Multi-instance learning of graph neural networks for aqueous pKa prediction.
Ontology highlight
ABSTRACT: Motivation
The acid dissociation constant (pKa) is a critical parameter to reflect the ionization ability of chemical compounds and is widely applied in a variety of industries. However, the experimental determination of pKa is intricate and time-consuming, especially for the exact determination of micro pKa information at the atomic level. Hence, a fast and accurate prediction of pKa values of chemical compounds is of broad interest.Results
Here, we compiled a large scale pKa dataset containing 16595 compounds with 17489 pKa values. Based on this dataset, a novel pK a prediction model, named Graph-pKa, was established using graph neural networks. Graph-pKa performed well on the prediction of macro pK a values, with a mean absolute error around 0.55 and a coefficient of determination around 0.92 on the test dataset. Furthermore, combining multi-instance learning, Graph-pKa was also able to automatically deconvolute the predicted macro pKa into discrete micro pK a values.Availability
The Graph-pK a model is now freely accessible via a web-based interface (https://pka.simm.ac.cn/).Supplementary information
Supplementary data are available at Bioinformatics online.
SUBMITTER: Xiong J
PROVIDER: S-EPMC8756178 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:We investigate the potential of graph neural networks for transfer learning and improving molecular property prediction on sparse and expensive to acquire high-fidelity data by leveraging low-fidelity measurements as an inexpensive proxy for a targeted property of interest. This problem arises in discovery processes that rely on screening funnels for trading off the overall costs against throughput and accuracy. Typically, individual stages in these processes are loosely connected and each one generates data at different scale and fidelity. We consider this setup holistically and demonstrate empirically that existing transfer learning techniques for graph neural networks are generally unable to harness the information from multi-fidelity cascades. Here, we propose several effective transfer learning strategies and study them in transductive and inductive settings. Our analysis involves a collection of more than 28 million unique experimental protein-ligand interactions across 37 targets from drug discovery by high-throughput screening and 12 quantum properties from the dataset QMugs. The results indicate that transfer learning can improve the performance on sparse tasks by up to eight times while using an order of magnitude less high-fidelity training data. Moreover, the proposed methods consistently outperform existing transfer learning strategies for graph-structured data on drug discovery and quantum mechanics datasets.
| S-EPMC11258334 | biostudies-literature
Project description:Recent breakthrough in spatial transcriptomics has brought great opportunities for exploring gene regulatory networks (GRNs) from a brand-new perspective. Especially, the local expression patterns and spatio-temporal regulation mechanisms captured by spatial expression images allow more delicate delineation of the interplay between transcript factors and their target genes. However, the complexity and size of spatial image collections pose significant challenges to GRN inference using image-based methods. Extracting regulatory information from expression images is difficult due to the lack of supervision and the multi-instance nature of the problem, where a gene often corresponds to multiple images captured from different views. While graph models, particularly graph neural networks, have emerged as a promising method for leveraging underlying structure information from known GRNs, incorporating expression images into graphs is not straightforward. To address these challenges, we propose a two-stage approach, MIGGRI, for capturing comprehensive regulatory patterns from image collections for each gene and known interactions. Our approach involves a multi-instance graph neural network (GNN) model for GRN inference, which first extracts gene regulatory features from spatial expression images via contrastive learning, and then feeds them to a multi-instance GNN for semi-supervised learning. We apply our approach to a large set of Drosophila embryonic spatial gene expression images. MIGGRI achieves outstanding performance in the inference of GRNs for early eye development and mesoderm development of Drosophila, and shows robustness in the scenarios of missing image information. Additionally, we perform interpretable analysis on image reconstruction and functional subgraphs that may reveal potential pathways or coordinate regulations. By leveraging the power of graph neural networks and the information contained in spatial expression images, our approach has the potential to advance our understanding of gene regulation in complex biological systems.
| S-EPMC10659162 | biostudies-literature
Project description:Predictive modeling of toxicity is a crucial step in the drug discovery pipeline. It can help filter out molecules with a high probability of failing in the early stages of de novo drug design. Thus, several machine learning (ML) models have been developed to predict the toxicity of molecules by combining classical ML techniques or deep neural networks with well-known molecular representations such as fingerprints or 2D graphs. But the more natural, accurate representation of molecules is expected to be defined in physical 3D space like in ab initio methods. Recent studies successfully used equivariant graph neural networks (EGNNs) for representation learning based on 3D structures to predict quantum-mechanical properties of molecules. Inspired by this, we investigated the performance of EGNNs to construct reliable ML models for toxicity prediction. We used the equivariant transformer (ET) model in TorchMD-NET for this. Eleven toxicity data sets taken from MoleculeNet, TDCommons, and ToxBenchmark have been considered to evaluate the capability of ET for toxicity prediction. Our results show that ET adequately learns 3D representations of molecules that can successfully correlate with toxicity activity, achieving good accuracies on most data sets comparable to state-of-the-art models. We also test a physicochemical property, namely, the total energy of a molecule, to inform the toxicity prediction with a physical prior. However, our work suggests that these two properties can not be related. We also provide an attention weight analysis for helping to understand the toxicity prediction in 3D space and thus increase the explainability of the ML model. In summary, our findings offer promising insights considering 3D geometry information via EGNNs and provide a straightforward way to integrate molecular conformers into ML-based pipelines for predicting and investigating toxicity prediction in physical space. We expect that in the future, especially for larger, more diverse data sets, EGNNs will be an essential tool in this domain.
| S-EPMC10583285 | biostudies-literature
Project description:Deep learning has been applied to magnetic resonance imaging (MRI) for a variety of purposes, ranging from the acceleration of image acquisition and image denoising to tissue segmentation and disease diagnosis. Convolutional neural networks have been particularly useful for analyzing MRI data due to the regularly sampled spatial and temporal nature of the data. However, advances in the field of brain imaging have led to network- and surface-based analyses that are often better represented in the graph domain. In this analysis, we propose a general purpose cortical segmentation method that, given resting-state connectivity features readily computed during conventional MRI pre-processing and a set of corresponding training labels, can generate cortical parcellations for new MRI data. We applied recent advances in the field of graph neural networks to the problem of cortical surface segmentation, using resting-state connectivity to learn discrete maps of the human neocortex. We found that graph neural networks accurately learn low-dimensional representations of functional brain connectivity that can be naturally extended to map the cortices of new datasets. After optimizing over algorithm type, network architecture, and training features, our approach yielded mean classification accuracies of 79.91% relative to a previously published parcellation. We describe how some hyperparameter choices including training and testing data duration, network architecture, and algorithm choice affect model performance.
| S-EPMC8739886 | biostudies-literature
Project description:High-throughput sequencing technologies have generated massive protein sequences, but the annotations of protein sequences highly rely on the low-throughput and expensive biological experiments. Therefore, accurate and fast computational alternatives are needed to infer functional knowledge from protein sequences. The gene ontology (GO) directed acyclic graph (DAG) contains the hierarchical relationships between GO terms but is hard to be integrated into machine learning algorithms for functional predictions. We developed a deep learning system named PANDA2 to predict protein functions, which used the cutting-edge graph neural network to model the topology of the GO DAG and integrated the features generated by transformer protein language models. Compared with the top 10 methods in CAFA3, PANDA2 ranked first in cellular component ontology (CCO), tied first in biological process ontology (BPO) but had a higher coverage rate, and second in molecular function ontology (MFO). Compared with other recently-developed cutting-edge predictors DeepGOPlus, GOLabeler, and DeepText2GO, and benchmarked on another independent dataset, PANDA2 ranked first in CCO, first in BPO, and second in MFO. PANDA2 can be freely accessed from http://dna.cs.miami.edu/PANDA2/.
| S-EPMC8808544 | biostudies-literature
Project description:Link prediction in biomedical graphs has several important applications including predicting Drug-Target Interactions (DTI), Protein-Protein Interaction (PPI) prediction and Literature-Based Discovery (LBD). It can be done using a classifier to output the probability of link formation between nodes. Recently several works have used neural networks to create node representations which allow rich inputs to neural classifiers. Preliminary works were done on this and report promising results. However they did not use realistic settings like time-slicing, evaluate performances with comprehensive metrics or explain when or why neural network methods outperform. We investigated how inputs from four node representation algorithms affect performance of a neural link predictor on random- and time-sliced biomedical graphs of real-world sizes (??6 million edges) containing information relevant to DTI, PPI and LBD. We compared the performance of the neural link predictor to those of established baselines and report performance across five metrics.In random- and time-sliced experiments when the neural network methods were able to learn good node representations and there was a negligible amount of disconnected nodes, those approaches outperformed the baselines. In the smallest graph (??15,000 edges) and in larger graphs with approximately 14% disconnected nodes, baselines such as Common Neighbours proved a justifiable choice for link prediction. At low recall levels (??0.3) the approaches were mostly equal, but at higher recall levels across all nodes and average performance at individual nodes, neural network approaches were superior. Analysis showed that neural network methods performed well on links between nodes with no previous common neighbours; potentially the most interesting links. Additionally, while neural network methods benefit from large amounts of data, they require considerable amounts of computational resources to utilise them.Our results indicate that when there is enough data for the neural network methods to use and there are a negligible amount of disconnected nodes, those approaches outperform the baselines. At low recall levels the approaches are mostly equal but at higher recall levels and average performance at individual nodes, neural network approaches are superior. Performance at nodes without common neighbours which indicate more unexpected and perhaps more useful links account for this.
| S-EPMC5963080 | biostudies-other
Project description:The efficient calculation of nucleation collective variables (CVs) is one of the main limitations to the application of enhanced sampling methods to the investigation of nucleation processes in realistic environments. Here we discuss the development of a graph-based model for the approximation of nucleation CVs that enables orders-of-magnitude gains in computational efficiency in the on-the-fly evaluation of nucleation CVs. By performing simulations on a nucleating colloidal system mimicking a multistep nucleation process from solution, we assess the model's efficiency in both postprocessing and on-the-fly biasing of nucleation trajectories with pulling, umbrella sampling, and metadynamics simulations. Moreover, we probe and discuss the transferability of graph-based models of nucleation CVs across systems using the model of a CV based on sixth-order Steinhardt parameters trained on a colloidal system to drive the nucleation of crystalline copper from its melt. Our approach is general and potentially transferable to more complex systems as well as to different CVs.
| S-EPMC10902841 | biostudies-literature
Project description:Graph neural network (GNN)-based deep learning (DL) models have been widely implemented to predict the experimental aqueous solvation free energy, while its prediction accuracy has reached a plateau partly due to the scarcity of available experimental data. In order to tackle this challenge, we first build a large and diverse calculated data set Frag20-Aqsol-100K of aqueous solvation free energy with reasonable computational cost and accuracy via electronic structure calculations with continuum solvent models. Then, we develop a novel 3D atomic feature-based GNN model with the principal neighborhood aggregation (PNAConv) and demonstrate that 3D atomic features obtained from molecular mechanics-optimized geometries can significantly improve the learning power of GNN models in predicting calculated solvation free energies. Finally, we employ a transfer learning strategy by pre-training our DL model on Frag20-Aqsol-100K and fine-tuning it on the small experimental data set, and the fine-tuned model A3D-PNAConv-FT achieves the state-of-the-art prediction on the FreeSolv data set with a root-mean-squared error of 0.719 kcal/mol and a mean-absolute error of 0.417 kcal/mol using random data splits. These results indicate that integrating molecular modeling and DL would be a promising strategy to develop robust prediction models in molecular science. The source code and data are accessible at: https://yzhang.hpc.nyu.edu/IMA.
| S-EPMC9038704 | biostudies-literature
Project description:Gene function annotation is the main challenge in the post genome era, which is an important part of the genome annotation. The sequencing of the human genome project produces a whole genome data, providing abundant biological information for the study of gene function annotation. However, to obtain useful knowledge from a large amount of data, a potential strategy is to apply machine learning methods to mine these data and predict gene function. In this study, we improved multi-instance hierarchical clustering by using gene ontology hierarchy to annotate gene function, which combines gene ontology hierarchy with multi-instance multi-label learning frame structure. Then, we used multi-label support vector machine (MLSVM) and multi-label k-nearest neighbor (MLKNN) algorithm to predict the function of gene. Finally, we verified our method in four yeast expression datasets. The performance of the simulated experiments proved that our method is efficient.
| S-EPMC9083914 | biostudies-literature
Project description:Natural vibrational frequencies of proteins help to correlate functional shifts with sequence or geometric variations that lead to negligible changes in protein structures, such as point mutations related to disease lethality or medication effectiveness. Normal mode analysis is a well-known approach to accurately obtain protein natural frequencies. However, it is not feasible when high-resolution protein structures are not available or time consuming to obtain. Here we provide a machine learning model to directly predict protein frequencies from primary amino acid sequences and low-resolution structural features such as contact or distance maps. We utilize a graph neural network called principal neighborhood aggregation, trained with the structural graphs and normal mode frequencies of more than 34 000 proteins from the protein data bank. combining with existing contact/distance map prediction tools, this approach enables an end-to-end prediction of the frequency spectrum of a protein given its primary sequence.
| S-EPMC9189858 | biostudies-literature