Search

Identifying the genes and mutations that drive the emergence of tumors is a critical step to improving our understanding of cancer and identifying new directions for disease diagnosis and treatment. Despite the large volume of genomics data, the precise detection of driver mutations and their carrying genes, known as cancer driver genes, from the millions of possible somatic mutations remains a challenge. Computational methods play an increasingly important role in discovering genomic patterns associated with cancer drivers and developing predictive models to identify these elements. Machine learning (ML), including deep learning, has been the engine behind many of these efforts and provides excellent opportunities for tackling remaining gaps in the field. Thus, this survey aims to perform a comprehensive analysis of ML-based computational approaches to identify cancer driver mutations and genes, providing an integrated, panoramic view of the broad data and algorithmic landscape within this scientific problem. We discuss how the interactions among data types and ML algorithms have been explored in previous solutions and outline current analytical limitations that deserve further attention from the scientific community. We hope that by helping readers become more familiar with significant developments in the field brought by ML, we may inspire new researchers to address open problems and advance our knowledge towards cancer driver discovery. [ABSTRACT FROM AUTHOR]

The article provides information about the 23rd European Conference on Computational Biology (ECCB2024) held in Turku, Finland. The conference focuses on data and algorithms for health and science and attracts scientists and industry professionals from various disciplines. It showcases cutting-edge developments in computational biology, including systems biology, artificial intelligence, single-cell and spatial technologies, and data integration. The conference features keynote lectures, scientific debates, poster presentations, workshops, and tutorials. The ECCB2024 proceedings include 24 papers selected through a peer-review process, and the conference promotes gender equity and adheres to a code of conduct to ensure a safe and respectful environment for all attendees. [Extracted from the article]

As an emerging geophysical exploration technology in recent years, airborne electromagnetic exploration has the advantages of adapting to diverse terrains, wide coverage, and providing a large amount of electromagnetic data, and can be applied to the rapid collection of large amounts of data. Scenarios are often used in fields such as deep geological structures, mineral resource exploration, and environmental engineering research. However, traditional airborne electromagnetic data inversion technology usually takes a long time to process a large amount of airborne electromagnetic data, and it is difficult to remove the noise in the later signals. Therefore, this paper proposes a multi-task learning network structure based on Transformer. By constraining the two network branches of imaging and denoising, a sub-network with simultaneous denoising and imaging is established to process aeronautical electromagnetic data. The noise test set is introduced for testing. This model achieved a 582.61% signal-to-noise ratio improvement in smooth Gaussian noise denoising, and a 129.69% and 112.74% signal-to-noise ratio improvement in non-smooth Gaussian noise and random impulse noise denoising, respectively. The method proposed in this article overcomes the shortcomings of traditional inversion imaging such as slow speed and low resolution, and at the same time eliminates the influence of noise in airborne electromagnetic data. This is of great significance for the application of deep learning in the field of geophysical exploration. [ABSTRACT FROM AUTHOR]

The quality factor (Q) is a parameter reflecting the physical properties of reservoirs. Accurate estimation of the quality factor plays an important role in improving the resolution of seismic data. Spectral-ratio method is a widely used traditional method based on the linear least-squares fitting to extract the quality factor, but is sensitive to noise. This is the main reason preventing this method from being widely used. Some supervised deep-learning methods are proposed to extract Q in which the construction of training labels is a key link. The proposed method is based on the spectral-ratio method to create training labels, avoiding errors in generating them. In contrast to the least-squares method, this paper proposes to use a nonlinear regression algorithm based on a fully connected network to fit the spectral logarithmic ratio and frequency. Meanwhile, the empirical equation is applied to constrain prediction results. The proposed method can effectively overcome the influence of noise and improve the accuracy of prediction results. Tests on the synthesized data of vertical seismic profile and common middle profile show that the proposed method has better generalization ability than the spectral-ratio method. Applying the method to the field vertical seismic profile data successfully extracts the quality factor, which can provide effective information for dividing stratigraphic layers. [ABSTRACT FROM AUTHOR]

Accurately predicting the external morphology and internal structure of fractured-vuggy reservoirs is of significant importance for the exploration and development of carbonate oil and gas reservoirs. Conventional seismic prediction methods suffer from serious non-uniqueness and low efficiency, while recent advances in deep learning exhibit strong feature learning capabilities and high generalization. Therefore, this paper proposes an intelligent prediction technique for fault-controlled fracture-vuggy reservoirs based on deep learning methods. The approach involves constructing 3D seismic geological models that conform to the geological characteristics of the study area, simulating seismic wavefield propagation, and combining the interpretation results of fractured-vuggy reservoirs. Training sample datasets are separately established for strike-slip faults, karst caves, and fault-controlled fractured-vuggy reservoir outlines, which are then input into the U-Net model in batches for training. This leads to the creation of a deep learning network model for fault-controlled fractured-vuggy reservoirs. The trained network model is applied to the intelligent identification of fault, karst cave, and fault-controlled fracture-vuggy reservoir outlines using actual seismic data from the Shunbei area. A comparison with traditional methods is conducted, and the experimental results demonstrate that the proposed deep learning approach shows excellent performance in the identification and prediction of fault-controlled fractured-vuggy reservoirs. [ABSTRACT FROM AUTHOR]

Predicting the strength of promoters and guiding their directed evolution is a crucial task in synthetic biology. This approach significantly reduces the experimental costs in conventional promoter engineering. Previous studies employing machine learning or deep learning methods have shown some success in this task, but their outcomes were not satisfactory enough, primarily due to the neglect of evolutionary information. In this paper, we introduce the Chaos-Attention net for Promoter Evolution (CAPE) to address the limitations of existing methods. We comprehensively extract evolutionary information within promoters using merged chaos game representation and process the overall information with modified DenseNet and Transformer structures. Our model achieves state-of-the-art results on two kinds of distinct tasks related to prokaryotic promoter strength prediction. The incorporation of evolutionary information enhances the model's accuracy, with transfer learning further extending its adaptability. Furthermore, experimental results confirm CAPE's efficacy in simulating in silico directed evolution of promoters, marking a significant advancement in predictive modeling for prokaryotic promoter strength. Our paper also presents a user-friendly website for the practical implementation of in silico directed evolution on promoters. The source code implemented in this study and the instructions on accessing the website can be found in our GitHub repository https://github.com/BobYHY/CAPE. [ABSTRACT FROM AUTHOR]

Background: Surgical waiting lists have risen dramatically across the UK as a result of the COVID-19 pandemic. The effective use of operating theatres by optimal scheduling could help mitigate this, but this requires accurate case duration predictions. Current standards for predicting the duration of surgery are inaccurate. Artificial intelligence (AI) offers the potential for greater accuracy in predicting surgical case duration. This study aimed to investigate whether there is evidence to support that AI is more accurate than current industry standards at predicting surgical case duration, with a secondary aim of analysing whether the implementation of the models used produced efficiency savings. Method: PubMed, Embase, and MEDLINE libraries were searched through to July 2023 to identify appropriate articles. PRISMA extension for scoping reviews and the Arksey and O'Malley framework were followed. Study quality was assessed using a modified version of the reporting guidelines for surgical AI papers by Farrow et al. Algorithm performance was reported using evaluation metrics. Results: The search identified 2593 articles: 14 were suitable for inclusion and 13 reported on the accuracy of AI algorithms against industry standards, with seven demonstrating a statistically significant improvement in prediction accuracy (P < 0.05). The larger studies demonstrated the superiority of neural networks over other machine learning techniques. Efficiency savings were identified in a RCT. Significant methodological limitations were identified across most studies. Conclusion: The studies suggest that machine learning and deep learning models are more accurate at predicting the duration of surgery; however, further research is required to determine the best way to implement this technology. Waiting lists for elective surgeries are rising in the UK. We conducted a scoping review with the aim to understand if artificial intelligence has the potential to improve the utilization of operating theatre resources through improved scheduling. [ABSTRACT FROM AUTHOR]

Summary Phenotype-based drug screening emerges as a powerful approach for identifying compounds that actively interact with cells. Transcriptional and proteomic profiling of cell lines and individual cells provide insights into the cellular state alterations that occur at the molecular level in response to external perturbations, such as drugs or genetic manipulations. In this paper, we propose cycleCDR, a novel deep learning framework to predict cellular response to external perturbations. We leverage the autoencoder to map the unperturbed cellular states to a latent space, in which we postulate the effects of drug perturbations on cellular states follow a linear additive model. Next, we introduce the cycle consistency constraints to ensure that unperturbed cellular state subjected to drug perturbation in the latent space would produces the perturbed cellular state through the decoder. Conversely, removal of perturbations from the perturbed cellular states can restore the unperturbed cellular state. The cycle consistency constraints and linear modeling in the latent space enable to learn transferable representations of external perturbations, so that our model can generalize well to unseen drugs during training stage. We validate our model on four different types of datasets, including bulk transcriptional responses, bulk proteomic responses, and single-cell transcriptional responses to drug/gene perturbations. The experimental results demonstrate that our model consistently outperforms existing state-of-the-art methods, indicating our method is highly versatile and applicable to a wide range of scenarios. Availability and implementation The source code is available at: https://github.com/hliulab/cycleCDR. [ABSTRACT FROM AUTHOR]

Motivation Gene set enrichment (GSE) analysis allows for an interpretation of gene expression through pre-defined gene set databases and is a critical step in understanding different phenotypes. With the rapid development of single-cell RNA sequencing (scRNA-seq) technology, GSE analysis can be performed on fine-grained gene expression data to gain a nuanced understanding of phenotypes of interest. However, with the cellular heterogeneity in single-cell gene profiles, current statistical GSE analysis methods sometimes fail to identify enriched gene sets. Meanwhile, deep learning has gained traction in applications like clustering and trajectory inference in single-cell studies due to its prowess in capturing complex data patterns. However, its use in GSE analysis remains limited, due to interpretability challenges. Results In this paper, we present DeepGSEA, an explainable deep gene set enrichment analysis approach which leverages the expressiveness of interpretable, prototype-based neural networks to provide an in-depth analysis of GSE. DeepGSEA learns the ability to capture GSE information through our designed classification tasks, and significance tests can be performed on each gene set, enabling the identification of enriched sets. The underlying distribution of a gene set learned by DeepGSEA can be explicitly visualized using the encoded cell and cellular prototype embeddings. We demonstrate the performance of DeepGSEA over commonly used GSE analysis methods by examining their sensitivity and specificity with four simulation studies. In addition, we test our model on three real scRNA-seq datasets and illustrate the interpretability of DeepGSEA by showing how its results can be explained. Availability and implementation https://github.com/Teddy-XiongGZ/DeepGSEA [ABSTRACT FROM AUTHOR]

The growing demand for high-quality industrial products has led to a significant emphasis on image anomaly detection (AD). AD in industrial goods presents a formidable research challenge that demands the application of sophisticated techniques to identify and address deviations from the expected norm accurately. Manufacturers increasingly recognize the significance of employing intelligent systems to detect flaws and defects in product parts. However, industrial settings pose several challenges: diverse categories, limited abnormal samples and vagueness. Hence, there is a growing demand for advanced image AD techniques within industrial product manufacturing. In this paper, an intelligent industrial defective chips detection framework is proposed which mainly consists of three core components. First, the convolutional features of the efficient backbone model is effectively utilized to balance the computational complexity and performance of industrial resource-constrained devices. Secondly, a novel inverse feature matching followed by masking method is proposed to enhance the explanability that localizes the abnormal regions of the abnormal chips. Finally, to evaluate our proposed method a comprehensive ablation study is conducted, where different machine learning and deep learning algorithms are analysed to claim the superiority of our method. Furthermore, to help the research community, a benchmark dataset is collected from real-world industry manufacturing for defective chip detection. The empirical results from the dataset demonstrate the strength and effectiveness of the proposed model compared to the other models. [ABSTRACT FROM AUTHOR]

This paper aims to automatize the performance-based design of fire engineering and the fire risk assessment of buildings with large open spaces and complex shapes. We first establish a database of high-quality fire simulations for diverse building shapes with heights up to 60 m and complex atriums with volumes up to 22   400 m³. Then, artificial intelligence (AI) models are trained to predict the soot visibility slices for new fire cases in buildings of different atrium shapes, symmetricities, and volumes. Two deep learning models were demonstrated: the pix2pix generative adversarial network (GAN) and image-prompt diffusion model. Compared with high-fidelity computational fluid dynamics fire modeling, the available safe egress time predicted by both models shows a high accuracy of 92% for random atrium shapes that are not distinct from the training cases, proving their performance in actual design practices. The diffusion model reproduces more flow details of the smoke visibility profiles than GAN, but it takes a longer computational time to render the fire scene. This work demonstrates the potential of leveraging AI technologies in building fire safety design, offering significant cost and time reductions and optimal solution identification. [ABSTRACT FROM AUTHOR]

Controlled-source audio frequency magnetotellurics (CSAMT) is an artificial-source electromagnetic technique that partially mitigates the limitations of weak natural-field signals. However, practical field surveys inevitably encounter strong interference, severely affecting signal quality. Traditional methods such as Fourier transformation, which directly computes apparent resistivity from frequency-domain information, are inadequate in this context, so we need alternative denoising approaches. However, research on CSAMT denoising is currently limited. Given the excellent performance of long short-term memory (LSTM) neural networks in the processing of magnetotelluric (MT) data, as demonstrated by previous studies, this paper proposes the use of LSTM to denoise CSAMT signals in the time domain. Unlike traditional denoising methods, we aim to directly extract the target frequency signal from the time-series data for denoising. For MT data, target frequency signals and noise are all mixed together, so noise suppression can only be achieved by identifying noise characteristics in the time series. However, unlike MT data, CSAMT data has an artificial transmitting source, and the frequency of the valid signal is fixed within a time interval. This allows for the direct extraction of target frequency signals without considering the complex characteristics of noise. In this study, we developed a neural network based on bidirectional LSTM to accomplish the task of noise suppression. After conducting both simulated and measured data tests, this method was able to, on average, improve the signal-to-noise ratio (SNR) of CSAMT data by approximately 20 dB and partially address the challenge of denoising when the data's SNR falls below 0 dB. [ABSTRACT FROM AUTHOR]

With the widespread use of computer-aided technologies like CAD/CAM/CAPP in the product manufacturing process, a large amount of process data is constantly generated and data-driven process planning has shown promising potentials for effectively reusing the process knowledge. However, a lot of labeled data are needed to train a deep learning model for effectively extracting the embedded knowledge and experiences within these process data and the labeling of process data is quite expensive and time-consuming. This paper proposes a cost-effective process design intents extraction approach for process data by combining active learning (AL) and self-paced learning (SPL). First, the process design intents inference model based on Bi-LSTM is generated by using a few pre-labeled samples. Then, the prediction uncertainty of each unlabeled sample is calculated by using a Bayesian neural network, which can assist in the identification of high confidence samples in SPL and low confidence samples in AL. Finally, the low confidence samples with manual-labels and the high confidence samples with pseudo-labels are incorporated into the training data for retraining the process design intents inference model iteratively until the model attains optimal performance. The experiments demonstrate that our approach can substantially decrease the number of labeled samples required for model training and the design intents in the process data could be inferred effectively with dynamically undated training data. [ABSTRACT FROM AUTHOR]

Deep learning methods achieve excellent noise reduction performances in seismic data processing compared with traditional methods. However, deep learning usually requires a large number of pairwise noisy-clean training data, which is an extremely challenging task. In this paper, an unsupervised approach without clean seismic data is proposed to suppress random noise. Seismic data is divided into odd and even traces, which serve as the input and output of the depth network, so that the proposed algorithm can be trained directly on the original data. What is more, the proposed method introduces two regularization terms to solve the over-smoothing problem caused by reconstruction of adjacent traces. The first term considers an ideal denoising network that does not cause oversmooth as a constraint, while the second term considers the structural information existing in seismic data. Experiments on synthetic post-stack data illustrate that the proposed method obtain a higher signal-to-noise ratio than the comparison methods. In the application of field post-stack seismic data, the proposed method can effectively maintain the seismic amplitude and generate good spectral characteristics. [ABSTRACT FROM AUTHOR]

Predicting the remaining useful life (RUL) of the aircraft engine based on historical data plays a pivotal role in formulating maintenance strategies and mitigating the risk of critical failures. None the less, attaining precise RUL predictions often encounters challenges due to the scarcity of historical condition monitoring data. This paper introduces a multiscale deep transfer learning framework via integrating domain adaptation principles. The framework encompasses three integral components: a feature extraction module, an encoding module, and an RUL prediction module. During pre-training phase, the framework leverages a multiscale convolutional neural network to extract distinctive features from data across varying scales. The ensuing parameter transfer adopts a domain adaptation strategy centered around maximum mean discrepancy. This method efficiently facilitates the acquisition of domain-invariant features from the source and target domains. The refined domain adaptation Transformer-based multiscale convolutional neural network model exhibits enhanced suitability for predicting RUL in the target domain under the condition of limited samples. Experiments on the C-MAPSS dataset have shown that the proposed method significantly outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Motivation A patient's disease phenotype can be driven and determined by specific groups of cells whose marker genes are either unknown or can only be detected at late-stage using conventional bulk assays such as RNA-Seq technology. Recent advances in single-cell RNA sequencing (scRNA-seq) enable gene expression profiling in cell-level resolution, and therefore have the potential to identify those cells driving the disease phenotype even while the number of these cells is small. However, most existing methods rely heavily on accurate cell type detection, and the number of available annotated samples is usually too small for training deep learning predictive models. Results Here, we propose the method ScRAT for phenotype prediction using scRNA-seq data. To train ScRAT with a limited number of samples of different phenotypes, such as coronavirus disease (COVID) and non-COVID, ScRAT first applies a mixup module to increase the number of training samples. A multi-head attention mechanism is employed to learn the most informative cells for each phenotype without relying on a given cell type annotation. Using three public COVID datasets, we show that ScRAT outperforms other phenotype prediction methods. The performance edge of ScRAT over its competitors increases as the number of training samples decreases, indicating the efficacy of our sample mixup. Critical cell types detected based on high-attention cells also support novel findings in the original papers and the recent literature. This suggests that ScRAT overcomes the challenge of missing marker genes and limited sample number with great potential revealing novel molecular mechanisms and/or therapies. Availability and implementation The code of our proposed method ScRAT is published at https://github.com/yuzhenmao/ScRAT. [ABSTRACT FROM AUTHOR]

Studies have confirmed that the occurrence of many complex diseases in the human body is closely related to the microbial community, and microbes can affect tumorigenesis and metastasis by regulating the tumor microenvironment. However, there are still large gaps in the clinical observation of the microbiota in disease. Although biological experiments are accurate in identifying disease-associated microbes, they are also time-consuming and expensive. The computational models for effective identification of diseases related microbes can shorten this process, and reduce capital and time costs. Based on this, in the paper, a model named DSAE_RF is presented to predict latent microbe–disease associations by combining multi-source features and deep learning. DSAE_RF calculates four similarities between microbes and diseases, which are then used as feature vectors for the disease-microbe pairs. Later, reliable negative samples are screened by k -means clustering, and a deep sparse autoencoder neural network is further used to extract effective features of the disease-microbe pairs. In this foundation, a random forest classifier is presented to predict the associations between microbes and diseases. To assess the performance of the model in this paper, 10-fold cross-validation is implemented on the same dataset. As a result, the AUC and AUPR of the model are 0.9448 and 0.9431, respectively. Furthermore, we also conduct a variety of experiments, including comparison of negative sample selection methods, comparison with different models and classifiers, Kolmogorov–Smirnov test and t -test, ablation experiments, robustness analysis, and case studies on Covid-19 and colorectal cancer. The results fully demonstrate the reliability and availability of our model. [ABSTRACT FROM AUTHOR]

The rapid growth of omics-based data has revolutionized biomedical research and precision medicine, allowing machine learning models to be developed for cutting-edge performance. However, despite the wealth of high-throughput data available, the performance of these models is hindered by the lack of sufficient training data, particularly in clinical research (in vivo experiments). As a result, translating this knowledge into clinical practice, such as predicting drug responses, remains a challenging task. Transfer learning is a promising tool that bridges the gap between data domains by transferring knowledge from the source to the target domain. Researchers have proposed transfer learning to predict clinical outcomes by leveraging pre-clinical data (mouse, zebrafish), highlighting its vast potential. In this work, we present a comprehensive literature review of deep transfer learning methods for health informatics and clinical decision-making, focusing on high-throughput molecular data. Previous reviews mostly covered image-based transfer learning works, while we present a more detailed analysis of transfer learning papers. Furthermore, we evaluated original studies based on different evaluation settings across cross-validations, data splits and model architectures. The result shows that those transfer learning methods have great potential; high-throughput sequencing data and state-of-the-art deep learning models lead to significant insights and conclusions. Additionally, we explored various datasets in transfer learning papers with statistics and visualization. [ABSTRACT FROM AUTHOR]

The transient electromagnetic method (TEM) is a geophysical exploration method that can efficiently acquire subsurface electrical parameters. For airborne, towed and other mobile platforms, TEM systems, large data volumes and the traditional one-dimensional denoising method with low efficiency and low signal-to-noise ratio (SNR) of late-time are the main bottlenecks limiting its reliable application. To address this problem, this paper proposes a neural network structure suitable for two-dimensional (2D) TEM data processing. The proposed structure combines a classical convolutional neural network denoising autoencoder with a gated recurrent neural network autoencoder, called the CNN-GRU dual autoencoder (CG-DAE). This method can directly input 2D TEM response data as images into the network for processing, which greatly improves data processing efficiency compared to single-time-channel processing. The simulation experiments verified the effectiveness of CG-DAE. After using CG-DAE denoising, the SNR of late-time (0.2–1 ms) signals is improved to nearly 29 dB, the 2D anomaly layer position is clear and the relative error (RE) between the denoised data and the corresponding clean data is <1.41%, while the RE of the late-time signals can be reduced to 3.68%. The proposed method can lay the foundation for fast processing of TEM data based on mobile platforms such as those that are airborne and/or towed. [ABSTRACT FROM AUTHOR]

Advancing spatially resolved transcriptomics (ST) technologies help biologists comprehensively understand organ function and tissue microenvironment. Accurate spatial domain identification is the foundation for delineating genome heterogeneity and cellular interaction. Motivated by this perspective, a graph deep learning (GDL) based spatial clustering approach is constructed in this paper. First, the deep graph infomax module embedded with residual gated graph convolutional neural network is leveraged to address the gene expression profiles and spatial positions in ST. Then, the Bayesian Gaussian mixture model is applied to handle the latent embeddings to generate spatial domains. Designed experiments certify that the presented method is superior to other state-of-the-art GDL-enabled techniques on multiple ST datasets. The codes and dataset used in this manuscript are summarized at https://github.com/narutoten520/SCGDL. [ABSTRACT FROM AUTHOR]

CRISPR/Cas9 (Clustered Regularly Interspaced Short Palindromic Repeats and CRISPR-associated protein 9) is a popular and effective two-component technology used for targeted genetic manipulation. It is currently the most versatile and accurate method of gene and genome editing, which benefits from a large variety of practical applications. For example, in biomedicine, it has been used in research related to cancer, virus infections, pathogen detection, and genetic diseases. Current CRISPR/Cas9 research is based on data-driven models for on- and off-target prediction as a cleavage may occur at non-target sequence locations. Nowadays, conventional machine learning and deep learning methods are applied on a regular basis to accurately predict on-target knockout efficacy and off-target profile of given single-guide RNAs (sgRNAs). In this paper, we present an overview and a comparative analysis of traditional machine learning and deep learning models used in CRISPR/Cas9. We highlight the key research challenges and directions associated with target activity prediction. We discuss recent advances in the sgRNA–DNA sequence encoding used in state-of-the-art on- and off-target prediction models. Furthermore, we present the most popular deep learning neural network architectures used in CRISPR/Cas9 prediction models. Finally, we summarize the existing challenges and discuss possible future investigations in the field of on- and off-target prediction. Our paper provides valuable support for academic and industrial researchers interested in the application of machine learning methods in the field of CRISPR/Cas9 genome editing. [ABSTRACT FROM AUTHOR]

In this paper, a method for seismic random noise detection and suppression using a denoising convolutional neural network (DnCNN) is presented. Thanks to the residual learning and batch normalization, deep learning networks can converge faster, the gradient descent and disappearance due to the increase of network layers are solved, and the residual results can be predicted more accurately. For seismic data, the variance estimation method is useful for obtaining an accurate noise distribution model and statistical parameters that provide a useful assessment of the noise level. With the variance estimation method based on weak texture blocks, a noise distribution model and statistical parameters can be derived with high accuracy, and this method effectively estimates seismic noise levels. The DnCNN networks are trained, and non-Gaussian noise reduction technology is used to achieve blind noise reduction at unknown levels, improving the noise reduction of seismic data. In addition, stratigraphic dip characteristics related to layer structure are used as DnCNN training network constraints to prevent effective signals in seismic data from being corrupted by conventional DnCNN noise reduction methods. Geological features such as faults and fracture-cavities can be effectively protected. Carbonate faults in the Tarim Basin in China are affected by the desert surface and the depth at which reservoirs are buried. The seismic data has a low signal-to-noise ratio, and the effective signals of the reservoir are low resolution. The seismic data can be effectively enhanced with this method for noise reduction in this area, the fracture-cavity is effectively displayed, and the fault features are also highlighted. [ABSTRACT FROM AUTHOR]

The finite difference forward modeling has been widely used in geophysics exploration and petroleum fields. Because of its high efficiency and easy application for graphical processing units, it has been widely concerned by industry and academia. However, owing to many factors, the problem of numerical dispersion has been an important factor hindering this method. To overcome the numerical dispersion, this paper proposes a method for removing numerical dispersion using deep learning. Unlike the conventional optimized algorithms target to optimize the finite difference coefficients, our strategy is based on big data training to eliminate the dispersion data after seismic data modeling. We design a neural network architecture based on cycle-consistent generative adversarial networks (Cycle-GANs) and residual learning for elastic wave propagation. Under the premise of not significantly increasing the calculation time, we can obtain higher calculation accuracy. Compared with the high-order finite difference algorithm, the calculation time is the advantage of our proposed deep learning method. Tests prove the efficiency and stability of our proposed algorithm. [ABSTRACT FROM AUTHOR]

In recent years, there have been many studies using artificial intelligence to recognize machining features in three-dimensional models in the computer-aided design (CAD)/computer-aided manufacturing field. Most of these studies converted the original CAD data into images, point clouds, or voxels for recognition. This led to information loss during the conversion process, resulting in decreased recognition accuracy. In this paper, we propose a novel deep learning model called the boundary representation graph attention network (BRepGAT) to segment faces in an original boundary representation (B-rep) model containing machining features. We define descriptors that represent information about the faces and edges of the B-rep model from the perspective of feature recognition. These descriptors are extracted from the B-rep model and transformed into homogeneous graph data, which are then passed to graph networks. BRepGAT recognizes machining features from the graph data input. Our experimental results using the MFCAD18++ dataset showed that BRepGAT achieved state-of-the-art recognition accuracy (99.1%). Furthermore, BRepGAT showed relatively robust performance on other datasets besides MFCAD18++. [ABSTRACT FROM AUTHOR]

Background Literature about SARS-CoV-2 widely discusses the effects of variations that have spread in the past 3 years. Such information is dispersed in the texts of several research articles, hindering the possibility of practically integrating it with related datasets (e.g. millions of SARS-CoV-2 sequences available to the community). We aim to fill this gap, by mining literature abstracts to extract—for each variant/mutation—its related effects (in epidemiological, immunological, clinical, or viral kinetics terms) with labeled higher/lower levels in relation to the nonmutated virus. Results The proposed framework comprises (i) the provisioning of abstracts from a COVID-19–related big data corpus (CORD-19) and (ii) the identification of mutation/variant effects in abstracts using a GPT2-based prediction model. The above techniques enable the prediction of mutations/variants with their effects and levels in 2 distinct scenarios: (i) the batch annotation of the most relevant CORD-19 abstracts and (ii) the on-demand annotation of any user-selected CORD-19 abstract through the CoVEffect web application (http://gmql.eu/coveffect), which assists expert users with semiautomated data labeling. On the interface, users can inspect the predictions and correct them; user inputs can then extend the training dataset used by the prediction model. Our prototype model was trained through a carefully designed process, using a minimal and highly diversified pool of samples. Conclusions The CoVEffect interface serves for the assisted annotation of abstracts, allowing the download of curated datasets for further use in data integration or analysis pipelines. The overall framework can be adapted to resolve similar unstructured-to-structured text translation tasks, which are typical of biomedical domains. [ABSTRACT FROM AUTHOR]

Aims: Most patients who receive implantable cardioverter defibrillators (ICDs) for primary prevention do not receive therapy during the lifespan of the ICD, whilst up to 50% of sudden cardiac death (SCD) occur in individuals who are considered low risk by conventional criteria. Machine learning offers a novel approach to risk stratification for ICD assignment.Methods and Results: Systematic search was performed in MEDLINE, Embase, Emcare, CINAHL, Cochrane Library, OpenGrey, MedrXiv, arXiv, Scopus, and Web of Science. Studies modelling SCD risk prediction within days to years using machine learning were eligible for inclusion. Transparency and quality of reporting (TRIPOD) and risk of bias (PROBAST) were assessed. A total of 4356 studies were screened with 11 meeting the inclusion criteria with heterogeneous populations, methods, and outcome measures preventing meta-analysis. The study size ranged from 122 to 124 097 participants. Input data sources included demographic, clinical, electrocardiogram, electrophysiological, imaging, and genetic data ranging from 4 to 72 variables per model. The most common outcome metric reported was the area under the receiver operator characteristic (n = 7) ranging between 0.71 and 0.96. In six studies comparing machine learning models and regression, machine learning improved performance in five. No studies adhered to a reporting standard. Five of the papers were at high risk of bias.Conclusion: Machine learning for SCD prediction has been under-applied and incorrectly implemented but is ripe for future investigation. It may have some incremental utility in predicting SCD over traditional models. The development of reporting standards for machine learning is required to improve the quality of evidence reporting in the field. [ABSTRACT FROM AUTHOR]

With rapidly evolving high-throughput technologies and consistently decreasing costs, collecting multimodal omics data in large-scale studies has become feasible. Although studying multiomics provides a new comprehensive approach in understanding the complex biological mechanisms of human diseases, the high dimensionality of omics data and the complexity of the interactions among various omics levels in contributing to disease phenotypes present tremendous analytical challenges. There is a great need of novel analytical methods to address these challenges and to facilitate multiomics analyses. In this paper, we propose a multimodal functional deep learning (MFDL) method for the analysis of high-dimensional multiomics data. The MFDL method models the complex relationships between multiomics variants and disease phenotypes through the hierarchical structure of deep neural networks and handles high-dimensional omics data using the functional data analysis technique. Furthermore, MFDL leverages the structure of the multimodal model to capture interactions between different types of omics data. Through simulation studies and real-data applications, we demonstrate the advantages of MFDL in terms of prediction accuracy and its robustness to the high dimensionality and noise within the data. [ABSTRACT FROM AUTHOR]

Synthetic lethality (SL) has shown great promise for the discovery of novel targets in cancer. CRISPR double-knockout (CDKO) technologies can only screen several hundred genes and their combinations, but not genome-wide. Therefore, good SL prediction models are highly needed for genes and gene pairs selection in CDKO experiments. However, lack of scalable SL properties prevents generalizability of SL interactions to out-of-sample data, thereby hindering modeling efforts. In this paper, we recognize that SL connectivity is a scalable and generalizable SL property. We develop a novel two-step multilayer encoder for individual sample-specific SL prediction model (MLEC-iSL), which predicts SL connectivity first and SL interactions subsequently. MLEC-iSL has three encoders, namely, gene, graph, and transformer encoders. MLEC-iSL achieves high SL prediction performance in K562 (AUPR, 0.73; AUC, 0.72) and Jurkat (AUPR, 0.73; AUC, 0.71) cells, while no existing methods exceed 0.62 AUPR and AUC. The prediction performance of MLEC-iSL is validated in a CDKO experiment in 22Rv1 cells, yielding a 46.8% SL rate among 987 selected gene pairs. The screen also reveals SL dependency between apoptosis and mitosis cell death pathways. [ABSTRACT FROM AUTHOR]

The molecular property prediction (MPP) plays a crucial role in the drug discovery process, providing valuable insights for molecule evaluation and screening. Although deep learning has achieved numerous advances in this area, its success often depends on the availability of substantial labeled data. The few-shot MPP is a more challenging scenario, which aims to identify unseen property with only few available molecules. In this paper, we propose an attribute-guided prototype network (APN) to address the challenge. APN first introduces an molecular attribute extractor, which can not only extract three different types of fingerprint attributes (single fingerprint attributes, dual fingerprint attributes, triplet fingerprint attributes) by considering seven circular-based, five path-based, and two substructure-based fingerprints, but also automatically extract deep attributes from self-supervised learning methods. Furthermore, APN designs the Attribute-Guided Dual-channel Attention module to learn the relationship between the molecular graphs and attributes and refine the local and global representation of the molecules. Compared with existing works, APN leverages high-level human-defined attributes and helps the model to explicitly generalize knowledge in molecular graphs. Experiments on benchmark datasets show that APN can achieve state-of-the-art performance in most cases and demonstrate that the attributes are effective for improving few-shot MPP performance. In addition, the strong generalization ability of APN is verified by conducting experiments on data from different domains. [ABSTRACT FROM AUTHOR]

Motivation The secondary structure of RNA is of importance to its function. Over the last few years, several papers attempted to use machine learning to improve de novo RNA secondary structure prediction. Many of these papers report impressive results for intra-family predictions but seldom address the much more difficult (and practical) inter-family problem. Results We demonstrate that it is nearly trivial with convolutional neural networks to generate pseudo-free energy changes, modelled after structure mapping data that improve the accuracy of structure prediction for intra-family cases. We propose a more rigorous method for inter-family cross-validation that can be used to assess the performance of learning-based models. Using this method, we further demonstrate that intra-family performance is insufficient proof of generalization despite the widespread assumption in the literature and provide strong evidence that many existing learning-based models have not generalized inter-family. Availability and implementation Source code and data are available at https://github.com/marcellszi/dl-rna. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Traditional geophysical inversion methods rely on an assumption of prior knowledge, starting from the establishment of the initial model and ending with the model being modified many times. This iterative process makes the forward modelling results move increasingly closer to the observed data. However, each inversion step requires multiple forward calculations, which consumes considerable time and computing resources. This is the greatest obstacle to real-time inversion at present. Airborne transient electromagnetic (ATEM) response data are collected in a time-channel manner. The different stratigraphic structures reveal different time-varying electromagnetic response laws. In this paper, deep learning technology is used to advance the 'model correction-forward iteration' step in the geophysical inversion process to the data preprocessing stage, to better adapt to the specialty of ATEM, improve the efficiency of the inversion and shorten the inversion time. In this method, a sample set composed of a 'stratigraphic texture model—ATEM response' is established, the K-Means clustering technique of unsupervised learning is used to complete the sample tag attachment, and the multilayer perceptron (MLP) deep learning network with supervised learning is used to complete the multiclassification tasks. Then, the sample sets are input into the deep learning network for training to build the inversion from the input response data to the output of the stratigraphic model. Finally, the inversion flow is verified with test set samples. The prediction results are consistent with the simulated data, and the inversion, from the test data to the prediction model, is implemented efficiently. [ABSTRACT FROM AUTHOR]

Seismic velocity analysis is the basis for seismic imaging and understanding complex subsurface geological structures. Although the performance of automatic velocity analysis methods based on Common Middle Point (CMP) data or Velocity Spectra (VS) is encouraging, particularly deep learning methods. However, most methods ignore the complementarity between CMP data and VS data, and only one of them is selected for velocity modelling. We propose a multimodal neural network (MMN) that combines the advantages of CMP data details representation and simplification of VS. MMN includes multilayer convolution structures and auto-encoder structures, which are used to extract time–space amplitude information from CMP gathers and energy groups features from VS data, respectively. This paper compared MMN with the CMP single-modal network (CSN) and the velocity spectra single-modal network (VSSN). Based on synthetic data, we investigated their differences in terms of continuity, accuracy, noise resistance and generalization. The MMN prediction results makes a trade-off between the overall continuity and local details. Visualization analysis of the intermediate feature maps explains the MMN velocity prediction mechanism, that is, the multi-angle representation and complementary fusion of velocity information. Finally, the performance of the proposed method is demonstrated using the braided river deposited field data example. [ABSTRACT FROM AUTHOR]

In this paper, we explore the use of seismicity data on a single-station basis in site response characterization. We train a supervised deep-learning model, SeismAmp, to recognize and separate seismic site response with reference to seismological bedrock (VS  = 3.45 km s−1) in a broad frequency range (0.2–20 Hz) directly from single-station earthquake recordings (features) in Japan. Ground-truth data are homogeneously created using a classical multistation approach—generalized spectral inversion at a total number of 1725 sites. We demonstrate that site response can be reliably separated from single-station seismograms in an end-to-end approach. When SeismAmp is tested at new sites in both Japan (in-domain) and Europe (cross-domain), it achieves the lowest standard deviation among all tested single-station techniques. We also find that horizontal-to-vertical spectral ratio (HVSR) is not the optimal use of single-station recordings. The individual components of each record carry salient information on site response, especially at high frequencies. However, part of the information is lost in HVSR. SeismAmp could lead to improved site-specific earthquake hazard prediction in cases where recordings are available or can be collected at target sites. It is also a convenient tool to remove repeatable site effects from ground motions, which may benefit other applications, for example, improving the retrieval of seismic source parameters. Finally, SeismAmp is trained on data from Japan, future studies could explore transfer learning for practical applications in other regions. [ABSTRACT FROM AUTHOR]

MicroRNAs (miRNAs) silence genes by binding to messenger RNAs, whereas long non-coding RNAs (lncRNAs) act as competitive endogenous RNAs (ceRNAs) that can relieve miRNA silencing effects and upregulate target gene expression. The ceRNA association between lncRNAs and miRNAs has been a research hotspot due to its medical importance, but it is challenging to verify experimentally. In this paper, we propose a novel deep learning scheme, i.e. sequence pre-training-based graph neural network (SPGNN), that combines pre-training and fine-tuning stages to predict lncRNA–miRNA associations from RNA sequences and the existing interactions represented as a graph. First, we utilize a sequence-to-vector technique to generate pre-trained embeddings based on the sequences of all RNAs during the pre-training stage. In the fine-tuning stage, we use Graph Neural Network to learn node representations from the heterogeneous graph constructed using lncRNA–miRNA association information. We evaluate our proposed scheme SPGNN on our newly collected animal lncRNA–miRNA association dataset and demonstrate that combining the |$k$| -mer technique and Doc2vec model for pre-training with the Simple Graph Convolution Network for fine-tuning is effective in predicting lncRNA–miRNA associations. Our approach outperforms state-of-the-art baselines across various evaluation metrics. We also conduct an ablation study and hyperparameter analysis to verify the effectiveness of each component and parameter of our scheme. The complete code and dataset are available on GitHub: https://github.com/zixwang/SPGNN. [ABSTRACT FROM AUTHOR]

Cancer heterogeneity has posed great challenges in exploring precise therapeutic strategies for cancer treatment. The identification of cancer subtypes aims to detect patients with distinct molecular profiles and thus could provide new clues on effective clinical therapies. While great efforts have been made, it remains challenging to develop powerful computational methods that can efficiently integrate multi-omics datasets for the task. In this paper, we propose a novel self-supervised learning model called Deep Multi-view Contrastive Learning (DMCL) for cancer subtype identification. Specifically, by incorporating the reconstruction loss, contrastive loss and clustering loss into a unified framework, our model simultaneously encodes the sample discriminative information into the extracted feature representations and well preserves the sample cluster structures in the embedded space. Moreover, DMCL is an end-to-end framework where the cancer subtypes could be directly obtained from the model outputs. We compare DMCL with eight alternatives ranging from classic cancer subtype identification methods to recently developed state-of-the-art systems on 10 widely used cancer multi-omics datasets as well as an integrated dataset, and the experimental results validate the superior performance of our method. We further conduct a case study on liver cancer and the analysis results indicate that different subtypes might have different responses to the selected chemotherapeutic drugs. [ABSTRACT FROM AUTHOR]

Molecular property prediction (MPP) is a crucial and fundamental task for AI-aided drug discovery (AIDD). Recent studies have shown great promise of applying self-supervised learning (SSL) to producing molecular representations to cope with the widely-concerned data scarcity problem in AIDD. As some specific substructures of molecules play important roles in determining molecular properties, molecular representations learned by deep learning models are expected to attach more importance to such substructures implicitly or explicitly to achieve better predictive performance. However, few SSL pre-trained models for MPP in the literature have ever focused on such substructures. To challenge this situation, this paper presents a C hemistry- A ware F ragmentation for E ffective MPP (CAFE-MPP in short) under the self-supervised contrastive learning framework. First, a novel fragment-based molecular graph (FMG) is designed to represent the topological relationship between chemistry-aware substructures that constitute a molecule. Then, with well-designed hard negative pairs, a is pre-trained on fragment-level by contrastive learning to extract representations for the nodes in FMGs. Finally, a Graphormer model is leveraged to produce molecular representations for MPP based on the embeddings of fragments. Experiments on 11 benchmark datasets show that the proposed CAFE-MPP method achieves state-of-the-art performance on 7 of the 11 datasets and the second-best performance on 3 datasets, compared with six remarkable self-supervised methods. Further investigations also demonstrate that CAFE-MPP can learn to embed molecules into representations implicitly containing the information of fragments highly correlated to molecular properties, and can alleviate the over-smoothing problem of graph neural networks. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) systems utilizing deep neural networks and machine learning (ML) algorithms are widely used for solving critical problems in bioinformatics, biomedical informatics and precision medicine. However, complex ML models that are often perceived as opaque and black-box methods make it difficult to understand the reasoning behind their decisions. This lack of transparency can be a challenge for both end-users and decision-makers, as well as AI developers. In sensitive areas such as healthcare, explainability and accountability are not only desirable properties but also legally required for AI systems that can have a significant impact on human lives. Fairness is another growing concern, as algorithmic decisions should not show bias or discrimination towards certain groups or individuals based on sensitive attributes. Explainable AI (XAI) aims to overcome the opaqueness of black-box models and to provide transparency in how AI systems make decisions. Interpretable ML models can explain how they make predictions and identify factors that influence their outcomes. However, the majority of the state-of-the-art interpretable ML methods are domain-agnostic and have evolved from fields such as computer vision, automated reasoning or statistics, making direct application to bioinformatics problems challenging without customization and domain adaptation. In this paper, we discuss the importance of explainability and algorithmic transparency in the context of bioinformatics. We provide an overview of model-specific and model-agnostic interpretable ML methods and tools and outline their potential limitations. We discuss how existing interpretable ML methods can be customized and fit to bioinformatics research problems. Further, through case studies in bioimaging, cancer genomics and text mining, we demonstrate how XAI methods can improve transparency and decision fairness. Our review aims at providing valuable insights and serving as a starting point for researchers wanting to enhance explainability and decision transparency while solving bioinformatics problems. GitHub: https://github.com/rezacsedu/XAI-for-bioinformatics. [ABSTRACT FROM AUTHOR]

Motivation Cancer heterogeneity drastically affects cancer therapeutic outcomes. Predicting drug response in vitro is expected to help formulate personalized therapy regimens. In recent years, several computational models based on machine learning and deep learning have been proposed to predict drug response in vitro. However, most of these methods capture drug features based on a single drug description (e.g. drug structure), without considering the relationships between drugs and biological entities (e.g. target, diseases, and side effects). Moreover, most of these methods collect features separately for drugs and cell lines but fail to consider the pairwise interactions between drugs and cell lines. Results In this paper, we propose a deep learning framework, named MSDRP for drug response prediction. MSDRP uses an interaction module to capture interactions between drugs and cell lines, and integrates multiple associations/interactions between drugs and biological entities through similarity network fusion algorithms, outperforming some state-of-the-art models in all performance measures for all experiments. The experimental results of de novo test and independent test demonstrate the excellent performance of our model for new drugs. Furthermore, several case studies illustrate the rationality for using feature vectors derived from drug similarity matrices from multisource data to represent drugs and the interpretability of our model. Availability and implementation The codes of MSDRP are available at https://github.com/xyzhang-10/MSDRP. [ABSTRACT FROM AUTHOR]

Objective Social determinants of health (SDOH) are nonmedical factors that can influence health outcomes. This paper seeks to extract SDOH from clinical texts in the context of the National NLP Clinical Challenges (n2c2) 2022 Track 2 Task. Materials and Methods Annotated and unannotated data from the Medical Information Mart for Intensive Care III (MIMIC-III) corpus, the Social History Annotation Corpus, and an in-house corpus were used to develop 2 deep learning models that used classification and sequence-to-sequence (seq2seq) approaches. Results The seq2seq approach had the highest overall F1 scores in the challenge's 3 subtasks: 0.901 on the extraction subtask, 0.774 on the generalizability subtask, and 0.889 on the learning transfer subtask. Discussion Both approaches rely on SDOH event representations that were designed to be compatible with transformer-based pretrained models, with the seq2seq representation supporting an arbitrary number of overlapping and sentence-spanning events. Models with adequate performance could be produced quickly, and the remaining mismatch between representation and task requirements was then addressed in postprocessing. The classification approach used rules to generate entity relationships from its sequence of token labels, while the seq2seq approach used constrained decoding and a constraint solver to recover entity text spans from its sequence of potentially ambiguous tokens. Conclusion We proposed 2 different approaches to extract SDOH from clinical texts with high accuracy. However, accuracy suffers on text from new healthcare institutions not present in the training data, and thus generalization remains an important topic for future study. [ABSTRACT FROM AUTHOR]

SUMMARY: Gravity inversion is a process that obtains the spatial structure and physical properties of underground anomalies using surface collected gravity anomaly data. In recent years, the rapid development of deep learning (DL) has enabled the achievement of good results for gravity inversion methods based on DL. These methods aim to learn the mapping between geological models and gravity anomaly data by training a neural network with geological models as labels. However, using DL inversion requires generating a large amount of training data for each geological target and involves the forward calculation of the generated models, which inevitably consumes a large amount of time and storage space. To address this issue, we propose using a neural network to approximate the expensive forward computation with a fast evaluation alternative. After training, the network can reproduce gravity anomalies at any observation point. To evaluate the effectiveness of the forward model, we use the gravity anomalies predicted by the forward network for inversion network training. Additionally, to mitigate the problem of poor generalization of existing DL inversions, we propose using multitask learning. By learning multiple related tasks simultaneously, the generalization ability of the model improves, thus enhancing the performance of the main task. In this paper, a multitask UNet3+ network is proposed to realize anomaly bodies localization and density contrasts reconstruction simultaneously. Test results on the synthetic data set demonstrate that the gravity anomalies predicted by the forward network can be successfully inverted, and the multitask approach can predict subsurface geology more accurately than the single-task. To further illustrate the effectiveness of the algorithm, we apply this method to the inversion of the San Nicolas deposit in central Mexico. [ABSTRACT FROM AUTHOR]

The conventional deep learning-based fault diagnosis approach faces challenges under the domain shift problem, where the model encounters different working conditions from the ones it was trained on. This challenge is particularly pronounced in the diagnosis of planetary gearboxes due to the complicated vibrations they generate, which can vary significantly based on the system characteristics of the gearbox. To solve this challenge, this paper proposes a robust deep learning-based fault-detection approach for planetary gearboxes by utilizing an enhanced health data map (HDMap). Although there is an HDMap method that visually expresses the vibration signal of the planetary gearbox according to the gear meshing position, it is greatly influenced by machine operating conditions. In this study, domain-specific features from the HDMap are further removed, while the fault-related features are enhanced. Autoencoderbased residual analysis and digital image-processing techniques are employed to address the domain-shift problem. The performance of the proposed method was validated under significant domain-shift problem conditions, as demonstrated by studying two gearbox test rigs with different configurations operated under stationary and non-stationary operating conditions. Validation accuracy was measured in all 12 possible domain-shift scenarios. The proposed method achieved robust fault detection accuracy, outperforming prior methods in most cases. [ABSTRACT FROM AUTHOR]

Automatic classification of different species of fish is important for the comprehension of marine ecology, fish behaviour analysis, aquaculture management, and fish health monitoring. In recent years, many automatic classification methods have been developed, among which machine vision-based classification methods are widely used with the advantages of being fast and non-destructive. In addition, the successful application of rapidly emerging deep learning techniques in machine vision has brought new opportunities for fish classification. This paper provides an overview of machine vision models applied in the field of fish classification, followed by a detailed discussion of specific applications of various classification methods. Furthermore, the challenges and future research directions in the field of fish classification are discussed. This paper would help researchers and practitioners to understand the applicability of machine vision in fish classification and encourage them to develop advanced algorithms and models to address the complex problems that exist in fish classification practice. [ABSTRACT FROM AUTHOR]

Sequence database searches followed by homology-based function transfer form one of the oldest and most popular approaches for predicting protein functions, such as Gene Ontology (GO) terms. These searches are also a critical component in most state-of-the-art machine learning and deep learning-based protein function predictors. Although sequence search tools are the basis of homology-based protein function prediction, previous studies have scarcely explored how to select the optimal sequence search tools and configure their parameters to achieve the best function prediction. In this paper, we evaluate the effect of using different options from among popular search tools, as well as the impacts of search parameters, on protein function prediction. When predicting GO terms on a large benchmark dataset, we found that BLASTp and MMseqs2 consistently exceed the performance of other tools, including DIAMOND—one of the most popular tools for function prediction—under default search parameters. However, with the correct parameter settings, DIAMOND can perform comparably to BLASTp and MMseqs2 in function prediction. Additionally, we developed a new scoring function to derive GO prediction from homologous hits that consistently outperform previously proposed scoring functions. These findings enable the improvement of almost all protein function prediction algorithms with a few easily implementable changes in their sequence homolog-based component. This study emphasizes the critical role of search parameter settings in homology-based function transfer and should have an important contribution to the development of future protein function prediction algorithms. [ABSTRACT FROM AUTHOR]

Thyroid cancer incidences endure to increase even though a large number of inspection tools have been developed recently. Since there is no standard and certain procedure to follow for the thyroid cancer diagnoses, clinicians require conducting various tests. This scrutiny process yields multi-dimensional big data and lack of a common approach leads to randomly distributed missing (sparse) data, which are both formidable challenges for the machine learning algorithms. This paper aims to develop an accurate and computationally efficient deep learning algorithm to diagnose the thyroid cancer. In this respect, randomly distributed missing data stemmed singularity in learning problems is treated and dimensionality reduction with inner and target similarity approaches are developed to select the most informative input datasets. In addition, size reduction with the hierarchical clustering algorithm is performed to eliminate the considerably similar data samples. Four machine learning algorithms are trained and also tested with the unseen data to validate their generalization and robustness abilities. The results yield 100% training and 83% testing preciseness for the unseen data. Computational time efficiencies of the algorithms are also examined under the equal conditions. [ABSTRACT FROM AUTHOR]

Nucleic acid-binding proteins (NABPs), including DNA-binding proteins (DBPs) and RNA-binding proteins (RBPs), play important roles in essential biological processes. To facilitate functional annotation and accurate prediction of different types of NABPs, many machine learning-based computational approaches have been developed. However, the datasets used for training and testing as well as the prediction scopes in these studies have limited their applications. In this paper, we developed new strategies to overcome these limitations by generating more accurate and robust datasets and developing deep learning-based methods including both hierarchical and multi-class approaches to predict the types of NABPs for any given protein. The deep learning models employ two layers of convolutional neural network and one layer of long short-term memory. Our approaches outperform existing DBP and RBP predictors with a balanced prediction between DBPs and RBPs, and are more practically useful in identifying novel NABPs. The multi-class approach greatly improves the prediction accuracy of DBPs and RBPs, especially for the DBPs with ~12% improvement. Moreover, we explored the prediction accuracy of single-stranded DNA binding proteins and their effect on the overall prediction accuracy of NABP predictions. [ABSTRACT FROM AUTHOR]

Machine learning (ML) algorithms are becoming popular in cosmology for extracting valuable information from cosmological data. In this paper, we evaluate the performance of a convolutional neural network (CNN) trained on matter density snapshots to distinguish clustering dark energy (DE) from the cosmological constant scenario and to detect the speed of sound (c s) associated with clustering DE. We compare the CNN results with those from a Random Forest (RF) algorithm trained on power spectra. Varying the DE equation of state parameter w DE within the range of −0.7 to −0.99 while keeping |$c_s^2 = 1$|⁠ , we find that the CNN approach results in a significant improvement in accuracy over the RF algorithm. The improvement in classification accuracy can be as high as 40 per cent depending on the physical scales involved. We also investigate the ML algorithms' ability to detect the impact of the speed of sound by choosing |$c_s^2$| from the set {1, 10−2, 10−4, 10−7} while maintaining a constant w DE for three different cases: w DE ∈ {−0.7, −0.8, −0.9}. Our results suggest that distinguishing between various values of |$c_s^2$| and the case where |$c_s^2=1$| is challenging, particularly at small scales and when w DE ≈ −1. However, as we consider larger scales, the accuracy of |$c_s^2$| detection improves. Notably, the CNN algorithm consistently outperforms the RF algorithm, leading to an approximate 20 per cent enhancement in |$c_s^2$| detection accuracy in some cases. [ABSTRACT FROM AUTHOR]

Transcription factors (TFs) are proteins essential for regulating genetic transcriptions by binding to transcription factor binding sites (TFBSs) in DNA sequences. Accurate predictions of TFBSs can contribute to the design and construction of metabolic regulatory systems based on TFs. Although various deep-learning algorithms have been developed for predicting TFBSs, the prediction performance needs to be improved. This paper proposes a bidirectional encoder representations from transformers (BERT)-based model, called BERT-TFBS, to predict TFBSs solely based on DNA sequences. The model consists of a pre-trained BERT module (DNABERT-2), a convolutional neural network (CNN) module, a convolutional block attention module (CBAM) and an output module. The BERT-TFBS model utilizes the pre-trained DNABERT-2 module to acquire the complex long-term dependencies in DNA sequences through a transfer learning approach, and applies the CNN module and the CBAM to extract high-order local features. The proposed model is trained and tested based on 165 ENCODE ChIP-seq datasets. We conducted experiments with model variants, cross-cell-line validations and comparisons with other models. The experimental results demonstrate the effectiveness and generalization capability of BERT-TFBS in predicting TFBSs, and they show that the proposed model outperforms other deep-learning models. The source code for BERT-TFBS is available at https://github.com/ZX1998-12/BERT-TFBS. [ABSTRACT FROM AUTHOR]

Protein–ligand interaction prediction presents a significant challenge in drug design. Numerous machine learning and deep learning (DL) models have been developed to accurately identify docking poses of ligands and active compounds against specific targets. However, current models often suffer from inadequate accuracy or lack practical physical significance in their scoring systems. In this research paper, we introduce IGModel, a novel approach that utilizes the geometric information of protein–ligand complexes as input for predicting the root mean square deviation of docking poses and the binding strength (pKd, the negative value of the logarithm of binding affinity) within the same prediction framework. This ensures that the output scores carry intuitive meaning. We extensively evaluate the performance of IGModel on various docking power test sets, including the CASF-2016 benchmark, PDBbind-CrossDocked-Core and DISCO set, consistently achieving state-of-the-art accuracies. Furthermore, we assess IGModel's generalizability and robustness by evaluating it on unbiased test sets and sets containing target structures generated by AlphaFold2. The exceptional performance of IGModel on these sets demonstrates its efficacy. Additionally, we visualize the latent space of protein–ligand interactions encoded by IGModel and conduct interpretability analysis, providing valuable insights. This study presents a novel framework for DL-based prediction of protein–ligand interactions, contributing to the advancement of this field. The IGModel is available at GitHub repository https://github.com/zchwang/IGModel. [ABSTRACT FROM AUTHOR]

In this review article, we explore the transformative impact of deep learning (DL) on structural bioinformatics, emphasizing its pivotal role in a scientific revolution driven by extensive data, accessible toolkits and robust computing resources. As big data continue to advance, DL is poised to become an integral component in healthcare and biology, revolutionizing analytical processes. Our comprehensive review provides detailed insights into DL, featuring specific demonstrations of its notable applications in bioinformatics. We address challenges tailored for DL, spotlight recent successes in structural bioinformatics and present a clear exposition of DL—from basic shallow neural networks to advanced models such as convolution, recurrent, artificial and transformer neural networks. This paper discusses the emerging use of DL for understanding biomolecular structures, anticipating ongoing developments and applications in the realm of structural bioinformatics. [ABSTRACT FROM AUTHOR]