Representation Of Molecular Structure Research Articles

Optimizing GNN Architectures Through Nonlinear Activation Functions for Potent Molecular Property Prediction

Accurate predictions of molecular properties are crucial for advancements in drug discovery and materials science. However, this task is complex and requires effective representations of molecular structures. Recently, Graph Neural Networks (GNNs) have emerged as powerful tools for this purpose, demonstrating significant potential in modeling molecular data. Despite advancements in GNN predictive performance, existing methods lack clarity on how architectural choices, particularly activation functions, affect training dynamics and inference stages in interpreting the predicted results. To address this gap, this paper introduces a novel activation function called the Sine Linear Unit (SLU), aimed at enhancing the predictive capabilities of GNNs in the context of molecular property prediction. To demonstrate the effectiveness of SLU within GNN architecture, we conduct experiments on diverse molecular datasets encompassing various regression and classification tasks. Our findings indicate that SLU consistently outperforms traditional activation functions on hydration free energy (FreeSolv), inhibitory binding of human β secretase (BACE), and blood brain barrier penetration (BBBP), achieving the superior performance in each task, with one exception on the GCN model using the QM9 data set. These results underscore SLU’s potential to significantly improve prediction accuracy, making it a valuable addition to the field of molecular modeling.

HydraScreen: A Generalizable Structure-Based Deep Learning Approach to Drug Discovery.

We propose HydraScreen, a deep-learning framework for safe and robust accelerated drug discovery. HydraScreen utilizes a state-of-the-art 3D convolutional neural network designed for the effective representation of molecular structures and interactions in protein-ligand binding. We designed an end-to-end pipeline for high-throughput screening and lead optimization, targeting applications in structure-based drug design. We assessed our approach using established public benchmarks based on the CASF-2016 core set, achieving top-tier results in affinity and pose prediction (Pearson's r = 0.86, RMSE = 1.15, Top-1 = 0.95). We introduced a novel approach for interaction profiling, aimed at detecting potential biases within both the model and data sets. This approach not only enhanced interpretability but also reinforced the impartiality of our methodology. Finally, we demonstrated HydraScreen's ability to generalize effectively across novel proteins and ligands through a temporal split. We also provide insights into potential avenues for future development aimed at enhancing the robustness of machine learning scoring functions. HydraScreen (accessible at http://hydrascreen.ro5.ai/paper) provides a user-friendly GUI and a public API, facilitating the easy-access assessment of protein-ligand complexes.

3DSGIMD: An accurate and interpretable molecular property prediction method using 3D spatial graph focusing network and structure-based feature fusion

A comprehensive representation of molecular structure is essential for establishing accurate and reliable molecular property prediction models. However, fully extracting and learning intrinsic molecular structure information, especially spatial structure features, remains a challenging task, leading that many molecular property prediction models still have no enough accuracy for the real application. In this study, we developed an innovative and interpretable deep learning method, termed 3DSGIMD, which predicted the molecular properties by integrating and learning the spatial structure and substructure information of molecules at multiple levels, and generated the focusing weights by aggregating spatial and adjacency information of molecules to improve understanding of prediction results. We evaluated the model on 10 public datasets and 14 cell-based phenotypic screening datasets. Extensive experimental results indicated that 3DSGIMD achieved superior or comparable predictive performance compared with some existing models, and the individually designed components contributed significantly to the advanced performance of the model. In addition, we also provided insight into the interpretability of our model via visualizing the focusing weights and perturbation analysis, and the results showed that 3DSGIMD can pinpoint crucial local structures and bits of molecular descriptors associated with the predicted properties. In summary, 3DSGIMD is a competitive molecular property prediction method that holds the potential to aid drug design and optimization.

Designing and developing Intuitionistic Fuzzy Logic Toolbox in MATLAB: Membership and non-membership functions gallery

The authors have designed and developed algorithms for pattern recognition and clustering techniques using intuitionistic fuzzy (IF) sets, IF operators, IF logic (IFL) – shortest path in networks using IF graphs and IF hypergraphs – video processing using temporal IF sets, RGB image representation through IF index matrices, and molecular structure representation through IF directed hypergraphs. The three major steps involved in the above-said modeling processes via IFSs are (i) intuitionistic fuzzification, (ii) modification of membership and non- membership values (using IF logic/operators/rules/relations) and (iii) intuitionistic defuzzification. While developing these algorithms, parameter tuning was one of the major limitations, and hence specific values were assigned to complete the running process. To overcome this, it is necessary to introduce a toolbox in MATLAB so that the users can select the appropriate tools and parameterize them. Hence, in the long process of contributing a full-pledged intuitionistic fuzzy logic toolbox, namely IFL Toolbox in MATLAB, the membership and non-membership functions gallery has been developed initially, as one of the modules which is the foundation for any IFL control system. This module contains functions, codes, examples and figures/graphs, which will be available on the MATLAB creation page. The proposed module is compared with the existing fuzzy logic toolbox in MATLAB and verified.

Gram matrix: an efficient representation of molecular conformation and learning objective for molecular pretraining.

Accurate prediction of molecular properties is fundamental in drug discovery and development, providing crucial guidance for effective drug design. A critical factor in achieving accurate molecular property prediction lies in the appropriate representation of molecular structures. Presently, prevalent deep learning-based molecular representations rely on 2D structure information as the primary molecular representation, often overlooking essential three-dimensional (3D) conformational information due to the inherent limitations of 2D structures in conveying atomic spatial relationships. In this study, we propose employing the Gram matrix as a condensed representation of 3D molecular structures and for efficient pretraining objectives. Subsequently, we leverage this matrix to construct a novel molecular representation model, Pre-GTM, which inherently encapsulates 3D information. The model accurately predicts the 3D structure of a molecule by estimating the Gram matrix. Our findings demonstrate that Pre-GTM model outperforms the baseline Graphormer model and other pretrained models in the QM9 and MoleculeNet quantitative property prediction task. The integration of the Gram matrix as a condensed representation of 3D molecular structure, incorporated into the Pre-GTM model, opens up promising avenues for its potential application across various domains of molecular research, including drug design, materials science, and chemical engineering.

MvMRL: a multi-view molecular representation learning method for molecular property prediction.

Effective molecular representation learning is very important for Artificial Intelligence-driven Drug Design because it affects the accuracy and efficiency of molecular property prediction and other molecular modeling relevant tasks. However, previous molecular representation learning studies often suffer from limitations, such as over-reliance on a single molecular representation, failure to fully capture both local and global information in molecular structure, and ineffective integration of multiscale features from different molecular representations. These limitations restrict the complete and accurate representation of molecular structure and properties, ultimately impacting the accuracy of predicting molecular properties. To this end, we propose a novel multi-view molecular representation learning method called MvMRL, which can incorporate feature information from multiple molecular representations and capture both local and global information from different views well, thus improving molecular property prediction. Specifically, MvMRL consists of four parts: a multiscale CNN-SE Simplified Molecular Input Line Entry System (SMILES) learning component and a multiscale Graph Neural Network encoder to extract local feature information and global feature information from the SMILES view and the molecular graph view, respectively; a Multi-Layer Perceptron network to capture complex non-linear relationship features from the molecular fingerprint view; and a dual cross-attention component to fuse feature information on the multi-views deeply for predicting molecular properties. We evaluate the performance of MvMRL on 11 benchmark datasets, and experimental results show that MvMRL outperforms state-of-the-art methods, indicating its rationality and effectiveness in molecular property prediction. The source code of MvMRL was released in https://github.com/jedison-github/MvMRL.

An Improved Machine Learning Model for Pure Component Property Estimation

Information on the physicochemical properties of chemical species is an important prerequisite when performing tasks such as process design and product design. However, the lack of extensive data and high experimental costs hinder the development of prediction techniques for these properties. Moreover, accuracy and predictive capabilities still limit the scope and applicability of most property estimation methods. This paper proposes a new Gaussian process-based modeling framework that aims to manage a discrete and high-dimensional input space related to molecular structure representation with the group-contribution approach. A warping function is used to map discrete input into a continuous domain in order to adjust the correlation between different compounds. Prior selection techniques, including prior elicitation and prior predictive checking, are also applied during the building procedure to provide the model with more information from previous research findings. The framework is assessed using datasets of varying sizes for 20 pure component properties. For 18 out of the 20 pure component properties, the new models are found to give improved accuracy and predictive power in comparison with other published models, with and without machine learning.

Difficulty in chirality recognition for Transformer architectures learning chemical structures from string representations

Recent years have seen rapid development of descriptor generation based on representation learning of extremely diverse molecules, especially those that apply natural language processing (NLP) models to SMILES, a literal representation of molecular structure. However, little research has been done on how these models understand chemical structure. To address this black box, we investigated the relationship between the learning progress of SMILES and chemical structure using a representative NLP model, the Transformer. We show that while the Transformer learns partial structures of molecules quickly, it requires extended training to understand overall structures. Consistently, the accuracy of molecular property predictions using descriptors generated from models at different learning steps was similar from the beginning to the end of training. Furthermore, we found that the Transformer requires particularly long training to learn chirality and sometimes stagnates with low performance due to misunderstanding of enantiomers. These findings are expected to deepen the understanding of NLP models in chemistry.

Enhanced Structure-Based Prediction of Chiral Stationary Phases for Chromatographic Enantioseparation from 3D Molecular Conformations.

The accurate prediction of suitable chiral stationary phases (CSPs) for resolving the enantiomers of a given compound poses a significant challenge in chiral chromatography. Previous attempts at developing machine learning models for structure-based CSP prediction have primarily relied on 1D SMILES strings [the simplified molecular-input line-entry system (SMILES) is a specification in the form of a line notation for describing the structure of chemical species using short ASCII strings] or 2D graphical representations of molecular structures and have met with only limited success. In this study, we apply the recently developed 3D molecular conformation representation learning algorithm, which uses rapid conformational analysis and point clouds of atom positions in the 3D space, enabling efficient chemical structure-based machine learning. By harnessing the power of the rapid 3D molecular representation learning and a data set comprising over 300,000 chromatographic enantioseparation records sourced from the literature, our models afford notable improvements for the chemical structure-based choice of appropriate CSP for enantioseparation, paving the way for more efficient and informed decision-making in the field of chiral chromatography.

Distilling coarse-grained representations of molecular electronic structure with continuously gated message passing.

Bottom-up methods for coarse-grained (CG) molecular modeling are critically needed to establish rigorous links between atomistic reference data and reduced molecular representations. For a target molecule, the ideal reduced CG representation is a function of both the conformational ensemble of the system and the target physical observable(s) to be reproduced at the CG resolution. However, there is an absence of algorithms for selecting CG representations of molecules from which complex properties, including molecular electronic structure, can be accurately modeled. We introduce continuously gated message passing (CGMP), a graph neural network (GNN) method for atomically decomposing molecular electronic structure sampled over conformational ensembles. CGMP integrates 3D-invariant GNNs and a novel gated message passing system to continuously reduce the atomic degrees of freedom accessible for electronic predictions, resulting in a one-shot importance ranking of atoms contributing to a target molecular property. Moreover, CGMP provides the first approach by which to quantify the degeneracy of "good" CG representations conditioned on specific prediction targets, facilitating the development of more transferable CG representations. We further show how CGMP can be used to highlight multiatom correlations, illuminating a path to developing CG electronic Hamiltonians in terms of interpretable collective variables for arbitrarily complex molecules.

Molecular toxicity of nitrobenzene derivatives to tetrahymena pyriformis based on SMILES descriptors using Monte Carlo, docking, and MD simulations

It is challenging to model the toxicity of nitroaromatic compounds due to limited experimental data. Nitrobenzene derivatives are commonly used in industry and can lead to environmental contamination. Extensive research, including several QSPR studies, has been conducted to understand their toxicity. Predictive QSPR models can help improve chemical safety, but their limitations must be considered, and the molecular factors affecting toxicity should be carefully investigated. The latest QSPR methods, molecular modeling techniques, machine learning algorithms, and computational chemistry tools are essential for developing accurate and robust models. In this work, we used these methods to study a series of fifty compounds derived from nitrobenzene. The Monte Carlo approach was used for QSPR modeling by applying the SMILES molecular structure representation and optimal molecular descriptors. The correlation ideality index (CII) and correlation contradiction index (CCI) were further introduced as validation parameters to estimate the developed models' predictive ability. The statistical quality of the CII models was better than those without CII. The best QSPR model with the following statistical parameters (Split-3): (R2 = 0.968, CCC = 0.984, IIC = 0.861, CII = 0.979, Q2 = 0.954, QF12 = 0.946, QF22 = 0.938, QF32 = 0.947, Rm2 = 0.878, RMSE = 0.187, MAE = 0.151, FTraining = 390, FInvisible = 218, FCalibration = 240, RTest2 = 0.905) was selected to generate the studied promoters with increasing and decreasing activity.

DeepFPlearn +: enhancing toxicity prediction across the chemical universe using graph neural networks.

Sophisticated approaches for the in silico prediction of toxicity are required to support the risk assessment of chemicals. The number of chemicals on the global chemical market and the speed of chemical innovation stand in massive contrast to the capacity for regularizing chemical use. We recently proved our ready-to-use application deepFPlearn as a suitable approach for this task. Here, we present its extension deepFPlearn+ incorporating (i) a graph neural network to feed our AI with a more sophisticated molecular structure representation and (ii) alternative train-test splitting strategies that involve scaffold structures and the molecular weights of chemicals. We show that the GNNs outperform the previous model substantially and that our models can generalize on unseen data even with a more robust and challenging test set. Therefore, we highly recommend the application of deepFPlearn+ on the chemical inventory to prioritize chemicals for experimental testing or any chemical subset of interest in monitoring studies. The software is compatible with python 3.6 or higher, and the source code can be found on our GitHub repository: https://github.com/yigbt/deepFPlearn. The data underlying this article are available in Zenodo, and can be accessed with the link below: https://zenodo.org/record/8146252. Detailed installation guides via Docker, Singularity, and Conda are provided within the repository for operability across all operating systems.

GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular Generation.

Condition-based molecular generation can generate a large number of molecules with particular properties, expanding the virtual drug screening library, and accelerating the process of drug discovery. In this study, we combined a molecular graph structure and sequential representations using a generative pretrained transformer (GPT) architecture for generating molecules conditionally. The incorporation of graph structure information facilitated a better comprehension of molecular topological features, and the augmentation of a sequential contextual understanding of GPT architecture facilitated molecular generation. The experiments indicate that our model efficiently produces molecules with the desired properties, with valid and unique metrics that are close to 100%. Faced with the typical task of generating molecules based on a scaffold in drug discovery, our model is able to preserve scaffold information and generate molecules with low similarity and specified properties.

GUIDEMOL: A Python graphical user interface for molecular descriptors based on RDKit.

GUIDEMOL is a Python computer program based on the RDKit software to process molecular structures and calculate molecular descriptors with a graphical user interface using the tkinter package. It can calculate descriptors already implemented in RDKit as well as grid representations of 3D molecular structures using the electrostatic potential or voxels. The GUIDEMOL app provides easy access to RDKit tools for chemoinformatics users with no programming skills and can be adapted to calculate other descriptors or to trigger other procedures. A command line interface (CLI) is also provided for the calculation of grid representations. The source code is available at https://github.com/jairesdesousa/guidemol.

AutoMSR: Auto Molecular Structure Representation Learning for Multi-label Metabolic Pathway Prediction.

It is significant to comprehend the relationship between metabolic pathway and molecular pathway for synthesizing new molecules, for instance optimizing drug metabolization. In bioinformatics fields, multi-label prediction of metabolic pathways is a typical manner to understand this relationship. Graph neural networks (GNNs) have become an effective method to extract molecular structure's features for multi-label prediction of metabolic pathways. Though GNNs can effectively capture structural features from molecular structure graphs, building a well-performed GNN model for a given molecular structure data set requires the manual design of the GNN architecture and fine-tuning of the hyperparameters, which are time-consuming and rely on expert experience. To address the above challenge, we design an end-to-end automatic molecular structure representation learning framework named AutoMSR that can design the optimal GNN model based on a given molecular structure data set without manual intervention. We propose a multi-seed age evolution (MSAE) search algorithm to identify the optimal GNN architecture from the GNN architecture subspace. For a given molecular structure data set, AutoMSR first uses MSAE to search the GNN architecture, and then it adopts a tree-structured parzen estimator to obtain the best hyperparameters in the hyperparameters subspace. Finally, AutoMSR automatically constructs the optimal GNN model based on the best GNN architecture and hyperparameters to extract the molecular structure features for multi-label metabolic pathway prediction. We test the performance of AutoMSR on the real data set KEGG. The experiment results show that AutoMSR outperforms baseline methods on different multi-label classification evaluation metrics.

Drug–target affinity prediction method based on multi-scale information interaction and graph optimization

Drug–target affinity (DTA) prediction as an emerging and effective method is widely applied to explore the strength of drug–target interactions in drug development research. By predicting these interactions, researchers can assess the potential efficacy and safety of candidate drugs at an early stage, narrowing down the search space for therapeutic targets and accelerating the discovery and development of new drugs. However, existing DTA prediction models mainly use graphical representations of drug molecules, which lack information on interactions between individual substructures, thus affecting prediction accuracy and model interpretability. Therefore, transformer and diffusion on drug graphs in DTA prediction (TDGraphDTA) are introduced to predict drug–target interactions using multi-scale information interaction and graph optimization. An interactive module is integrated into feature extraction of drug and target features at different granularity levels. A diffusion model-based graph optimization module is proposed to improve the representation of molecular graph structures and enhance the interpretability of graph representations while obtaining optimal feature representations. In addition, TDGraphDTA improves the accuracy and reliability of predictions by capturing relationships and contextual information between molecular substructures. The performance of the proposed TDGraphDTA in DTA prediction was verified on three publicly available benchmark datasets (Davis, Metz, and KIBA). Compared with state-of-the-art baseline models, it achieved better results in terms of consistency index, R-squared, etc. Furthermore, compared with some existing methods, the proposed TDGraphDTA is demonstrated to have better structure capturing capabilities by visualizing the feature capturing capabilities of the model using Grad-AAM toxicity labels in the ToxCast dataset. The corresponding source codes are available at https://github.com/Lamouryz/TDGraph.

有機結晶へのマテリアルズインフォマティクス応用

Organic crystals have presented flexible features in contrast with inorganic crystals, and are expected for the future applications of optoelectronics and active matters. Pharmaceuticals are also the utilization of the organic crystal family. This article presents the basis of the data science in organic crystals, and a few examples of application of my research. An attempt is to screen the structural phase transition of organic crystals, and another topic is to compare structural representation of molecular and crystal structures regressed by graph neural network.

Structural modeling and topological characterization of three kinds of dendrimer networks.

Dendrimers, also known as dendritic polymers, have various applications due to their unique properties, such as their monodisperse structure and their ability to be synthesized with precise control over their size, shape, and surface functionality. Dendrimers are used in drug delivery systems to improve drug solubility, bioavailability, and targeting. They can carry drugs to specific sites, such as cancer cells, and release them in a controlled manner, reducing side effects. Dendrimers can be used as gene delivery vehicles to deliver genetic material to cells in a controlled and targeted manner. Mathematical chemistry is useful to model chemical reactions and predict the behavior of chemical systems. It provides a quantitative understanding of chemical phenomena, which can aid in the design of new molecules and materials. It is used to develop molecular descriptors, which are mathematical representations of molecular structures that can be used to quantify the properties of molecules. These descriptors can be useful in structure-activity relationship studies to predict the biological activity of compounds. The topological descriptors are parameters of any molecular structure that gives a mathematical formula to model such molecular structures. In the current study, our concern is to calculate some useful topological indices for three kinds of dendrimer networks and derive closed mathematical formulas for them. The comparisons of these calculated topological indices are also investigated. Our obtained results will be helpful in investigating QSPRs/QSARs of such molecules in many fields of science, such as chemistry, physics and biochemistry. The dendrimer structure (left). From first (G0) to third (G3) generation, the dendrimer's increasing generations are shown schematically (right).

Group contribution-based property modeling for chemical product design: A perspective in the AI era

We provide a perspective of the challenges and opportunities for the group contribution approach for property prediction modeling with respect to their use in the design of chemical-based products in the modern era of artificial intelligence. In particular, we discuss issues related to the correct formulation of the product design problem, representation of molecular structures for property prediction as well as generation of product candidates, regression of property model parameters, and the integration of property related data and models with product design methods and tools using several conceptual examples. The need for developing appropriate hybrid AI models is described and recommendations for future work are presented.

Persistent Path-Spectral (PPS) Based Machine Learning for Protein-Ligand Binding Affinity Prediction.

Molecular descriptors are essential to quantitative structure activity/property relationship (QSAR/QSPR) models and machine learning models. Here we propose persistent path-spectral (PPS), PPS-based molecular descriptors, and PPS-based machine learning model for the prediction of the protein-ligand binding affinity, for the first time. For the graph, simplicial complex, and hypergraph representation of molecular structures and interactions, the path-Laplacian can be constructed and the derived path-spectral naturally gives a quantitative description of molecules. Further, by introducing the filtration process of the representation, the persistent path-spectral can be derived, which gives a multiscale characterization of molecules. Molecular descriptors from the persistent path-spectral attributes then are combined with the machine learning model, in particular, the gradient boosting tree, to form our PPS-ML model. We test our model on three most commonly used data sets, i.e., PDBbind-v2007, PDBbind-v2013, and PDBbind-v2016, and our model can achieve competitive results.