Formula Graph Self-Attention Network for Representation-Domain Independent Materials Discovery.
Ontology highlight
ABSTRACT:
SUBMITTER: Ihalage A
PROVIDER: S-EPMC9218748 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The use of high-throughput omics technologies is becoming increasingly popular in all facets of biomedical science. The mRNA sequencing (RNA-seq) method reports quantitative measures of more than tens of thousands of biological features. It provides a more comprehensive molecular perspective of studied cancer mechanisms compared to traditional approaches. Graph-based learning models have been proposed to learn important hidden representations from gene expression data and network structure to improve cancer outcome prediction, patient stratification, and cell clustering. However, these graph-based methods cannot rank the importance of the different neighbors for a particular sample in the downstream cancer subtype analyses. In this study, we introduce omicsGAT, a graph attention network (GAT) model to integrate graph-based learning with an attention mechanism for RNA-seq data analysis. The multi-head attention mechanism in omicsGAT can more effectively secure information of a particular sample by assigning different attention coefficients to its neighbors. Comprehensive experiments on The Cancer Genome Atlas (TCGA) breast cancer and bladder cancer bulk RNA-seq data and two single-cell RNA-seq datasets validate that (1) the proposed model can effectively integrate neighborhood information of a sample and learn an embedding vector to improve disease phenotype prediction, cancer patient stratification, and cell clustering of the sample and (2) the attention matrix generated from the multi-head attention coefficients provides more useful information compared to the sample correlation-based adjacency matrix. From the results, we can conclude that some neighbors play a more important role than others in cancer subtype analyses of a particular sample based on the attention coefficient.
| S-EPMC9499656 | biostudies-literature
Project description:Assessing the synthesizability of inorganic materials is a grand challenge for accelerating their discovery using computations. Synthesis of a material is a complex process that depends not only on its thermodynamic stability with respect to others, but also on factors from kinetics, to advances in synthesis techniques, to the availability of precursors. This complexity makes the development of a general theory or first-principles approach to synthesizability currently impractical. Here we show how an alternative pathway to predicting synthesizability emerges from the dynamics of the materials stability network: a scale-free network constructed by combining the convex free-energy surface of inorganic materials computed by high-throughput density functional theory and their experimental discovery timelines extracted from citations. The time-evolution of the underlying network properties allows us to use machine-learning to predict the likelihood that hypothetical, computer-generated materials will be amenable to successful experimental synthesis.
| S-EPMC6494829 | biostudies-other
Project description:MotivationAsthma is a heterogeneous disease where various subtypes are established and molecular biomarkers of the subtypes are yet to be discovered. Recent availability of multi-omics data paved a way to discover molecular biomarkers for the subtypes. However, multi-omics biomarker discovery is challenging because of the complex interplay between different omics layers.ResultsWe propose a deep attention model named Gene-level biomarker discovery from multi-Omics data using graph ATtention neural network (GOAT) for identifying molecular biomarkers for eosinophilic asthma subtypes with multi-omics data. GOAT identifies genes that discriminate subtypes using a graph neural network by modeling complex interactions among genes as the attention mechanism in the deep learning model. In experiments with multi-omics profiles of the COREA (Cohort for Reality and Evolution of Adult Asthma in Korea) asthma cohort of 300 patients, GOAT outperforms existing models and suggests interpretable biological mechanisms underlying asthma subtypes. Importantly, GOAT identified genes that are distinct only in terms of relationship with other genes through attention. To better understand the role of biomarkers, we further investigated two transcription factors, CTNNB1 and JUN, captured by GOAT. We were successful in showing the role of the transcription factors in eosinophilic asthma pathophysiology in a network propagation and transcriptional network analysis, which were not distinct in terms of gene expression level differences.Availability and implementationSource code is available https://github.com/DabinJeong/Multi-omics_biomarker. The preprocessed data underlying this article is accessible in data folder of the github repository. Raw data are available in Multi-Omics Platform at http://203.252.206.90:5566/, and it can be accessible when requested.
| S-EPMC10547929 | biostudies-literature
Project description:In addition to being the core quantity in density-functional theory, the charge density can be used in many tertiary analyses in materials sciences from bonding to assigning charge to specific atoms. The charge density is data-rich since it contains information about all the electrons in the system. With the increasing prevalence of machine-learning tools in materials sciences, a data-rich object like the charge density can be utilized in a wide range of applications. The database presented here provides a modern and user-friendly interface for a large and continuously updated collection of charge densities as part of the Materials Project. In addition to the charge density data, we provide the theory and code for changing the representation of the charge density which should enable more advanced machine-learning studies for the broader community.
| S-EPMC9616845 | biostudies-literature
Project description:Cocrystal engineering have been widely applied in pharmaceutical, chemistry and material fields. However, how to effectively choose coformer has been a challenging task on experiments. Here we develop a graph neural network (GNN) based deep learning framework to quickly predict formation of the cocrystal. In order to capture main driving force to crystallization from 6819 positive and 1052 negative samples reported by experiments, a feasible GNN framework is explored to integrate important prior knowledge into end-to-end learning on the molecular graph. The model is strongly validated against seven competitive models and three challenging independent test sets involving pharmaceutical cocrystals, π-π cocrystals and energetic cocrystals, exhibiting superior performance with accuracy higher than 96%, confirming its robustness and generalization. Furthermore, one new energetic cocrystal predicted is successfully synthesized, showcasing high potential of the model in practice. All the data and source codes are available at https://github.com/Saoge123/ccgnet for aiding cocrystal community.
| S-EPMC8511140 | biostudies-literature
Project description:Supervised learning method requires a large volume of annotated datasets. Collecting such datasets is time-consuming and expensive. Until now, very few annotated COVID-19 imaging datasets are available. Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method should be sensitive enough to detect deviation from normal-appearing tissue of each anatomical region; here, anatomy is the context. We introduce a novel approach with two levels of self-supervised representation learning objectives: one on the regional anatomical level and another on the patient-level. We use graph neural networks to incorporate the relationship between different anatomical regions. The structure of the graph is informed by anatomical correspondences between each patient and an anatomical atlas. In addition, the graph representation has the advantage of handling any arbitrarily sized image in full resolution. Experiments on large-scale Computer Tomography (CT) datasets of lung images show that our approach compares favorably to baseline methods that do not account for the context. We use the learnt embedding to quantify the clinical progression of COVID-19 and show that our method generalizes well to COVID-19 patients from different hospitals. Qualitative results suggest that our model can identify clinically relevant regions in the images.
| S-EPMC8513790 | biostudies-literature
Project description:A methodological framework is presented for the graph theoretical interpretation of NMR data of protein interactions. The proposed analysis generalizes the idea of network representations of protein structures by expanding it to protein interactions. This approach is based on regularization of residue-resolved NMR relaxation times and chemical shift data and subsequent construction of an adjacency matrix that represents the underlying protein interaction as a graph or network. The network nodes represent protein residues. Two nodes are connected if two residues are functionally correlated during the protein interaction event. The analysis of the resulting network enables the quantification of the importance of each amino acid of a protein for its interactions. Furthermore, the determination of the pattern of correlations between residues yields insights into the functional architecture of an interaction. This is of special interest for intrinsically disordered proteins, since the structural (three-dimensional) architecture of these proteins and their complexes is difficult to determine. The power of the proposed methodology is demonstrated at the example of the interaction between the intrinsically disordered protein osteopontin and its natural ligand heparin.
| S-EPMC5338233 | biostudies-literature
Project description:Scalar coupling constant (SCC), directly measured by nuclear magnetic resonance (NMR) spectroscopy, is a key parameter for molecular structure analysis, and widely used to predict unknown molecular structure. Restricted by the high cost of NMR experiments, it is impossible to measure the SCC of unknown molecules on a large scale. Using density functional theory (DFT) to theoretically calculate the SCC of molecules is incredibly challenging, due to the cost of substantial computational time and space. Graph neural networks (GNN) of artificial intelligence (AI) have great potential in constructing molecul ar-like topology models, which endows them the ability to rapidly predict SCC through data-driven machine learning methods, and avoiding time-consuming quantum chemical calculations. With a priori knowledge of angles, we propose a graph angle-attention neural network (GAANN) model to predict SCC by means of some easily accessible related information. GAANN, with a multilayer message-passing network and a self-attention mechanism, can accurately simulate the molecular-like topological structure and predict molecular properties. Our simulations show that the prediction accuracy by GAANN, with the log(MAE) = -2.52, is close to that by DFT calculations. Different from conventional AI methods, GAANN combining the AI method with quantum chemistry theory (Karplus equation) has a strong physicochemical interpretability about angles. From an AI perspective, we find that bond angle has the highest correlation with the SCC among all angle features (dihedral angle, bond angle, geometric angles) about multiple coupling types in the small molecule datasets.
| S-EPMC8455698 | biostudies-literature
Project description:MotivationProtein-protein interaction (PPI) networks and transcriptional regulatory networks are critical in regulating cells and their signaling. A thorough understanding of PPIs can provide more insights into cellular physiology at normal and disease states. Although numerous methods have been proposed to predict PPIs, it is still challenging for interaction prediction between unknown proteins. In this study, a novel neural network named AFTGAN was constructed to predict multi-type PPIs. Regarding feature input, ESM-1b embedding containing much biological information for proteins was added as a protein sequence feature besides amino acid co-occurrence similarity and one-hot coding. An ensemble network was also constructed based on a transformer encoder containing an AFT module (performing the weight operation on vital protein sequence feature information) and graph attention network (extracting the relational features of protein pairs) for the part of the network framework.ResultsThe experimental results showed that the Micro-F1 of the AFTGAN based on three partitioning schemes (BFS, DFS and the random mode) on the SHS27K and SHS148K datasets was 0.685, 0.711 and 0.867, as well as 0.745, 0.819 and 0.920, respectively, all higher than that of other popular methods. In addition, the experimental comparisons confirmed the performance superiority of the proposed model for predicting PPIs of unknown proteins on the STRING dataset.Availability and implementationThe source code is publicly available at https://github.com/1075793472/AFTGAN.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC9897180 | biostudies-literature
Project description:MotivationDrug-drug interaction (DDI) prediction is a challenging problem in pharmacology and clinical applications. With the increasing availability of large biomedical databases, large-scale biological knowledge graphs containing drug information have been widely used for DDI prediction. However, large knowledge graphs inevitably suffer from data noise problems, which limit the performance and interpretability of models based on the knowledge graph. Recent studies attempt to improve models by introducing inductive bias through an attention mechanism. However, they all only depend on the topology of entity nodes independently to generate fixed attention pathways, without considering the semantic diversity of entity nodes in different drug pair links. This makes it difficult for models to select more meaningful nodes to overcome data quality limitations and make more interpretable predictions.ResultsTo address this issue, we propose a Link-aware Graph Attention method for DDI prediction, called LaGAT, which is able to generate different attention pathways for drug entities based on different drug pair links. For a drug pair link, the LaGAT uses the embedding representation of one of the drugs as a query vector to calculate the attention weights, thereby selecting the appropriate topological neighbor nodes to obtain the semantic information of the other drug. We separately conduct experiments on binary and multi-class classification and visualize the attention pathways generated by the model. The results prove that LaGAT can better capture semantic relationships and achieves remarkably superior performance over both the classical and state-of-the-art models on DDI prediction.Availabilityand implementationThe source code and data are available at https://github.com/Azra3lzz/LaGAT.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC9750103 | biostudies-literature