Improving the Quantification of DNA Sequences Using Evolutionary Information Based on Deep Learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Tayara H
PROVIDER: S-EPMC6952993 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:More than 50 human diseases are characterized by the deposition of specific protein aggregates in the form of insoluble amyloid fibrils. However, only a very small number of proteins are known to form amyloids with high propensity, limiting our ability to understand, predict and engineer amyloid aggregation from sequence. Here we use a massively parallel assay to quantify the amyloid nucleation propensity of >100,000 random 20 amino acid sequences. Approximately 5% of assayed random sequences nucleate the formation of aggregates, generating a very large and diverse training dataset from which to train models to predict amyloid nucleation. We use this dataset to train CANYA, a convolution-attention hybrid neural network that predicts the propensity of any primary sequence to form amyloids. CANYA outperforms previous predictors of protein aggregation on additional random sequences and out-of-sample datasets including human disease-causing amyloids, with very stable performance across diverse prediction tasks. We adapt and extend recent advances in interpretability of genomic neural networks to elucidate CANYA’s decision-making process and learned grammar and to provide mechanistic insights into amyloid formation. Our results demonstrate the power of massive experimental random sequence-space exploration and provide an interpretable and robust neural network model for understanding, predicting and designing amyloid-forming proteins.
2024-07-17 | GSE268261 | GEO
Project description:PurposeTo develop a rapid 2D MR fingerprinting technique with a submillimeter in-plane resolution using a deep learning-based tissue quantification approach.MethodsA rapid and high-resolution MR fingerprinting technique was developed for brain T1 and T2 quantification. The 2D acquisition was performed using a FISP-based MR fingerprinting sequence and a spiral trajectory with 0.8-mm in-plane resolution. A deep learning-based method was used to replace the standard template matching method for improved tissue characterization. A novel network architecture (i.e., residual channel attention U-Net) was proposed to improve high-resolution details in the estimated tissue maps. Quantitative brain imaging was performed with 5 adults and 2 pediatric subjects, and the performance of the proposed approach was compared with several existing methods in the literature.ResultsIn vivo measurements with both adult and pediatric subjects show that high-quality T1 and T2 mapping with 0.8-mm in-plane resolution can be achieved in 7.5 seconds per slice. The proposed deep learning method outperformed existing algorithms in tissue quantification with improved accuracy. Compared with the standard U-Net, high-resolution details in brain tissues were better preserved by the proposed residual channel attention U-Net. Experiments on pediatric subjects further demonstrated the potential of the proposed technique for fast pediatric neuroimaging. Alongside reduced data acquisition time, a 5-fold acceleration in tissue property mapping was also achieved with the proposed method.ConclusionA rapid and high-resolution MR fingerprinting technique was developed, which enables high-quality T1 and T2 quantification with 0.8-mm in-plane resolution in 7.5 seconds per slice.
| S-EPMC8210473 | biostudies-literature
Project description:Reliable uncertainty quantification for statistical models is crucial in various downstream applications, especially for drug design and discovery where mistakes may incur a large amount of cost. This topic has therefore absorbed much attention and a plethora of methods have been proposed over the past years. The approaches that have been reported so far can be mainly categorized into two classes: distance-based approaches and Bayesian approaches. Although these methods have been widely used in many scenarios and shown promising performance with their distinct superiorities, being overconfident on out-of-distribution examples still poses challenges for the deployment of these techniques in real-world applications. In this study we investigated a number of consensus strategies in order to combine both distance-based and Bayesian approaches together with post-hoc calibration for improved uncertainty quantification in QSAR (Quantitative Structure-Activity Relationship) regression modeling. We employed a set of criteria to quantitatively assess the ranking and calibration ability of these models. Experiments based on 24 bioactivity datasets were designed to make critical comparison between the model we proposed and other well-studied baseline models. Our findings indicate that the hybrid framework proposed by us can robustly enhance the model ability of ranking absolute errors. Together with post-hoc calibration on the validation set, we show that well-calibrated uncertainty quantification results can be obtained in domain shift settings. The complementarity between different methods is also conceptually analyzed.
| S-EPMC8454160 | biostudies-literature
Project description:Pancreatic cancer is one of the most adverse diseases and it is very difficult to treat because the cancer cells formed in the pancreas intertwine themselves with nearby blood vessels and connective tissue. Hence, the surgical procedure of treatment becomes complicated and it does not always lead to a cure. Histopathological diagnosis is the usual approach for cancer diagnosis. However, the pancreas remains so deep inside the body that experts sometimes struggle to detect cancer in it. Computer-aided diagnosis can come to the aid of pathologists in this scenario. It assists experts by supporting their diagnostic decisions. In this research, we carried out a deep learning-based approach to analyze histopathology images. We collected whole-slide images of KPC mice to implement this work. The pancreatic abnormalities observed in KPC mice develop similar histological features to human beings. We created random patches from whole-slide images. Then, a convolutional autoencoder framework was used to embed these patches into an integrated latent space. We applied 'information maximization', a deep learning clustering technique to cluster the identical patches in an unsupervised manner since our dataset does not have annotation. Moreover, Uniform manifold approximation and projection, a nonlinear dimension reduction technique was utilized to visualize the embedded patches in a 2-dimensional space. Finally, we calculated a few internal cluster validation metrics to determine the optimal cluster set. Our work concentrated on patch-based anomaly detection in the whole slide histopathology images of KPC mice.
| S-EPMC10707605 | biostudies-literature
Project description:Human DNA sequencing has revealed numerous single nucleotide variants associated with complex diseases. Researchers have shown that these variants have potential effects on protein function, one of which is to disrupt protein phosphorylation. Based on conventional machine learning algorithms, several computational methods for predicting phospho-variants have been developed, but their performance still leaves considerable room for improvement. In recent years, deep learning has been successfully applied in biological sequence analysis with its efficient sequence pattern learning ability, which provides a powerful tool for improving phospho-variant prediction based on protein sequence information. In the study, we present PhosVarDeep, a novel unified deep-learning framework for phospho-variant prediction. PhosVarDeep takes reference and variant sequences as inputs and adopts a Siamese-like CNN architecture containing two identical subnetworks and a prediction module. In each subnetwork, general phosphorylation sequence features are extracted by a pre-trained sequence feature encoding network and then fed into a CNN module for capturing variant-aware phosphorylation sequence features. After that, a prediction module is introduced to integrate the outputs of the two subnetworks and generate the prediction results of phospho-variants. Comprehensive experimental results on phospho-variant data demonstrates that our method significantly improves the prediction performance of phospho-variants and compares favorably with existing conventional machine learning methods.
| S-EPMC8929166 | biostudies-literature
Project description:Deep learning models have been widely used in many supervised learning applications. However, these models suffer from overfitting due to various types of uncertainty with deteriorating performance when facing data biases, class imbalance, or noise propagation. The Information-Set Deep learning (ISDL) architectures with four variants are developed by integrating information set theory and deep learning principles to address the critical problem of the absence of robust deep learning models. There is a description of the ISDL architectures, learning algorithms, and analytic workflows. The performance of the ISDL models and standard architectures is evaluated using a noise-corrupted benchmark dataset. The experimental results show that the ISDL models can efficiently handle noise-dominated uncertainty and outperform peer architectures.
| S-EPMC10023670 | biostudies-literature
Project description:The interactions between non-coding RNAs (ncRNAs) and proteins play an important role in many biological processes, and their biological functions are primarily achieved by binding with a variety of proteins. High-throughput biological techniques are used to identify protein molecules bound with specific ncRNA, but they are usually expensive and time consuming. Deep learning provides a powerful solution to computationally predict RNA-protein interactions. In this work, we propose the RPI-SAN model by using the deep-learning stacked auto-encoder network to mine the hidden high-level features from RNA and protein sequences and feed them into a random forest (RF) model to predict ncRNA binding proteins. Stacked assembling is further used to improve the accuracy of the proposed method. Four benchmark datasets, including RPI2241, RPI488, RPI1807, and NPInter v2.0, were employed for the unbiased evaluation of five established prediction tools: RPI-Pred, IPMiner, RPISeq-RF, lncPro, and RPI-SAN. The experimental results show that our RPI-SAN model achieves much better performance than other methods, with accuracies of 90.77%, 89.7%, 96.1%, and 99.33%, respectively. It is anticipated that RPI-SAN can be used as an effective computational tool for future biomedical researches and can accurately predict the potential ncRNA-protein interacted pairs, which provides reliable guidance for biological research.
| S-EPMC5992449 | biostudies-literature
Project description:Radiological methodologies, such as chest x-rays and CT, are widely employed to help diagnose and monitor COVID-19 disease. COVID-19 displays certain radiological patterns easily detectable by X-rays of the chest. Therefore, radiologists can investigate these patterns for detecting coronavirus disease. However, this task is time-consuming and needs lots of trial and error. One of the main solutions to resolve this issue is to apply intelligent techniques such as deep learning (DL) models to automatically analyze the chest X-rays. Nevertheless, fine-tuning of architecture and hyperparameters of DL models is a complex and time-consuming procedure. In this paper, we propose an effective method to detect COVID-19 disease by applying convolutional neural network (CNN) to the chest X-ray images. To improve the accuracy of the proposed method, the last Softmax CNN layer is replaced with a K -nearest neighbors (KNN) classifier which takes into account the agreement of the neighborhood labeling. Moreover, we develop a novel evolutionary algorithm by improving the basic version of competitive swarm optimizer. To this end, three powerful evolutionary operators: Cauchy Mutation (CM), Evolutionary Boundary Constraint Handling (EBCH), and tent chaotic map are incorporated into the search process of the proposed evolutionary algorithm to speed up its convergence and make an excellent balance between exploration and exploitation phases. Then, the proposed evolutionary algorithm is used to automatically achieve the optimal values of CNN's hyperparameters leading to a significant improvement in the classification accuracy of the proposed method. Comprehensive comparative results reveal that compared with current models in the literature, the proposed method performs significantly more efficient.
| S-EPMC8966159 | biostudies-literature
Project description:DNA-binding proteins (DBPs) play pivotal roles in many biological functions such as alternative splicing, RNA editing, and methylation. Many traditional machine learning (ML) methods and deep learning (DL) methods have been proposed to predict DBPs. However, these methods either rely on manual feature extraction or fail to capture long-term dependencies in the DNA sequence. In this paper, we propose a method, called PDBP-Fusion, to identify DBPs based on the fusion of local features and long-term dependencies only from primary sequences. We utilize convolutional neural network (CNN) to learn local features and use bi-directional long-short term memory network (Bi-LSTM) to capture critical long-term dependencies in context. Besides, we perform feature extraction, model training, and model prediction simultaneously. The PDBP-Fusion approach can predict DBPs with 86.45% sensitivity, 79.13% specificity, 82.81% accuracy, and 0.661 MCC on the PDB14189 benchmark dataset. The MCC of our proposed methods has been increased by at least 9.1% compared to other advanced prediction models. Moreover, the PDBP-Fusion also gets superior performance and model robustness on the PDB2272 independent dataset. It demonstrates that the PDBP-Fusion can be used to predict DBPs from sequences accurately and effectively; the online server is at http://119.45.144.26:8080/PDBP-Fusion/.
| S-EPMC8101451 | biostudies-literature
Project description:We present a novel Deep Learning method for the Unsupervised Clustering of DNA Sequences (DeLUCS) that does not require sequence alignment, sequence homology, or (taxonomic) identifiers. DeLUCS uses Frequency Chaos Game Representations (FCGR) of primary DNA sequences, and generates "mimic" sequence FCGRs to self-learn data patterns (genomic signatures) through the optimization of multiple neural networks. A majority voting scheme is then used to determine the final cluster assignment for each sequence. The clusters learned by DeLUCS match true taxonomic groups for large and diverse datasets, with accuracies ranging from 77% to 100%: 2,500 complete vertebrate mitochondrial genomes, at taxonomic levels from sub-phylum to genera; 3,200 randomly selected 400 kbp-long bacterial genome segments, into clusters corresponding to bacterial families; three viral genome and gene datasets, averaging 1,300 sequences each, into clusters corresponding to virus subtypes. DeLUCS significantly outperforms two classic clustering methods (K-means++ and Gaussian Mixture Models) for unlabelled data, by as much as 47%. DeLUCS is highly effective, it is able to cluster datasets of unlabelled primary DNA sequences totalling over 1 billion bp of data, and it bypasses common limitations to classification resulting from the lack of sequence homology, variation in sequence length, and the absence or instability of sequence annotations and taxonomic identifiers. Thus, DeLUCS offers fast and accurate DNA sequence clustering for previously intractable datasets.
| S-EPMC8782307 | biostudies-literature