent optimization process. Recent groundbreaking advances in the field have also analyzed the integration of state-of-the-art machine learning approaches in every step of the drug discovery process (from prediction of target structure to customized molecular docking scoring functions), integration of multilevel omics data, and the use of a diversity of computational approaches to assist target validation and assess plausible binding pockets.

Mining Chemogenomic Spaces for Prediction of Drug-Target Interactions.

The pipeline of drug discovery consists of a number of processes; drug-target interaction determination is one of the salient steps among them. Computational prediction of drug-target interactions can facilitate in reducing the search space of experimental wet lab-based verifications steps, thus considerably reducing time and other resources dedicated to the drug discovery pipeline. While machine learning-based methods are more widespread for drug-target interaction prediction, network-centric methods are also evolving. In this chapter, we focus on the process of the drug-target interaction prediction from the perspective of using machine learning algorithms and the various stages involved for developing an accurate predictor.

A New Optimized Hybridization Approach for in silico High Throughput Molecular Docking on FPGA Platform.

BACKGROUND: The development process of a new drug should be a subject of continuous evolution and rapid improvement as drugs are essential to treat a wide range of diseases of which many are life-threatening. The advances in technology resulted in a novel track in drug discovery and development known as in silico drug design. The molecular docking phase plays a vital role in in silico drug development process. In this phase, thousands of 3D conformations of both the ligand and receptor are generated and the best conformations that create the most stable drug-receptor complex are determined. The speed in finding accurate and high-quality complexes depends on the efficiency of the search function in the molecular docking procedure. OBJECTIVE: The objective of this research is to propose and implement a novel hybrid approach called hABCDE to replace the EMC searching part inside the BUDE docking algorithm. This helps in reaching the best solution in a much accelerated time and higher solution quality compared to using the ABC and DE algorithms separately. METHODS: In this work, we have employed a new approach of hybridization between the Artificial Bee Colony (ABC) algorithm and the Differential Evolution (DE) algorithm as an alternative searching part of the Bristol University Docking Engine (BUDE) in order to accelerate the search for higher quality solutions. Moreover, the proposed docking approach was implemented on Field Programmable Gate Array (FPGA) parallel platform using Vivado High-Level Synthesis Tool (HLST) in order to optimize and enhance the execution time and overall efficiency. The NDM-1 protein was used as a model receptor in our experiments to demonstrate the efficiency of our approach. RESULTS: The NDM-1 protein was used as a model receptor in our experiments to demonstrate the efficiency of our approach. The results showed that the execution time for the BUDE with the new proposed hybridization approach was improved by 9,236 times. CONCLUSION: Our novel approach was significantly effective to improve the functionality of docking algorithms (Bristol University Docking Engine (BUDE)).

A Review on Retinal Blood Vessel Enhancement and Segmentation Techniques for Color Fundus Photography.

The retinal image is a trusted modality in biomedical image-based diagnosis of many ophthalmologic and cardiovascular diseases. Periodic examination of the retina can help in spotting these abnormalities in the early stage. However, to deal with today's large population, computerized retinal image analysis is preferred over manual inspection. The precise extraction of the retinal vessel is the first and decisive step for clinical applications. Every year, many more articles are added to the literature that describe new algorithms for the problem at hand. The majority of the review article is restricted to a fairly small number of approaches, assessment indices, and databases. In this context, a comprehensive review of different vessel extraction methods is inevitable. It includes the development of a first-hand classification of these methods. A bibliometric analysis of these articles is also presented. The benefits and drawbacks of the most commonly used techniques are summarized. The primary challenges, as well as the scope of possible changes, are discussed. In order to make a fair comparison, numerous assessment indices are considered. The findings of this survey could provide a new path for researchers for further work in this domain.

Structured low-rank reconstruction for navigator-free water/fat separated multi-shot diffusion-weighted EPI.

PURPOSE: Multi-shot diffusion-weighted EPI allows an increase in image resolution and reduced geometric distortions and can be combined with chemical-shift encoding (Dixon) to separate water/fat signals. However, such approaches suffer from physiological motion-induced shot-to-shot phase variations. In this work, a structured low-rank-based navigator-free algorithm is proposed to address the challenge of simultaneously separating water/fat signals and correcting for physiological motion-induced shot-to-shot phase variations in multi-shot EPI-based diffusion-weighted MRI. THEORY AND METHODS: We propose an iterative, model-based reconstruction pipeline that applies structured low-rank regularization to estimate and eliminate the shot-to-shot phase variations in a data-driven way, while separating water/fat images. The algorithm is tested in different anatomies, including head-neck, knee, brain, and prostate. The performance is validated in simulations and in-vivo experiments in comparison to existing approaches. RESULTS: In-vivo experiments and simulations demonstrated the effectiveness of the proposed algorithm compared to extra-navigated and an alternative self-navigation approach. The proposed algorithm demonstrates the capability to reconstruct in the multi-shot/Dixon hybrid space domain under-sampled datasets, using the same number of acquired EPI shots compared to conventional fat-suppression techniques but eliminating fat signals through chemical-shift encoding. In addition, partial Fourier reconstruction can also be achieved by using the concept of virtual conjugate coils in conjunction with the proposed algorithm. CONCLUSION: The proposed algorithm effectively eliminates the shot-to-shot phase variations and separates water/fat images, making it a promising solution for future DWI on different anatomies.

Optimization of 3D dynamic speech MRI: Poisson-disc undersampling and locally higher-rank reconstruction through partial separability model with regional optimized temporal basis.

PURPOSE: To improve the spatiotemporal qualities of images and dynamics of speech MRI through an improved data sampling and image reconstruction approach. METHODS: For data acquisition, we used a Poisson-disc random under sampling scheme that reduced the undersampling coherence. For image reconstruction, we proposed a novel locally higher-rank partial separability model. This reconstruction model represented the oral and static regions using separate low-rank subspaces, therefore, preserving their distinct temporal signal characteristics. Regional optimized temporal basis was determined from the regional-optimized virtual coil approach. Overall, we achieved a better spatiotemporal image reconstruction quality with the potential of reducing total acquisition time by 50%. RESULTS: The proposed method was demonstrated through several 2-mm isotropic, 64 mm total thickness, dynamic acquisitions with 40 frames per second and compared to the previous approach using a global subspace model along with other k-space sampling patterns. Individual timeframe images and temporal profiles of speech samples were shown to illustrate the ability of the Poisson-disc under sampling pattern in reducing total acquisition time. Temporal information of sagittal and coronal directions was also shown to illustrate the effectiveness of the locally higher-rank operator and regional optimized temporal basis. To compare the reconstruction qualities of different regions, voxel-wise temporal SNR analysis were performed. CONCLUSION: Poisson-disc sampling combined with a locally higher-rank model and a regional-optimized temporal basis can drastically improve the spatiotemporal image quality and provide a 50% reduction in overall acquisition time.

A novel chlorophyll-a retrieval model based on suspended particulate matter classification and different machine learning.

Chlorophyll-a (Chla) in inland waters is one of the most significant optical parameters of aquatic ecosystem assessment, and long-term and daily Chla concentration monitoring has the potential to facilitate in early warning of algal blooms. MOD09 products have multiple observation advantages (higher temporal, spatial resolution and signal-to-noise ratio), and play an extremely important role in the remote sensing of water color. For developing a high accuracy machine learning model of remotely estimating Chla concentration in inland waters based on MOD09 products, this study proposed an assumption that the accuracy of Chla concentration retrieval will be improved after classifying water bodies into three groups by suspended particulate matter (SPM) concentration. A total of 10 commonly used machine learning models were compared and evaluated in this study, including random forest regressor (RFR), deep neural networks (DNN), extreme gradient boosting (XGBoost), and convolutional neural network (CNN). Altogether, 41 basic bands and 820 band ratios between the 41 bands were filtered by measuring their correlation with Ln(Chla) and several bands brought into different machine learning models. Results demonstrated that the construction of Chla concentration remote estimation model based on SPM classification could significantly improve the correlation between Ln(Chla) and 41 basic spectral band combinations, the correlation between Ln(Chla) and 820 band ratios, and the model verification R2 from 0.41 to 0.83. Furthermore, B3, B20, and B32 were finally selected based on correlation with SPM to classify SPM and the classification accuracy could reach 0.9. Finally, we concluded that RFR model performed best via comparing the R2, RMSE, and MAPE. By comparing the relative contribution of input bands in different groups, B3 contributed most to three groups. The model constructed in this study has promising prospects for promotion and application in other inland waters, and could provide systematic research reference for subsequent research.

Alternating Look-Locker for quantitative T1 , T1ρ and B1 3D MRI mapping.

PURPOSE: To develop a new MRI method, entitled alternating Look-Locker (aLL), for quantitative T 1 $$ {T}_1 $$ , T 1 ρ $$ {T}_{1\uprho} $$ , and B 1 $$ {B}_1 $$ 3D mapping. METHODS: A Look-Locker scheme that alternates magnetization from +Z and -Z axes of the laboratory frame is utilized in combination with a 3D Multi-Band Sweep Imaging with Fourier Transformation (MB-SWIFT) readout. The analytical solution describing the spin evolution during aLL, as well as the correction required for segmented acquisition were derived. The simultaneous B 1 $$ {B}_1 $$ and T 1 $$ {T}_1 $$ mapping are demonstrated on an agar/saline phantom and on an in-vivo rat head. T 1 ρ $$ {T}_{1\uprho} $$ relaxation was achieved by cyclically applying magnetization preparation (MP) modules consisting of two adiabatic pulses. T 1 ρ $$ {T}_{1\uprho} $$ values in the rat brain in-vivo and in a gadobenate dimeglumine (Gd-DTPA) phantom were compared to those obtained with a previously introduced steady-state (SS) method. RESULTS: The accuracy and precision of the analytical solution was tested by Bloch simulations. With the application of MP modules, the aLL method provides simultaneous T 1 $$ {T}_1 $$ and T 1 ρ $$ {T}_{1\uprho} $$ maps. Conversely, without it, the method can be used for simultaneous T 1 $$ {T}_1 $$ and B 1 $$ {B}_1 $$ mapping. T 1 ρ $$ {T}_{1\uprho} $$ values were similar with both aLL and SS techniques. However, the aLL method resulted in more robust quantitative mapping compared to the SS method. Unlike the SS method, the aLL method does not require additional scans for generating T 1 $$ {T}_1 $$ maps. CONCLUSION: The proposed method offers a new flexible tool for quantitative mapping of T 1 $$ {T}_1 $$ , T 1 ρ $$ {T}_{1\uprho} $$ , and B 1 $$ {B}_1 $$ . The aLL method can also be used with readout schemes different from MB-SWIFT.

Ultrasound Plane-Wave Compressed Sensing Reconstruction Method Using Intra-frame and Inter-frame Joint Multi-hypothesis and Reference Frame Multi-hypothesis Predictions.

OBJECTIVE: Ultrasound plane-wave imaging has the advantage of high frame rate in addition to high data volume. High data sampling rates and large amounts of data storage can become bottlenecks in ultrasound system design. Although compressed sensing technology can help reduce the burden of sampling and transmission, it achieves relatively low image quality because of its reliance solely on signal sparsity. Therefore, we proposed reconstructing the ultrasound signal by applying additional prior knowledge, such as plane-wave imaging and its echo characteristics. METHODS: Inspired by multi-hypothesis prediction methods in video compression coding, the plane-wave multi-hypothesis prediction compressed sensing reconstruction method was proposed to improve the accuracy of reconstructions. We applied multi-hypothesis prediction and residual reconstruction on the plane wave to enhance the quality of reconstruction and correct predicted values. Also, to acquire high-quality hypotheses, two hypothesis acquisition schemes were evaluated, constructing search windows on both preceding and subsequent frames as well as the reference frame. RESULTS: Compared with traditional reconstruction methods that rely on sparsity, multi-hypothesis prediction compressed sensing methods can reduce signal reconstruction errors and significantly eliminate image artifacts. Furthermore, by using improved hypotheses, signal reconstruction and image quality can be enhanced, resulting in higher contrast. CONCLUSION: Comparative simulation experimental results based on the publicly available Plane-Wave Imaging Challenge in Medical Ultrasound (PICMUS) and acoustic radiation force imaging data sets demonstrate that the proposed method outperforms other methods in both reconstruction errors and image quality. This helps to reduce the complexity of sampling and transmission of the ultrasound system.

A method to assess industrial paraffin contamination levels in rice and its transferability analysis based on transfer component analysis.

Accurate assessment of industrial paraffin contamination levels (IPCLs) in rice is critical for food safety. However, time-consuming and labor-intensive experiments to produce labels for targeted adulterated rice have hindered the development of IPCL estimation methods. In this paper, a transfer learning method (TCA-LSSVR) has been developed. The algorithm integrates transfer component analysis (TCA) with domain adaptive capabilities to produce accurate estimates. Rice from 7 different regions and 3 industrial paraffins were used to generate 4,680 samples from 9 datasets for benchmarking. The test results showed that the established algorithm achieved good estimation performance in various modelling strategies, and only 20 % of off-site samples were needed to supplement the source dataset, the average determination coefficient R2 reached 0.7045, the average RMSE reached 0.140 %, and the average RPD reached 2.023. This work highlights the prospect of rapidly developing a new generation of adulteration detection algorithms using only previous trial data.

Genomics and Artificial Intelligence: Prostate Cancer.

Artificial intelligence (AI) is revolutionizing prostate cancer genomics research. By leveraging machine learning and deep learning algorithms, researchers can rapidly analyze vast genomic datasets to identify patterns and correlations that may be missed by traditional methods. These AI-driven insights can lead to the discovery of novel biomarkers, enhance the accuracy of diagnosis, and predict disease progression and treatment response. As such, AI is becoming an indispensable tool in the pursuit of personalized medicine for prostate cancer.

Artificial Intelligence in Pediatric Urology.

Application of artificial intelligence (AI) is one of the hottest topics in medicine. Unlike traditional methods that rely heavily on statistical assumptions, machine learning algorithms can identify highly complex patterns from data, allowing robust predictions. There is an abundance of evidence of exponentially increasing pediatric urologic publications using AI methodology in recent years. While these studies show great promise for better understanding of disease and patient care, we should be realistic about the challenges arising from the nature of pediatric urologic conditions and practice, in order to continue to produce high-impact research.

Rapid classification of SARS-CoV-2 variant strains using machine learning-based label-free SERS strategy.

The spread of COVID-19 over the past three years is largely due to the continuous mutation of the virus, which has significantly impeded global efforts to prevent and control this epidemic. Specifically, mutations in the amino acid sequence of the surface spike (S) protein of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have directly impacted its biological functions, leading to enhanced transmission and triggering an immune escape effect. Therefore, prompt identification of these mutations is crucial for formulating targeted treatment plans and implementing precise prevention and control measures. In this study, the label-free surface-enhanced Raman scattering (SERS) technology combined with machine learning (ML) algorithms provide a potential solution for accurate identification of SARS-CoV-2 variants. We establish a SERS spectral database of SARS-CoV-2 variants and demonstrate that a diagnostic classifier using a logistic regression (LR) algorithm can provide accurate results within 10 min. Our classifier achieves 100% accuracy for Beta (B.1.351/501Y.V2), Delta (B.1.617), Wuhan (COVID-19) and Omicron (BA.1) variants. In addition, our method achieves 100% accuracy in blind tests of positive and negative human nasal swabs based on the LR model. This method enables detection and classification of variants in complex biological samples. Therefore, ML-based SERS technology is expected to accurately discriminate various SARS-CoV-2 variants and may be used for rapid diagnosis and therapeutic decision-making.

Protein classification by autofluorescence spectral shape analysis using machine learning.

Depending on the relative numbers and spatial arrangement of Tryptophan (Trp; W) and Tyrosine (Tyr; Y) residues, different proteins produce distinct autofluorescence (AF) spectral shapes when excited at ∼280 nm. Yet, considering the vast number and heterogeneous forms in nature, visual analysis and precise identification of proteins based on their AF spectra is challenging and further compounded in cases when different proteins produce substantially similar AF spectral shapes. There is, thus, a serious need to develop a methodology to address this problem. The current study proposes a practical technology to quickly identify proteins using machine learning (ML) algorithms based on their AF spectra. Specifically, AF spectra of fifteen different standard proteins of varying origin with distinct structural and Trp/Tyr compositions were recorded; based on the spectral features selected by the Minimum-Redundancy-Maximum-Relevance (mRMR) algorithm, a multiclass Support Vector Machine (SVM) learning model with Radial Basis Function (RBF), Polynomial, and Linear kernels classified the proteins with high accuracy of 99.06%, 99.03%, and 98.29% respectively. Since protein identification is the key to understand biological functions and disease diagnosis, the proposed methodology could offer a viable alternative to and improve the existing protein identification techniques.

A multivariate algorithm for identifying contaminated peanut using visible and near-infrared hyperspectral imaging.

In this study, a novel uniform manifold approximation and projection combined-improved simultaneous optimization genetic algorithm-convolutional neural network (UMAP-ISOGA-CNN) algorithm was proposed. The improved simultaneous optimization genetic algorithm (ISOGA) combined with convolutional neural network (CNN) to optimize the architecture, hyperparameters, and optimizer of the CNN model simultaneously. Additionally, a uniform manifold approximation and projection (UMAP) method was used to visualize the feature space of all feature layers of the ISOGA-CNN model. The UMAP-ISOGA-CNN algorithm combined with visible and near-infrared hyperspectral imaging was used to identify peanut kernels contaminated with Aspergillus flavus and to distinguish their storage time, which is essential for the food industry to monitor the freshness of products. Overall, the UMAP-ISOGA-CNN algorithm provides useful insights into the feature space of the ISOGA-CNN model, contributing to a better understanding of the model's internal mechanisms. This study has practical implications for the food industry and future research on deep learning optimization.

Big Data Analysis in Computational Biology and Bioinformatics.

Advancements in high-throughput technologies, genomics, transcriptomics, and metabolomics play an important role in obtaining biological information about living organisms. The field of computational biology and bioinformatics has experienced significant growth with the advent of high-throughput sequencing technologies and other high-throughput techniques. The resulting large amounts of data present both opportunities and challenges for data analysis. Big data analysis has become essential for extracting meaningful insights from the massive amount of data. In this chapter, we provide an overview of the current status of big data analysis in computational biology and bioinformatics. We discuss the various aspects of big data analysis, including data acquisition, storage, processing, and analysis. We also highlight some of the challenges and opportunities of big data analysis in this area of research. Despite the challenges, big data analysis presents significant opportunities like development of efficient and fast computing algorithms for advancing our understanding of biological processes, identifying novel biomarkers for breeding research and developments, predicting disease, and identifying potential drug targets for drug development programs.

A Review of Computational Approach for S-system-based Modeling of Gene Regulatory Network.

Inference of gene regulatory network (GRN) from time series microarray data remains as a fascinating task for computer science researchers to understand the complex biological process that occurred inside a cell. Among the different popular models to infer GRN, S-system is considered as one of the promising non-linear mathematical tools to model the dynamics of gene expressions, as well as to infer the GRN. S-system is based on biochemical system theory and power law formalism. By observing the value of kinetic parameters of S-system model, it is possible to extract the regulatory relationships among genes. In this review, several existing intelligent methods that were already proposed for inference of S-system-based GRN are explained. It is observed that finding out the most suitable and efficient optimization technique for the accurate inference of all kinds of networks, i.e., in-silico, in-vivo, etc., with less computational complexity is still an open research problem to all. This paper may help the beginners or researchers who want to continue their research in the field of computational biology and bioinformatics.