1
|
Soleymani F, Paquet E, Viktor HL, Michalowski W. Structure-based protein and small molecule generation using EGNN and diffusion models: A comprehensive review. Comput Struct Biotechnol J 2024; 23:2779-2797. [PMID: 39050782 PMCID: PMC11268121 DOI: 10.1016/j.csbj.2024.06.021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2024] [Revised: 06/13/2024] [Accepted: 06/18/2024] [Indexed: 07/27/2024] Open
Abstract
Recent breakthroughs in deep learning have revolutionized protein sequence and structure prediction. These advancements are built on decades of protein design efforts, and are overcoming traditional time and cost limitations. Diffusion models, at the forefront of these innovations, significantly enhance design efficiency by automating knowledge acquisition. In the field of de novo protein design, the goal is to create entirely novel proteins with predetermined structures. Given the arbitrary positions of proteins in 3-D space, graph representations and their properties are widely used in protein generation studies. A critical requirement in protein modelling is maintaining spatial relationships under transformations (rotations, translations, and reflections). This property, known as equivariance, ensures that predicted protein characteristics adapt seamlessly to changes in orientation or position. Equivariant graph neural networks offer a solution to this challenge. By incorporating equivariant graph neural networks to learn the score of the probability density function in diffusion models, one can generate proteins with robust 3-D structural representations. This review examines the latest deep learning advancements, specifically focusing on frameworks that combine diffusion models with equivariant graph neural networks for protein generation.
Collapse
Affiliation(s)
- Farzan Soleymani
- Telfer School of Management, University of Ottawa, ON, K1N 6N5, Canada
| | - Eric Paquet
- National Research Council, 1200 Montreal Road, Ottawa, ON, K1A 0R6, Canada
- School of Electrical Engineering and Computer Science, University of Ottawa, ON, K1N 6N5, Canada
| | - Herna Lydia Viktor
- School of Electrical Engineering and Computer Science, University of Ottawa, ON, K1N 6N5, Canada
| | | |
Collapse
|
2
|
Sirugue L, Langenfeld F, Lagarde N, Montes M. PLO3S: Protein LOcal Surficial Similarity Screening. Comput Struct Biotechnol J 2024; 26:1-10. [PMID: 38189058 PMCID: PMC10770625 DOI: 10.1016/j.csbj.2023.12.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2022] [Revised: 12/01/2023] [Accepted: 12/03/2023] [Indexed: 01/09/2024] Open
Abstract
The study of protein molecular surfaces enables to better understand and predict protein interactions. Different methods have been developed in computer vision to compare surfaces that can be applied to protein molecular surfaces. The present work proposes a method using the Wave Kernel Signature: Protein LOcal Surficial Similarity Screening (PLO3S). The descriptor of the PLO3S method is a local surface shape descriptor projected on a unit sphere mapped onto a 2D plane and called Surface Wave Interpolated Maps (SWIM). PLO3S allows to rapidly compare protein surface shapes through local comparisons to filter large protein surfaces datasets in protein structures virtual screening protocols.
Collapse
Affiliation(s)
- Léa Sirugue
- Laboratoire GBCM, EA7528, Conservatoire National des Arts et Métiers, Hesam Université, 2, rue Conté, Paris, 75003, France
| | - Florent Langenfeld
- Laboratoire GBCM, EA7528, Conservatoire National des Arts et Métiers, Hesam Université, 2, rue Conté, Paris, 75003, France
| | - Nathalie Lagarde
- Laboratoire GBCM, EA7528, Conservatoire National des Arts et Métiers, Hesam Université, 2, rue Conté, Paris, 75003, France
| | - Matthieu Montes
- Laboratoire GBCM, EA7528, Conservatoire National des Arts et Métiers, Hesam Université, 2, rue Conté, Paris, 75003, France
| |
Collapse
|
3
|
Dou Z, He J, Han C, Wu X, Wan L, Yang J, Zheng Y, Gong B, Wang L. qProtein: Exploring Physical Features of Protein Thermostability Based on Structural Proteomics. J Chem Inf Model 2024. [PMID: 39375829 DOI: 10.1021/acs.jcim.4c01303] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/09/2024]
Abstract
Thermostability, which is essential for the functional performance of enzymes, is largely determined by intramolecular physical interactions. Although many tools have been developed, existing computational methods have struggled to find the universal principles of protein thermostability. Recent advancements in structural proteomics have been driven by the introduction of deep neural networks such as AlphaFold2 and ESMFold. These innovations have enabled the characterization of protein structures with unprecedented speed and accuracy. Here, we introduce qProtein, a Python-implemented workflow designed for the quantitative analysis of physical interactions on the scale of structural proteomics. This platform accepts protein sequences as input and produces four structural features, including hydrophobic clusters, hydrogen bonds, electrostatic interactions, and disulfide bonds. To demonstrate the use of qProtein, we investigate the structural features related to protein thermostability in six glycoside hydrolase (GH) families, comprising a total of 3,811 protein structures. Our results indicate that in five enzyme families (GH11, GH12, GH5_2, GH10, and GH48), the thermophilic enzymes have a larger average area of hydrophobic clusters compared to the nonthermophilic enzymes within each family. Furthermore, our analysis of the local-structure regions reveals that the hydrophobic clusters are predominantly distributed in the distal regions of the GH11 enzymes. In addition, the average hydrophobic cluster area of the thermophilic enzymes is significantly higher than that of the nonthermophilic enzymes in the distal regions of the GH11 enzymes. Therefore, qProtein is a well-suited platform for analyzing the structural features of thermal stability at the level of structural proteomics. We provide the source code for qProtein at https://github.com/bj600800/qProtein, and the web server is available at http://qProtein.sdu.edu.cn:8888.
Collapse
Affiliation(s)
- Zhixin Dou
- State Key Laboratory of Microbial Technology, Shandong University, No. 72 Binhai Road, Qingdao 266237, P.R. China
| | - Jiaxin He
- School of Computer Science and Technology, Shandong University, No. 72 Binhai Road, Qingdao 266237, P.R. China
| | - Chao Han
- Shandong Key Laboratory of Agricultural Microbiology, Shandong Agricultural University, Tai'an 271018, China
| | - Xiuyun Wu
- State Key Laboratory of Microbial Technology, Shandong University, No. 72 Binhai Road, Qingdao 266237, P.R. China
| | - Lin Wan
- School of Software, Shandong University, Shunhua Road, Jinan 250101, P.R. China
| | - Jian Yang
- School of Computer Science and Technology, Shandong University, No. 72 Binhai Road, Qingdao 266237, P.R. China
| | - Yanwei Zheng
- School of Computer Science and Technology, Shandong University, No. 72 Binhai Road, Qingdao 266237, P.R. China
| | - Bin Gong
- School of Software, Shandong University, Shunhua Road, Jinan 250101, P.R. China
| | - Lushan Wang
- State Key Laboratory of Microbial Technology, Shandong University, No. 72 Binhai Road, Qingdao 266237, P.R. China
| |
Collapse
|
4
|
Harding-Larsen D, Funk J, Madsen NG, Gharabli H, Acevedo-Rocha CG, Mazurenko S, Welner DH. Protein representations: Encoding biological information for machine learning in biocatalysis. Biotechnol Adv 2024; 77:108459. [PMID: 39366493 DOI: 10.1016/j.biotechadv.2024.108459] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2024] [Revised: 09/19/2024] [Accepted: 09/29/2024] [Indexed: 10/06/2024]
Abstract
Enzymes offer a more environmentally friendly and low-impact solution to conventional chemistry, but they often require additional engineering for their application in industrial settings, an endeavour that is challenging and laborious. To address this issue, the power of machine learning can be harnessed to produce predictive models that enable the in silico study and engineering of improved enzymatic properties. Such machine learning models, however, require the conversion of the complex biological information to a numerical input, also called protein representations. These inputs demand special attention to ensure the training of accurate and precise models, and, in this review, we therefore examine the critical step of encoding protein information to numeric representations for use in machine learning. We selected the most important approaches for encoding the three distinct biological protein representations - primary sequence, 3D structure, and dynamics - to explore their requirements for employment and inductive biases. Combined representations of proteins and substrates are also introduced as emergent tools in biocatalysis. We propose the division of fixed representations, a collection of rule-based encoding strategies, and learned representations extracted from the latent spaces of large neural networks. To select the most suitable protein representation, we propose two main factors to consider. The first one is the model setup, which is influenced by the size of the training dataset and the choice of architecture. The second factor is the model objectives such as consideration about the assayed property, the difference between wild-type models and mutant predictors, and requirements for explainability. This review is aimed at serving as a source of information and guidance for properly representing enzymes in future machine learning models for biocatalysis.
Collapse
Affiliation(s)
- David Harding-Larsen
- The Novo Nordisk Center for Biosustainability, Technical University of Denmark, Søltofts Plads, Bygning 220, 2800 Kgs. Lyngby, Denmark
| | - Jonathan Funk
- The Novo Nordisk Center for Biosustainability, Technical University of Denmark, Søltofts Plads, Bygning 220, 2800 Kgs. Lyngby, Denmark
| | - Niklas Gesmar Madsen
- The Novo Nordisk Center for Biosustainability, Technical University of Denmark, Søltofts Plads, Bygning 220, 2800 Kgs. Lyngby, Denmark
| | - Hani Gharabli
- The Novo Nordisk Center for Biosustainability, Technical University of Denmark, Søltofts Plads, Bygning 220, 2800 Kgs. Lyngby, Denmark
| | - Carlos G Acevedo-Rocha
- The Novo Nordisk Center for Biosustainability, Technical University of Denmark, Søltofts Plads, Bygning 220, 2800 Kgs. Lyngby, Denmark
| | - Stanislav Mazurenko
- Loschmidt Laboratories, Department of Experimental Biology and RECETOX, Faculty of Science, Masaryk University, Kamenice 5, 625 00 Brno, Czech Republic; International Clinical Research Center, St. Anne's University Hospital Brno, Pekarska 53, 656 91 Brno, Czech Republic
| | - Ditte Hededam Welner
- The Novo Nordisk Center for Biosustainability, Technical University of Denmark, Søltofts Plads, Bygning 220, 2800 Kgs. Lyngby, Denmark.
| |
Collapse
|
5
|
Ozawa M, Nakamura S, Yasuo N, Sekijima M. IEV2Mol: Molecular Generative Model Considering Protein-Ligand Interaction Energy Vectors. J Chem Inf Model 2024; 64:6969-6978. [PMID: 39254942 PMCID: PMC11423338 DOI: 10.1021/acs.jcim.4c00842] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/11/2024]
Abstract
Generating drug candidates with desired protein-ligand interactions is a significant challenge in structure-based drug design. In this study, a new generative model, IEV2Mol, is proposed that incorporates interaction energy vectors (IEVs) between proteins and ligands obtained from docking simulations, which quantitatively capture the strength of each interaction type, such as hydrogen bonds, electrostatic interactions, and van der Waals forces. By integrating this IEV into an end-to-end variational autoencoder (VAE) framework that learns the chemical space from SMILES and minimizes the reconstruction error of the SMILES, the model can more accurately generate compounds with the desired interactions. To evaluate the effectiveness of IEV2Mol, we performed benchmark comparisons with randomly selected compounds, unconstrained VAE models (JT-VAE), and compounds generated by RNN models based on interaction fingerprints (IFP-RNN). The results show that the compounds generated by IEV2Mol retain a significantly greater percentage of the binding mode of the query structure than those of the other methods. Furthermore, IEV2Mol was able to generate compounds with interactions similar to those of the input compounds, regardless of structural similarity. The source code and trained models for IEV2Mol, JT-VAE, and IFP-RNN designed for generating compounds active against the DRD2, AA2AR, and AKT1, as well as the data sets (DM-QP-1M, active compounds to each protein, and ChEMBL33) utilized in this study, are released under the MIT License and available at https://github.com/sekijima-lab/IEV2Mol.
Collapse
Affiliation(s)
- Mami Ozawa
- Department of Computer Science, Tokyo Institute of Technology, Yokohama, Kanagawa 226-8501, Japan
| | - Shogo Nakamura
- Department of Life Science and Technology, Tokyo Institute of Technology, Yokohama, Kanagawa 226-8501, Japan
| | - Nobuaki Yasuo
- Academy for Convergence of Materials and Informatics (TAC-MI), Tokyo Institute of Technology, Tokyo 152-8550, Japan
| | - Masakazu Sekijima
- Department of Computer Science, Tokyo Institute of Technology, Yokohama, Kanagawa 226-8501, Japan
| |
Collapse
|
6
|
Comajuncosa-Creus A, Jorba G, Barril X, Aloy P. Comprehensive detection and characterization of human druggable pockets through binding site descriptors. Nat Commun 2024; 15:7917. [PMID: 39256431 PMCID: PMC11387482 DOI: 10.1038/s41467-024-52146-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2024] [Accepted: 08/27/2024] [Indexed: 09/12/2024] Open
Abstract
Druggable pockets are protein regions that have the ability to bind organic small molecules, and their characterization is essential in target-based drug discovery. However, deriving pocket descriptors is challenging and existing strategies are often limited in applicability. We introduce PocketVec, an approach to generate pocket descriptors via inverse virtual screening of lead-like molecules. PocketVec performs comparably to leading methodologies while addressing key limitations. Additionally, we systematically search for druggable pockets in the human proteome, using experimentally determined structures and AlphaFold2 models, identifying over 32,000 binding sites across 20,000 protein domains. We then generate PocketVec descriptors for each site and conduct an extensive similarity search, exploring over 1.2 billion pairwise comparisons. Our results reveal druggable pocket similarities not detected by structure- or sequence-based methods, uncovering clusters of similar pockets in proteins lacking crystallized inhibitors and opening the door to strategies for prioritizing chemical probe development to explore the druggable space.
Collapse
Affiliation(s)
- Arnau Comajuncosa-Creus
- Institute for Research in Biomedicine (IRB Barcelona), The Barcelona Institute of Science and Technology, Barcelona, Catalonia, Spain
| | - Guillem Jorba
- Institute for Research in Biomedicine (IRB Barcelona), The Barcelona Institute of Science and Technology, Barcelona, Catalonia, Spain
| | - Xavier Barril
- Facultat de Farmàcia and Institut de Biomedicina, Universitat de Barcelona, Barcelona, Catalonia, Spain
- Institució Catalana de Recerca i Estudis Avançats (ICREA), Barcelona, Catalonia, Spain
| | - Patrick Aloy
- Institute for Research in Biomedicine (IRB Barcelona), The Barcelona Institute of Science and Technology, Barcelona, Catalonia, Spain.
- Institució Catalana de Recerca i Estudis Avançats (ICREA), Barcelona, Catalonia, Spain.
| |
Collapse
|
7
|
Wang C, Wang J, Song W, Luo G, Jiang T. EpiScan: accurate high-throughput mapping of antibody-specific epitopes using sequence information. NPJ Syst Biol Appl 2024; 10:101. [PMID: 39251627 PMCID: PMC11383971 DOI: 10.1038/s41540-024-00432-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2023] [Accepted: 08/27/2024] [Indexed: 09/11/2024] Open
Abstract
The identification of antibody-specific epitopes on virus proteins is crucial for vaccine development and drug design. Nonetheless, traditional wet-lab approaches for the identification of epitopes are both costly and labor-intensive, underscoring the need for the development of efficient and cost-effective computational tools. Here, EpiScan, an attention-based deep learning framework for predicting antibody-specific epitopes, is presented. EpiScan adopts a multi-input and single-output strategy by designing independent blocks for different parts of antibodies, including variable heavy chain (VH), variable light chain (VL), complementary determining regions (CDRs), and framework regions (FRs). The block predictions are weighted and integrated for the prediction of potential epitopes. Using multiple experimental data samples, we show that EpiScan, which only uses antibody sequence information, can accurately map epitopes on specific antigen structures. The antibody-specific epitopes on the receptor binding domain (RBD) of SARS coronavirus 2 (SARS-CoV-2) were located by EpiScan, and the potentially valuable vaccine epitope was identified. EpiScan can expedite the epitope mapping process for high-throughput antibody sequencing data, supporting vaccine design and drug development. Availability: For the convenience of related wet-experimental researchers, the source code and web server of EpiScan are publicly available at https://github.com/gzBiomedical/EpiScan .
Collapse
Affiliation(s)
- Chuan Wang
- School of Life Sciences, Sun Yat-sen University, Guangzhou, China
- Guangzhou National Laboratory, Guangzhou, China
| | | | - Wenjun Song
- Guangzhou National Laboratory, Guangzhou, China
- Institute of Integration of Traditional and Western Medicine, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China
| | - Guanzheng Luo
- School of Life Sciences, Sun Yat-sen University, Guangzhou, China.
| | - Taijiao Jiang
- Guangzhou National Laboratory, Guangzhou, China.
- State Key Laboratory of Respiratory Disease, The Key laboratory of Advanced Interdisciplinary Studies Center, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
| |
Collapse
|
8
|
Zheng Y, Li Q, Freiberger MI, Song H, Hu G, Zhang M, Gu R, Li J. Predicting the Dynamic Interaction of Intrinsically Disordered Proteins. J Chem Inf Model 2024; 64:6768-6777. [PMID: 39163306 DOI: 10.1021/acs.jcim.4c00930] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/22/2024]
Abstract
Intrinsically disordered proteins (IDPs) participate in various biological processes. Interactions involving IDPs are usually dynamic and are affected by their inherent conformation fluctuations. Comprehensive characterization of these interactions based on current techniques is challenging. Here, we present GSALIDP, a GraphSAGE-embedded LSTM network, to capture the dynamic nature of IDP-involved interactions and predict their behaviors. This framework models multiple conformations of IDP as a dynamic graph, which can effectively describe the fluctuation of its flexible conformation. The dynamic interaction between IDPs is studied, and the data sets of IDP conformations and their interactions are obtained through atomistic molecular dynamic (MD) simulations. Residues of IDP are encoded through a series of features including their frustration. GSALIDP can effectively predict the interaction sites of IDP and the contact residue pairs between IDPs. Its performance in predicting IDP interactions is on par with or even better than the conventional models in predicting the interaction of structural proteins. To the best of our knowledge, this is the first model to extend the protein interaction prediction to IDP-involved interactions.
Collapse
Affiliation(s)
- Yuchuan Zheng
- School of Physics, Zhejiang University, Hangzhou 310058, PR China
| | - Qixiu Li
- School of Physics, Zhejiang University, Hangzhou 310058, PR China
| | - Maria I Freiberger
- Protein Physiology Lab, Departamento de Quimica Biologica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires-CONICET-IQUIBICEN, Buenos Aires C1428EGA, Argentina
| | - Haoyu Song
- School of Physics, Zhejiang University, Hangzhou 310058, PR China
| | - Guorong Hu
- School of Physics, Zhejiang University, Hangzhou 310058, PR China
| | - Moxin Zhang
- School of Physics, Zhejiang University, Hangzhou 310058, PR China
| | - Ruoxu Gu
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, PR China
| | - Jingyuan Li
- School of Physics, Zhejiang University, Hangzhou 310058, PR China
| |
Collapse
|
9
|
Castro-Correa JA, Giraldo JH, Badiey M, Malliaros FD. Gegenbauer Graph Neural Networks for Time-Varying Signal Reconstruction. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:11734-11745. [PMID: 38598390 DOI: 10.1109/tnnls.2024.3381069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/12/2024]
Abstract
Reconstructing time-varying graph signals (or graph time-series imputation) is a critical problem in machine learning and signal processing with broad applications, ranging from missing data imputation in sensor networks to time-series forecasting. Accurately capturing the spatio-temporal information inherent in these signals is crucial for effectively addressing these tasks. However, existing approaches relying on smoothness assumptions of temporal differences and simple convex optimization techniques that have inherent limitations. To address these challenges, we propose a novel approach that incorporates a learning module to enhance the accuracy of the downstream task. To this end, we introduce the Gegenbauer-based graph convolutional (GegenConv) operator, which is a generalization of the conventional Chebyshev graph convolution by leveraging the theory of Gegenbauer polynomials. By deviating from traditional convex problems, we expand the complexity of the model and offer a more accurate solution for recovering time-varying graph signals. Building upon GegenConv, we design the Gegenbauer-based time graph neural network (GegenGNN) architecture, which adopts an encoder-decoder structure. Likewise, our approach also uses a dedicated loss function that incorporates a mean squared error (MSE) component alongside Sobolev smoothness regularization. This combination enables GegenGNN to capture both the fidelity to ground truth and the underlying smoothness properties of the signals, enhancing the reconstruction performance. We conduct extensive experiments on real datasets to evaluate the effectiveness of our proposed approach. The experimental results demonstrate that GegenGNN outperforms state-of-the-art methods, showcasing its superior capability in recovering time-varying graph signals.
Collapse
|
10
|
Li P, Liu ZP. MuToN Quantifies Binding Affinity Changes upon Protein Mutations by Geometric Deep Learning. ADVANCED SCIENCE (WEINHEIM, BADEN-WURTTEMBERG, GERMANY) 2024; 11:e2402918. [PMID: 38995072 PMCID: PMC11425207 DOI: 10.1002/advs.202402918] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/20/2024] [Revised: 06/04/2024] [Indexed: 07/13/2024]
Abstract
Assessing changes in protein-protein binding affinity due to mutations helps understanding a wide range of crucial biological processes within cells. Despite significant efforts to create accurate computational models, predicting how mutations affect affinity remains challenging due to the complexity of the biological mechanisms involved. In the present work, a geometric deep learning framework called MuToN is introduced for quantifying protein binding affinity change upon residue mutations. The method, designed with geometric attention networks, is mechanism-aware. It captures changes in the protein binding interfaces of mutated complexes and assesses the allosteric effects of amino acids. Experimental results highlight MuToN's superiority compared to existing methods. Additionally, MuToN's flexibility and effectiveness are illustrated by its precise predictions of binding affinity changes between SARS-CoV-2 variants and the ACE2 complex.
Collapse
Affiliation(s)
- Pengpai Li
- Department of Biomedical Engineering, School of Control Science and Engineering, Shandong University, Jinan, Shandong, 250061, China
| | - Zhi-Ping Liu
- Department of Biomedical Engineering, School of Control Science and Engineering, Shandong University, Jinan, Shandong, 250061, China
| |
Collapse
|
11
|
Ji T, Liaqat F, Khazi MI, Liaqat N, Nawaz MZ, Zhu D. Lignin biotransformation: Advances in enzymatic valorization and bioproduction strategies. INDUSTRIAL CROPS AND PRODUCTS 2024; 216:118759. [DOI: 10.1016/j.indcrop.2024.118759] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/23/2024]
|
12
|
Zhao Y, He S, Xing Y, Li M, Cao Y, Wang X, Zhao D, Bo X. A Point Cloud Graph Neural Network for Protein-Ligand Binding Site Prediction. Int J Mol Sci 2024; 25:9280. [PMID: 39273227 PMCID: PMC11394757 DOI: 10.3390/ijms25179280] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2024] [Revised: 08/25/2024] [Accepted: 08/26/2024] [Indexed: 09/15/2024] Open
Abstract
Predicting protein-ligand binding sites is an integral part of structural biology and drug design. A comprehensive understanding of these binding sites is essential for advancing drug innovation, elucidating mechanisms of biological function, and exploring the nature of disease. However, accurately identifying protein-ligand binding sites remains a challenging task. To address this, we propose PGpocket, a geometric deep learning-based framework to improve protein-ligand binding site prediction. Initially, the protein surface is converted into a point cloud, and then the geometric and chemical properties of each point are calculated. Subsequently, the point cloud graph is constructed based on the inter-point distances, and the point cloud graph neural network (GNN) is applied to extract and analyze the protein surface information to predict potential binding sites. PGpocket is trained on the scPDB dataset, and its performance is verified on two independent test sets, Coach420 and HOLO4K. The results show that PGpocket achieves a 58% success rate on the Coach420 dataset and a 56% success rate on the HOLO4K dataset. These results surpass competing algorithms, demonstrating PGpocket's advancement and practicality for protein-ligand binding site prediction.
Collapse
Affiliation(s)
- Yanpeng Zhao
- Academy of Military Medical Sciences, Beijing 100850, China
| | - Song He
- Academy of Military Medical Sciences, Beijing 100850, China
| | - Yuting Xing
- Defense Innovation Institute, Beijing 100071, China
| | - Mengfan Li
- Academy of Military Medical Sciences, Beijing 100850, China
| | - Yang Cao
- Academy of Military Medical Sciences, Beijing 100850, China
| | - Xuanze Wang
- Academy of Military Medical Sciences, Beijing 100850, China
| | - Dongsheng Zhao
- Academy of Military Medical Sciences, Beijing 100850, China
| | - Xiaochen Bo
- Academy of Military Medical Sciences, Beijing 100850, China
| |
Collapse
|
13
|
Zitnik M, Li MM, Wells A, Glass K, Morselli Gysi D, Krishnan A, Murali TM, Radivojac P, Roy S, Baudot A, Bozdag S, Chen DZ, Cowen L, Devkota K, Gitter A, Gosline SJC, Gu P, Guzzi PH, Huang H, Jiang M, Kesimoglu ZN, Koyuturk M, Ma J, Pico AR, Pržulj N, Przytycka TM, Raphael BJ, Ritz A, Sharan R, Shen Y, Singh M, Slonim DK, Tong H, Yang XH, Yoon BJ, Yu H, Milenković T. Current and future directions in network biology. BIOINFORMATICS ADVANCES 2024; 4:vbae099. [PMID: 39143982 PMCID: PMC11321866 DOI: 10.1093/bioadv/vbae099] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Revised: 05/31/2024] [Accepted: 07/08/2024] [Indexed: 08/16/2024]
Abstract
Summary Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales. Although the field has been around for two decades, it remains nascent. It has witnessed rapid evolution, accompanied by emerging challenges. These stem from various factors, notably the growing complexity and volume of data together with the increased diversity of data types describing different tiers of biological organization. We discuss prevailing research directions in network biology, focusing on molecular/cellular networks but also on other biological network types such as biomedical knowledge graphs, patient similarity networks, brain networks, and social/contact networks relevant to disease spread. In more detail, we highlight areas of inference and comparison of biological networks, multimodal data integration and heterogeneous networks, higher-order network analysis, machine learning on networks, and network-based personalized medicine. Following the overview of recent breakthroughs across these five areas, we offer a perspective on future directions of network biology. Additionally, we discuss scientific communities, educational initiatives, and the importance of fostering diversity within the field. This article establishes a roadmap for an immediate and long-term vision for network biology. Availability and implementation Not applicable.
Collapse
Affiliation(s)
- Marinka Zitnik
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, United States
| | - Michelle M Li
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, United States
| | - Aydin Wells
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN 46556, United States
- Lucy Family Institute for Data and Society, University of Notre Dame, Notre Dame, IN 46556, United States
- Eck Institute for Global Health, University of Notre Dame, Notre Dame, IN 46556, United States
| | - Kimberly Glass
- Channing Division of Network Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, United States
| | - Deisy Morselli Gysi
- Channing Division of Network Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, United States
- Department of Statistics, Federal University of Paraná, Curitiba, Paraná 81530-015, Brazil
- Department of Physics, Northeastern University, Boston, MA 02115, United States
| | - Arjun Krishnan
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, United States
| | - T M Murali
- Department of Computer Science, Virginia Tech, Blacksburg, VA 24061, United States
| | - Predrag Radivojac
- Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, United States
| | - Sushmita Roy
- Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI 53715, United States
- Wisconsin Institute for Discovery, Madison, WI 53715, United States
| | - Anaïs Baudot
- Aix Marseille Université, INSERM, MMG, Marseille, France
| | - Serdar Bozdag
- Department of Computer Science and Engineering, University of North Texas, Denton, TX 76203, United States
- Department of Mathematics, University of North Texas, Denton, TX 76203, United States
| | - Danny Z Chen
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN 46556, United States
| | - Lenore Cowen
- Department of Computer Science, Tufts University, Medford, MA 02155, United States
| | - Kapil Devkota
- Department of Computer Science, Tufts University, Medford, MA 02155, United States
| | - Anthony Gitter
- Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI 53715, United States
- Morgridge Institute for Research, Madison, WI 53715, United States
| | - Sara J C Gosline
- Biological Sciences Division, Pacific Northwest National Laboratory, Seattle, WA 98109, United States
| | - Pengfei Gu
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN 46556, United States
| | - Pietro H Guzzi
- Department of Medical and Surgical Sciences, University Magna Graecia of Catanzaro, Catanzaro, 88100, Italy
| | - Heng Huang
- Department of Computer Science, University of Maryland College Park, College Park, MD 20742, United States
| | - Meng Jiang
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN 46556, United States
| | - Ziynet Nesibe Kesimoglu
- Department of Computer Science and Engineering, University of North Texas, Denton, TX 76203, United States
- National Center of Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20814, United States
| | - Mehmet Koyuturk
- Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, OH 44106, United States
| | - Jian Ma
- Ray and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, United States
| | - Alexander R Pico
- Institute of Data Science and Biotechnology, Gladstone Institutes, San Francisco, CA 94158, United States
| | - Nataša Pržulj
- Department of Computer Science, University College London, London, WC1E 6BT, England
- ICREA, Catalan Institution for Research and Advanced Studies, Barcelona, 08010, Spain
- Barcelona Supercomputing Center (BSC), Barcelona, 08034, Spain
| | - Teresa M Przytycka
- National Center of Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20814, United States
| | - Benjamin J Raphael
- Department of Computer Science, Princeton University, Princeton, NJ 08544, United States
| | - Anna Ritz
- Department of Biology, Reed College, Portland, OR 97202, United States
| | - Roded Sharan
- School of Computer Science, Tel Aviv University, Tel Aviv, 69978, Israel
| | - Yang Shen
- Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, United States
| | - Mona Singh
- Department of Computer Science, Princeton University, Princeton, NJ 08544, United States
- Lewis-Sigler Institute for Integrative Genomics, Princeton University, Princeton, NJ 08544, United States
| | - Donna K Slonim
- Department of Computer Science, Tufts University, Medford, MA 02155, United States
| | - Hanghang Tong
- Department of Computer Science, University of Illinois Urbana-Champaign, Urbana, IL 61801, United States
| | - Xinan Holly Yang
- Department of Pediatrics, University of Chicago, Chicago, IL 60637, United States
| | - Byung-Jun Yoon
- Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, United States
- Computational Science Initiative, Brookhaven National Laboratory, Upton, NY 11973, United States
| | - Haiyuan Yu
- Department of Computational Biology, Weill Institute for Cell and Molecular Biology, Cornell University, Ithaca, NY 14853, United States
| | - Tijana Milenković
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN 46556, United States
- Lucy Family Institute for Data and Society, University of Notre Dame, Notre Dame, IN 46556, United States
- Eck Institute for Global Health, University of Notre Dame, Notre Dame, IN 46556, United States
| |
Collapse
|
14
|
Carroll M, Rosenbaum E, Viswanathan R. Computational Methods to Predict Conformational B-Cell Epitopes. Biomolecules 2024; 14:983. [PMID: 39199371 PMCID: PMC11352882 DOI: 10.3390/biom14080983] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2024] [Revised: 08/04/2024] [Accepted: 08/08/2024] [Indexed: 09/01/2024] Open
Abstract
Accurate computational prediction of B-cell epitopes can greatly enhance biomedical research and rapidly advance efforts to develop therapeutics, monoclonal antibodies, vaccines, and immunodiagnostic reagents. Previous research efforts have primarily focused on the development of computational methods to predict linear epitopes rather than conformational epitopes; however, the latter is much more biologically predominant. Several conformational B-cell epitope prediction methods have recently been published, but their predictive performances are weak. Here, we present a review of the latest computational methods and assess their performances on a diverse test set of 29 non-redundant unbound antigen structures. Our results demonstrate that ISPIPab performs better than most methods and compares favorably with other recent antigen-specific methods. Finally, we suggest new strategies and opportunities to improve computational predictions of conformational B-cell epitopes.
Collapse
Affiliation(s)
| | | | - R. Viswanathan
- Department of Chemistry and Biochemistry, Yeshiva College, Yeshiva University, New York, NY 10033, USA; (M.C.); (E.R.)
| |
Collapse
|
15
|
Li MM, Huang Y, Sumathipala M, Liang MQ, Valdeolivas A, Ananthakrishnan AN, Liao K, Marbach D, Zitnik M. Contextual AI models for single-cell protein biology. Nat Methods 2024; 21:1546-1557. [PMID: 39039335 PMCID: PMC11310085 DOI: 10.1038/s41592-024-02341-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2023] [Accepted: 06/10/2024] [Indexed: 07/24/2024]
Abstract
Understanding protein function and developing molecular therapies require deciphering the cell types in which proteins act as well as the interactions between proteins. However, modeling protein interactions across biological contexts remains challenging for existing algorithms. Here we introduce PINNACLE, a geometric deep learning approach that generates context-aware protein representations. Leveraging a multiorgan single-cell atlas, PINNACLE learns on contextualized protein interaction networks to produce 394,760 protein representations from 156 cell type contexts across 24 tissues. PINNACLE's embedding space reflects cellular and tissue organization, enabling zero-shot retrieval of the tissue hierarchy. Pretrained protein representations can be adapted for downstream tasks: enhancing 3D structure-based representations for resolving immuno-oncological protein interactions, and investigating drugs' effects across cell types. PINNACLE outperforms state-of-the-art models in nominating therapeutic targets for rheumatoid arthritis and inflammatory bowel diseases and pinpoints cell type contexts with higher predictive capability than context-free models. PINNACLE's ability to adjust its outputs on the basis of the context in which it operates paves the way for large-scale context-specific predictions in biology.
Collapse
Affiliation(s)
- Michelle M Li
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Yepeng Huang
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Marissa Sumathipala
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Man Qing Liang
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | - Alberto Valdeolivas
- Roche Pharma Research and Early Development, Pharmaceutical Sciences, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd, Basel, Switzerland
| | - Ashwin N Ananthakrishnan
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
- Division of Gastroenterology, Massachusetts General Hospital, Boston, MA, USA
| | - Katherine Liao
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
- Division of Rheumatology, Inflammation, and Immunity, Brigham and Women's Hospital, Boston, MA, USA
| | - Daniel Marbach
- Roche Pharma Research and Early Development, Pharmaceutical Sciences, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd, Basel, Switzerland
| | - Marinka Zitnik
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
- Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Allston, MA, USA.
- Broad Institute of MIT and Harvard, Cambridge, MA, USA.
- Harvard Data Science Initiative, Cambridge, MA, USA.
| |
Collapse
|
16
|
Listov D, Goverde CA, Correia BE, Fleishman SJ. Opportunities and challenges in design and optimization of protein function. Nat Rev Mol Cell Biol 2024; 25:639-653. [PMID: 38565617 PMCID: PMC7616297 DOI: 10.1038/s41580-024-00718-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/27/2024] [Indexed: 04/04/2024]
Abstract
The field of protein design has made remarkable progress over the past decade. Historically, the low reliability of purely structure-based design methods limited their application, but recent strategies that combine structure-based and sequence-based calculations, as well as machine learning tools, have dramatically improved protein engineering and design. In this Review, we discuss how these methods have enabled the design of increasingly complex structures and therapeutically relevant activities. Additionally, protein optimization methods have improved the stability and activity of complex eukaryotic proteins. Thanks to their increased reliability, computational design methods have been applied to improve therapeutics and enzymes for green chemistry and have generated vaccine antigens, antivirals and drug-delivery nano-vehicles. Moreover, the high success of design methods reflects an increased understanding of basic rules that govern the relationships among protein sequence, structure and function. However, de novo design is still limited mostly to α-helix bundles, restricting its potential to generate sophisticated enzymes and diverse protein and small-molecule binders. Designing complex protein structures is a challenging but necessary next step if we are to realize our objective of generating new-to-nature activities.
Collapse
Affiliation(s)
- Dina Listov
- Department of Biomolecular Sciences, Weizmann Institute of Science, Rehovot, Israel
| | - Casper A Goverde
- Institute of Bioengineering, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
| | - Bruno E Correia
- Institute of Bioengineering, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland.
| | - Sarel Jacob Fleishman
- Department of Biomolecular Sciences, Weizmann Institute of Science, Rehovot, Israel.
| |
Collapse
|
17
|
Bigi F, Pozdnyakov SN, Ceriotti M. Wigner kernels: Body-ordered equivariant machine learning without a basis. J Chem Phys 2024; 161:044116. [PMID: 39056390 DOI: 10.1063/5.0208746] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2024] [Accepted: 06/10/2024] [Indexed: 07/28/2024] Open
Abstract
Machine-learning models based on a point-cloud representation of a physical object are ubiquitous in scientific applications and particularly well-suited to the atomic-scale description of molecules and materials. Among the many different approaches that have been pursued, the description of local atomic environments in terms of their discretized neighbor densities has been used widely and very successfully. We propose a novel density-based method, which involves computing "Wigner kernels." These are fully equivariant and body-ordered kernels that can be computed iteratively at a cost that is independent of the basis used to discretize the density and grows only linearly with the maximum body-order considered. Wigner kernels represent the infinite-width limit of feature-space models, whose dimensionality and computational cost instead scale exponentially with the increasing order of correlations. We present several examples of the accuracy of models based on Wigner kernels in chemical applications, for both scalar and tensorial targets, reaching an accuracy that is competitive with state-of-the-art deep-learning architectures. We discuss the broader relevance of these findings to equivariant geometric machine-learning.
Collapse
Affiliation(s)
- Filippo Bigi
- Laboratory of Computational Science and Modeling, Institut des Matériaux, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
| | - Sergey N Pozdnyakov
- Laboratory of Computational Science and Modeling, Institut des Matériaux, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
| | - Michele Ceriotti
- Laboratory of Computational Science and Modeling, Institut des Matériaux, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
| |
Collapse
|
18
|
Venkatraman V, Gaiser J, Demekas D, Roy A, Xiong R, Wheeler TJ. Do Molecular Fingerprints Identify Diverse Active Drugs in Large-Scale Virtual Screening? (No). Pharmaceuticals (Basel) 2024; 17:992. [PMID: 39204097 PMCID: PMC11356940 DOI: 10.3390/ph17080992] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2024] [Revised: 07/18/2024] [Accepted: 07/23/2024] [Indexed: 09/03/2024] Open
Abstract
Computational approaches for small-molecule drug discovery now regularly scale to the consideration of libraries containing billions of candidate small molecules. One promising approach to increased the speed of evaluating billion-molecule libraries is to develop succinct representations of each molecule that enable the rapid identification of molecules with similar properties. Molecular fingerprints are thought to provide a mechanism for producing such representations. Here, we explore the utility of commonly used fingerprints in the context of predicting similar molecular activity. We show that fingerprint similarity provides little discriminative power between active and inactive molecules for a target protein based on a known active-while they may sometimes provide some enrichment for active molecules in a drug screen, a screened data set will still be dominated by inactive molecules. We also demonstrate that high-similarity actives appear to share a scaffold with the query active, meaning that they could more easily be identified by structural enumeration. Furthermore, even when limited to only active molecules, fingerprint similarity values do not correlate with compound potency. In sum, these results highlight the need for a new wave of molecular representations that will improve the capacity to detect biologically active molecules based on their similarity to other such molecules.
Collapse
Affiliation(s)
- Vishwesh Venkatraman
- Department of Chemistry, Norwegian University of Science and Technology, 7034 Trondheim, Norway
| | - Jeremiah Gaiser
- School of Information, University of Arizona, Tucson, AZ 85721, USA
| | - Daphne Demekas
- R. Ken Coit College Pharmacy, University of Arizona, Tucson, AZ 85721, USA
| | - Amitava Roy
- Rocky Mountain Laboratories, Bioinformatics and Computational Biosciences Branch, Office of Cyber Infrastructure and Computational Biology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Hamilton, MT 59840, USA;
- Department of Biomedical and Pharmaceutical Sciences, University of Montana, Missoula, MT 59812, USA
| | - Rui Xiong
- Department of Pharmacology & Toxicology, University of Arizona, Tucson, AZ 85721, USA
| | - Travis J. Wheeler
- R. Ken Coit College Pharmacy, University of Arizona, Tucson, AZ 85721, USA
| |
Collapse
|
19
|
Shen A, Yuan M, Ma Y, Du J, Wang M. PGBind: pocket-guided explicit attention learning for protein-ligand docking. Brief Bioinform 2024; 25:bbae455. [PMID: 39293803 PMCID: PMC11410380 DOI: 10.1093/bib/bbae455] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2024] [Revised: 08/07/2024] [Accepted: 08/31/2024] [Indexed: 09/20/2024] Open
Abstract
As more and more protein structures are discovered, blind protein-ligand docking will play an important role in drug discovery because it can predict protein-ligand complex conformation without pocket information on the target proteins. Recently, deep learning-based methods have made significant advancements in blind protein-ligand docking, but their protein features are suboptimal because they do not fully consider the difference between potential pocket regions and non-pocket regions in protein feature extraction. In this work, we propose a pocket-guided strategy for guiding the ligand to dock to potential docking regions on a protein. To this end, we design a plug-and-play module to enhance the protein features, which can be directly incorporated into existing deep learning-based blind docking methods. The proposed module first estimates potential pocket regions on the target protein and then leverages a pocket-guided attention mechanism to enhance the protein features. Experiments are conducted on integrating our method with EquiBind and FABind, and the results show that their blind-docking performances are both significantly improved and new start-of-the-art performance is achieved by integration with FABind.
Collapse
Affiliation(s)
- Ao Shen
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 131 Dong’an Road, Shanghai 200032, China
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University, 131 Dong’an Road, Shanghai 200032, China
| | - Mingzhi Yuan
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 131 Dong’an Road, Shanghai 200032, China
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University, 131 Dong’an Road, Shanghai 200032, China
| | - Yingfan Ma
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 131 Dong’an Road, Shanghai 200032, China
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University, 131 Dong’an Road, Shanghai 200032, China
| | - Jie Du
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 131 Dong’an Road, Shanghai 200032, China
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University, 131 Dong’an Road, Shanghai 200032, China
| | - Manning Wang
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 131 Dong’an Road, Shanghai 200032, China
- Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University, 131 Dong’an Road, Shanghai 200032, China
| |
Collapse
|
20
|
Krapp LF, Meireles FA, Abriata LA, Devillard J, Vacle S, Marcaida MJ, Dal Peraro M. Context-aware geometric deep learning for protein sequence design. Nat Commun 2024; 15:6273. [PMID: 39054322 PMCID: PMC11272779 DOI: 10.1038/s41467-024-50571-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2023] [Accepted: 07/15/2024] [Indexed: 07/27/2024] Open
Abstract
Protein design and engineering are evolving at an unprecedented pace leveraging the advances in deep learning. Current models nonetheless cannot natively consider non-protein entities within the design process. Here, we introduce a deep learning approach based solely on a geometric transformer of atomic coordinates and element names that predicts protein sequences from backbone scaffolds aware of the restraints imposed by diverse molecular environments. To validate the method, we show that it can produce highly thermostable, catalytically active enzymes with high success rates. This concept is anticipated to improve the versatility of protein design pipelines for crafting desired functions.
Collapse
Affiliation(s)
- Lucien F Krapp
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland
| | - Fernando A Meireles
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland
| | - Luciano A Abriata
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland
| | - Jean Devillard
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL), Lausanne, Switzerland
| | - Sarah Vacle
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland
| | - Maria J Marcaida
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland
| | - Matteo Dal Peraro
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL), Lausanne, Switzerland.
- Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland.
| |
Collapse
|
21
|
Vornholt T, Mutný M, Schmidt GW, Schellhaas C, Tachibana R, Panke S, Ward TR, Krause A, Jeschek M. Enhanced Sequence-Activity Mapping and Evolution of Artificial Metalloenzymes by Active Learning. ACS CENTRAL SCIENCE 2024; 10:1357-1370. [PMID: 39071060 PMCID: PMC11273458 DOI: 10.1021/acscentsci.4c00258] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/15/2024] [Revised: 04/22/2024] [Accepted: 05/02/2024] [Indexed: 07/30/2024]
Abstract
Tailored enzymes are crucial for the transition to a sustainable bioeconomy. However, enzyme engineering is laborious and failure-prone due to its reliance on serendipity. The efficiency and success rates of engineering campaigns may be improved by applying machine learning to map the sequence-activity landscape based on small experimental data sets. Yet, it often proves challenging to reliably model large sequence spaces while keeping the experimental effort tractable. To address this challenge, we present an integrated pipeline combining large-scale screening with active machine learning, which we applied to engineer an artificial metalloenzyme (ArM) catalyzing a new-to-nature hydroamination reaction. Combining lab automation and next-generation sequencing, we acquired sequence-activity data for several thousand ArM variants. We then used Gaussian process regression to model the activity landscape and guide further screening rounds. Critical characteristics of our pipeline include the cost-effective generation of information-rich data sets, the integration of an explorative round to improve the model's performance, and the inclusion of experimental noise. Our approach led to an order-of-magnitude boost in the hit rate while making efficient use of experimental resources. Search strategies like this should find broad utility in enzyme engineering and accelerate the development of novel biocatalysts.
Collapse
Affiliation(s)
- Tobias Vornholt
- Department
of Biosystems Science and Engineering, ETH
Zurich, Mattenstrasse 26, 4058 Basel, Switzerland
- National
Centre of Competence in Research (NCCR) Molecular Systems Engineering, 4056 Basel,Switzerland
| | - Mojmír Mutný
- Department
of Computer Science, ETH Zurich, Andreasstrasse 5, 8092 Zurich, Switzerland
| | - Gregor W. Schmidt
- Department
of Biosystems Science and Engineering, ETH
Zurich, Mattenstrasse 26, 4058 Basel, Switzerland
| | - Christian Schellhaas
- Department
of Biosystems Science and Engineering, ETH
Zurich, Mattenstrasse 26, 4058 Basel, Switzerland
| | - Ryo Tachibana
- Department
of Chemistry, University of Basel, Mattenstrasse 24a, 4058 Basel, Switzerland
| | - Sven Panke
- Department
of Biosystems Science and Engineering, ETH
Zurich, Mattenstrasse 26, 4058 Basel, Switzerland
- National
Centre of Competence in Research (NCCR) Molecular Systems Engineering, 4056 Basel,Switzerland
| | - Thomas R. Ward
- National
Centre of Competence in Research (NCCR) Molecular Systems Engineering, 4056 Basel,Switzerland
- Department
of Chemistry, University of Basel, Mattenstrasse 24a, 4058 Basel, Switzerland
| | - Andreas Krause
- Department
of Computer Science, ETH Zurich, Andreasstrasse 5, 8092 Zurich, Switzerland
| | - Markus Jeschek
- Department
of Biosystems Science and Engineering, ETH
Zurich, Mattenstrasse 26, 4058 Basel, Switzerland
- Institute
of Microbiology, University of Regensburg, Universitätsstraße 31, 93053 Regensburg, Germany
| |
Collapse
|
22
|
Yuan Q, Tian C, Song Y, Ou P, Zhu M, Zhao H, Yang Y. GPSFun: geometry-aware protein sequence function predictions with language models. Nucleic Acids Res 2024; 52:W248-W255. [PMID: 38738636 PMCID: PMC11223820 DOI: 10.1093/nar/gkae381] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2024] [Revised: 04/22/2024] [Accepted: 04/26/2024] [Indexed: 05/14/2024] Open
Abstract
Knowledge of protein function is essential for elucidating disease mechanisms and discovering new drug targets. However, there is a widening gap between the exponential growth of protein sequences and their limited function annotations. In our prior studies, we have developed a series of methods including GraphPPIS, GraphSite, LMetalSite and SPROF-GO for protein function annotations at residue or protein level. To further enhance their applicability and performance, we now present GPSFun, a versatile web server for Geometry-aware Protein Sequence Function annotations, which equips our previous tools with language models and geometric deep learning. Specifically, GPSFun employs large language models to efficiently predict 3D conformations of the input protein sequences and extract informative sequence embeddings. Subsequently, geometric graph neural networks are utilized to capture the sequence and structure patterns in the protein graphs, facilitating various downstream predictions including protein-ligand binding sites, gene ontologies, subcellular locations and protein solubility. Notably, GPSFun achieves superior performance to state-of-the-art methods across diverse tasks without requiring multiple sequence alignments or experimental protein structures. GPSFun is freely available to all users at https://bio-web1.nscc-gz.cn/app/GPSFun with user-friendly interfaces and rich visualizations.
Collapse
Affiliation(s)
- Qianmu Yuan
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong 510000, China
| | - Chong Tian
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong 510000, China
| | - Yidong Song
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong 510000, China
| | - Peihua Ou
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong 510000, China
| | - Mingming Zhu
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong 510000, China
| | - Huiying Zhao
- Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong 510000, China
| | - Yuedong Yang
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong 510000, China
| |
Collapse
|
23
|
Lupo U, Sgarbossa D, Bitbol AF. Pairing interacting protein sequences using masked language modeling. Proc Natl Acad Sci U S A 2024; 121:e2311887121. [PMID: 38913900 PMCID: PMC11228504 DOI: 10.1073/pnas.2311887121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Accepted: 12/18/2023] [Indexed: 06/26/2024] Open
Abstract
Predicting which proteins interact together from amino acid sequences is an important task. We develop a method to pair interacting protein sequences which leverages the power of protein language models trained on multiple sequence alignments (MSAs), such as MSA Transformer and the EvoFormer module of AlphaFold. We formulate the problem of pairing interacting partners among the paralogs of two protein families in a differentiable way. We introduce a method called Differentiable Pairing using Alignment-based Language Models (DiffPALM) that solves it by exploiting the ability of MSA Transformer to fill in masked amino acids in multiple sequence alignments using the surrounding context. MSA Transformer encodes coevolution between functionally or structurally coupled amino acids within protein chains. It also captures inter-chain coevolution, despite being trained on single-chain data. Relying on MSA Transformer without fine-tuning, DiffPALM outperforms existing coevolution-based pairing methods on difficult benchmarks of shallow multiple sequence alignments extracted from ubiquitous prokaryotic protein datasets. It also outperforms an alternative method based on a state-of-the-art protein language model trained on single sequences. Paired alignments of interacting protein sequences are a crucial ingredient of supervised deep learning methods to predict the three-dimensional structure of protein complexes. Starting from sequences paired by DiffPALM substantially improves the structure prediction of some eukaryotic protein complexes by AlphaFold-Multimer. It also achieves competitive performance with using orthology-based pairing.
Collapse
Affiliation(s)
- Umberto Lupo
- Institute of Bioengineering, School of Life Sciences, École Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland
- SIB Swiss Institute of Bioinformatics, Lausanne CH-1015, Switzerland
| | - Damiano Sgarbossa
- Institute of Bioengineering, School of Life Sciences, École Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland
- SIB Swiss Institute of Bioinformatics, Lausanne CH-1015, Switzerland
| | - Anne-Florence Bitbol
- Institute of Bioengineering, School of Life Sciences, École Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland
- SIB Swiss Institute of Bioinformatics, Lausanne CH-1015, Switzerland
| |
Collapse
|
24
|
Xu S, Shen L, Zhang M, Jiang C, Zhang X, Xu Y, Liu J, Liu X. Surface-based multimodal protein-ligand binding affinity prediction. BIOINFORMATICS (OXFORD, ENGLAND) 2024; 40:btae413. [PMID: 38905501 DOI: 10.1093/bioinformatics/btae413] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/01/2024] [Revised: 05/15/2024] [Accepted: 06/19/2024] [Indexed: 06/23/2024]
Abstract
MOTIVATION In the field of drug discovery, accurately and effectively predicting the binding affinity between proteins and ligands is crucial for drug screening and optimization. However, current research primarily utilizes representations based on sequence or structure to predict protein-ligand binding affinity, with relatively less study on protein surface information, which is crucial for protein-ligand interactions. Moreover, when dealing with multimodal information of proteins, traditional approaches typically concatenate features from different modalities in a straightforward manner without considering the heterogeneity among them, which results in an inability to effectively exploit the complementary between modalities. RESULTS We introduce a novel multimodal feature extraction (MFE) framework that, for the first time, incorporates information from protein surfaces, 3D structures, and sequences, and uses cross-attention mechanism for feature alignment between different modalities. Experimental results show that our method achieves state-of-the-art performance in predicting protein-ligand binding affinity. Furthermore, we conduct ablation studies that demonstrate the effectiveness and necessity of protein surface information and multimodal feature alignment within the framework. AVAILABILITY AND IMPLEMENTATION The source code and data are available at https://github.com/Sultans0fSwing/MFE.
Collapse
Affiliation(s)
- Shiyu Xu
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen 361005, China
| | - Lian Shen
- Department of Computer Science and Technology, Xiamen University, Xiamen 361005, China
| | - Menglong Zhang
- Department of Computer Science and Technology, Xiamen University, Xiamen 361005, China
| | - Changzhi Jiang
- Department of Computer Science and Technology, Xiamen University, Xiamen 361005, China
| | - Xinyi Zhang
- Department of Computer Science and Technology, Xiamen University, Xiamen 361005, China
| | - Yanni Xu
- Department of Computer Science and Technology, Xiamen University, Xiamen 361005, China
| | - Juan Liu
- Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University, Xiamen 361005, China
| | - Xiangrong Liu
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen 361005, China
- Department of Computer Science and Technology, Xiamen University, Xiamen 361005, China
- Xiamen Key Laboratory of Intelligent Storage and Computing, Xiamen University, Xiamen 361005, China
| |
Collapse
|
25
|
Pegoraro M, Dominé C, Rodolà E, Veličković P, Deac A. Geometric epitope and paratope prediction. Bioinformatics 2024; 40:btae405. [PMID: 38984742 PMCID: PMC11245313 DOI: 10.1093/bioinformatics/btae405] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2023] [Revised: 05/14/2024] [Accepted: 07/09/2024] [Indexed: 07/11/2024] Open
Abstract
MOTIVATION Identifying the binding sites of antibodies is essential for developing vaccines and synthetic antibodies. In this article, we investigate the optimal representation for predicting the binding sites in the two molecules and emphasize the importance of geometric information. RESULTS Specifically, we compare different geometric deep learning methods applied to proteins' inner (I-GEP) and outer (O-GEP) structures. We incorporate 3D coordinates and spectral geometric descriptors as input features to fully leverage the geometric information. Our research suggests that different geometrical representation information is useful for different tasks. Surface-based models are more efficient in predicting the binding of the epitope, while graph models are better in paratope prediction, both achieving significant performance improvements. Moreover, we analyze the impact of structural changes in antibodies and antigens resulting from conformational rearrangements or reconstruction errors. Through this investigation, we showcase the robustness of geometric deep learning methods and spectral geometric descriptors to such perturbations. AVAILABILITY AND IMPLEMENTATION The python code for the models, together with the data and the processing pipeline, is open-source and available at https://github.com/Marco-Peg/GEP.
Collapse
Affiliation(s)
- Marco Pegoraro
- Department of Computer Science, Sapienza University of Rome, 00185, Italy
| | - Clémentine Dominé
- Gatsby Computational Neuroscience Unit, University College London, W1T 4JG, United-Kingdom
| | - Emanuele Rodolà
- Department of Computer Science, Sapienza University of Rome, 00185, Italy
| | | | - Andreea Deac
- Département d’informatique et de recherche opérationelle, Université de Montréal, QC H2S 3H1, Canada
| |
Collapse
|
26
|
Karnaukhov VK, Shcherbinin DS, Chugunov AO, Chudakov DM, Efremov RG, Zvyagin IV, Shugay M. Structure-based prediction of T cell receptor recognition of unseen epitopes using TCRen. NATURE COMPUTATIONAL SCIENCE 2024; 4:510-521. [PMID: 38987378 DOI: 10.1038/s43588-024-00653-0] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/16/2023] [Accepted: 06/04/2024] [Indexed: 07/12/2024]
Abstract
T cell receptor (TCR) recognition of foreign peptides presented by major histocompatibility complex protein is a major event in triggering the adaptive immune response to pathogens or cancer. The prediction of TCR-peptide interactions has great importance for therapy of cancer as well as infectious and autoimmune diseases but remains a major challenge, particularly for novel (unseen) peptide epitopes. Here we present TCRen, a structure-based method for ranking candidate unseen epitopes for a given TCR. The first stage of the TCRen pipeline is modeling of the TCR-peptide-major histocompatibility complex structure. Then a TCR-peptide residue contact map is extracted from this structure and used to rank all candidate epitopes on the basis of an interaction score with the target TCR. Scoring is performed using an energy potential derived from the statistics of TCR-peptide contact preferences in existing crystal structures. We show that TCRen has high performance in discriminating cognate versus unrelated peptides and can facilitate the identification of cancer neoepitopes recognized by tumor-infiltrating lymphocytes.
Collapse
MESH Headings
- Receptors, Antigen, T-Cell/immunology
- Receptors, Antigen, T-Cell/chemistry
- Receptors, Antigen, T-Cell/metabolism
- Humans
- Peptides/immunology
- Peptides/chemistry
- Epitopes/immunology
- Epitopes/chemistry
- Models, Molecular
- Neoplasms/immunology
- Epitopes, T-Lymphocyte/immunology
- Epitopes, T-Lymphocyte/chemistry
- Major Histocompatibility Complex/immunology
- Protein Conformation
- Lymphocytes, Tumor-Infiltrating/immunology
- Lymphocytes, Tumor-Infiltrating/metabolism
Collapse
Affiliation(s)
- Vadim K Karnaukhov
- Center of Life Sciences, Skolkovo Institute of Science and Technology, Moscow, Russia.
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia.
| | - Dmitrii S Shcherbinin
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia
- Institute of Translational Medicine, Center for Precision Genome Editing and Genetic Technologies for Biomedicine, Pirogov Russian National Research Medical University, Moscow, Russia
| | - Anton O Chugunov
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia
- Research Center for Molecular Mechanisms of Aging and Age-Related Diseases, Moscow Institute of Physics and Technology, Dolgoprudny, Russia
| | - Dmitriy M Chudakov
- Center of Life Sciences, Skolkovo Institute of Science and Technology, Moscow, Russia.
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia.
- Institute of Translational Medicine, Center for Precision Genome Editing and Genetic Technologies for Biomedicine, Pirogov Russian National Research Medical University, Moscow, Russia.
- Central European Institute of Technology, Brno, Czech Republic.
| | - Roman G Efremov
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia
- Research Center for Molecular Mechanisms of Aging and Age-Related Diseases, Moscow Institute of Physics and Technology, Dolgoprudny, Russia
- Higher School of Economics, Moscow, Russia
| | - Ivan V Zvyagin
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia
- Institute of Translational Medicine, Center for Precision Genome Editing and Genetic Technologies for Biomedicine, Pirogov Russian National Research Medical University, Moscow, Russia
| | - Mikhail Shugay
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia.
- Institute of Translational Medicine, Center for Precision Genome Editing and Genetic Technologies for Biomedicine, Pirogov Russian National Research Medical University, Moscow, Russia.
| |
Collapse
|
27
|
Bai Q, Xu T, Huang J, Pérez-Sánchez H. Geometric deep learning methods and applications in 3D structure-based drug design. Drug Discov Today 2024; 29:104024. [PMID: 38759948 DOI: 10.1016/j.drudis.2024.104024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2024] [Revised: 05/02/2024] [Accepted: 05/10/2024] [Indexed: 05/19/2024]
Abstract
3D structure-based drug design (SBDD) is considered a challenging and rational way for innovative drug discovery. Geometric deep learning is a promising approach that solves the accurate model training of 3D SBDD through building neural network models to learn non-Euclidean data, such as 3D molecular graphs and manifold data. Here, we summarize geometric deep learning methods and applications that contain 3D molecular representations, equivariant graph neural networks (EGNNs), and six generative model methods [diffusion model, flow-based model, generative adversarial networks (GANs), variational autoencoder (VAE), autoregressive models, and energy-based models]. Our review provides insights into geometric deep learning methods and advanced applications of 3D SBDD that will be of relevance for the drug discovery community.
Collapse
Affiliation(s)
- Qifeng Bai
- School of Basic Medical Sciences, Lanzhou University, Lanzhou 730000, Gansu, PR China.
| | | | - Junzhou Huang
- Department of Computer Science and Engineering, the University of Texas at Arlington, Arlington, TX 76019, USA
| | - Horacio Pérez-Sánchez
- Structural Bioinformatics and High Performance Computing Research Group (BIO-HPC), Computer Engineering Department, UCAM Universidad Católica de Murcia, Murcia 30107, Spain.
| |
Collapse
|
28
|
Travassos R, Martins SA, Fernandes A, Correia JDG, Melo R. Tailored Viral-like Particles as Drivers of Medical Breakthroughs. Int J Mol Sci 2024; 25:6699. [PMID: 38928403 PMCID: PMC11204272 DOI: 10.3390/ijms25126699] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2024] [Revised: 06/11/2024] [Accepted: 06/12/2024] [Indexed: 06/28/2024] Open
Abstract
Despite the recognized potential of nanoparticles, only a few formulations have progressed to clinical trials, and an even smaller number have been approved by the regulatory authorities and marketed. Virus-like particles (VLPs) have emerged as promising alternatives to conventional nanoparticles due to their safety, biocompatibility, immunogenicity, structural stability, scalability, and versatility. Furthermore, VLPs can be surface-functionalized with small molecules to improve circulation half-life and target specificity. Through the functionalization and coating of VLPs, it is possible to optimize the response properties to a given stimulus, such as heat, pH, an alternating magnetic field, or even enzymes. Surface functionalization can also modulate other properties, such as biocompatibility, stability, and specificity, deeming VLPs as potential vaccine candidates or delivery systems. This review aims to address the different types of surface functionalization of VLPs, highlighting the more recent cutting-edge technologies that have been explored for the design of tailored VLPs, their importance, and their consequent applicability in the medical field.
Collapse
Affiliation(s)
- Rafael Travassos
- Centro de Ciências e Tecnologias Nucleares, Instituto Superior Técnico, Universidade de Lisboa, CTN, Estrada Nacional 10 (km 139.7), 2695-066 Bobadela, Portugal; (R.T.); (S.A.M.); (A.F.)
| | - Sofia A. Martins
- Centro de Ciências e Tecnologias Nucleares, Instituto Superior Técnico, Universidade de Lisboa, CTN, Estrada Nacional 10 (km 139.7), 2695-066 Bobadela, Portugal; (R.T.); (S.A.M.); (A.F.)
| | - Ana Fernandes
- Centro de Ciências e Tecnologias Nucleares, Instituto Superior Técnico, Universidade de Lisboa, CTN, Estrada Nacional 10 (km 139.7), 2695-066 Bobadela, Portugal; (R.T.); (S.A.M.); (A.F.)
| | - João D. G. Correia
- Centro de Ciências e Tecnologias Nucleares, Instituto Superior Técnico, Universidade de Lisboa, CTN, Estrada Nacional 10 (km 139.7), 2695-066 Bobadela, Portugal; (R.T.); (S.A.M.); (A.F.)
- Departamento de Engenharia e Ciências Nucleares, Instituto Superior Técnico, Universidade de Lisboa, CTN, Estrada Nacional 10 (km 139.7), 2695-066 Bobadela, Portugal
| | - Rita Melo
- Centro de Ciências e Tecnologias Nucleares, Instituto Superior Técnico, Universidade de Lisboa, CTN, Estrada Nacional 10 (km 139.7), 2695-066 Bobadela, Portugal; (R.T.); (S.A.M.); (A.F.)
| |
Collapse
|
29
|
Richardson E, Trevizani R, Greenbaum JA, Carter H, Nielsen M, Peters B. The receiver operating characteristic curve accurately assesses imbalanced datasets. PATTERNS (NEW YORK, N.Y.) 2024; 5:100994. [PMID: 39005487 PMCID: PMC11240176 DOI: 10.1016/j.patter.2024.100994] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Revised: 03/05/2024] [Accepted: 05/03/2024] [Indexed: 07/16/2024]
Abstract
Many problems in biology require looking for a "needle in a haystack," corresponding to a binary classification where there are a few positives within a much larger set of negatives, which is referred to as a class imbalance. The receiver operating characteristic (ROC) curve and the associated area under the curve (AUC) have been reported as ill-suited to evaluate prediction performance on imbalanced problems where there is more interest in performance on the positive minority class, while the precision-recall (PR) curve is preferable. We show via simulation and a real case study that this is a misinterpretation of the difference between the ROC and PR spaces, showing that the ROC curve is robust to class imbalance, while the PR curve is highly sensitive to class imbalance. Furthermore, we show that class imbalance cannot be easily disentangled from classifier performance measured via PR-AUC.
Collapse
Affiliation(s)
- Eve Richardson
- Center for Infectious Disease and Vaccine Research, La Jolla Institute for Immunology, La Jolla, CA, USA
| | - Raphael Trevizani
- Center for Infectious Disease and Vaccine Research, La Jolla Institute for Immunology, La Jolla, CA, USA
- Fiocruz Ceará, Fundação Oswaldo Cruz, Rua São José s/n, Precabura, Eusébio/CE, Brazil
| | - Jason A Greenbaum
- Center for Infectious Disease and Vaccine Research, La Jolla Institute for Immunology, La Jolla, CA, USA
| | - Hannah Carter
- Department of Medicine, University of California, La Jolla, CA, USA
| | - Morten Nielsen
- Department of Health Technology, Section for Bioinformatics, Technical University of Denmark, Lyngby, Denmark
| | - Bjoern Peters
- Center for Infectious Disease and Vaccine Research, La Jolla Institute for Immunology, La Jolla, CA, USA
| |
Collapse
|
30
|
Li T, Huls NJ, Lu S, Hou P. Unsupervised manifold embedding to encode molecular quantum information for supervised learning of chemical data. Commun Chem 2024; 7:133. [PMID: 38862828 PMCID: PMC11166954 DOI: 10.1038/s42004-024-01217-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2024] [Accepted: 06/03/2024] [Indexed: 06/13/2024] Open
Abstract
Molecular representation is critical in chemical machine learning. It governs the complexity of model development and the fulfillment of training data to avoid either over- or under-fitting. As electronic structures and associated attributes are the root cause for molecular interactions and their manifested properties, we have sought to examine the local electron information on a molecular manifold to understand and predict molecular interactions. Our efforts led to the development of a lower-dimensional representation of a molecular manifold, Manifold Embedding of Molecular Surface (MEMS), to embody surface electronic quantities. By treating a molecular surface as a manifold and computing its embeddings, the embedded electronic attributes retain the chemical intuition of molecular interactions. MEMS can be further featurized as input for chemical learning. Our solubility prediction with MEMS demonstrated the feasibility of both shallow and deep learning by neural networks, suggesting that MEMS is expressive and robust against dimensionality reduction.
Collapse
Affiliation(s)
- Tonglei Li
- Deparment of Industrial and Molecular Pharmaceutics, Purdue University, West Lafayette, 47907, IN, USA.
| | - Nicholas J Huls
- Deparment of Industrial and Molecular Pharmaceutics, Purdue University, West Lafayette, 47907, IN, USA
| | - Shan Lu
- Deparment of Industrial and Molecular Pharmaceutics, Purdue University, West Lafayette, 47907, IN, USA
| | - Peng Hou
- Deparment of Industrial and Molecular Pharmaceutics, Purdue University, West Lafayette, 47907, IN, USA
| |
Collapse
|
31
|
Shankar SS, Banarjee R, Jathar SM, Rajesh S, Ramasamy S, Kulkarni MJ. De novo structure prediction of meteorin and meteorin-like protein for identification of domains, functional receptor binding regions, and their high-risk missense variants. J Biomol Struct Dyn 2024; 42:4522-4536. [PMID: 37288801 DOI: 10.1080/07391102.2023.2220804] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2023] [Accepted: 05/29/2023] [Indexed: 06/09/2023]
Abstract
Meteorin (Metrn) and Meteorin-like (Metrnl) are homologous secreted proteins involved in neural development and metabolic regulation. In this study, we have performed de novo structure prediction and analysis of both Metrn and Metrnl using Alphafold2 (AF2) and RoseTTAfold (RF). Based on the domain and structural homology analysis of the predicted structures, we have identified that these proteins are composed of two functional domains, a CUB domain and an NTR domain, connected by a hinge/loop region. We have identified the receptor binding regions of Metrn and Metrnl using the machine-learning tools ScanNet and Masif. These were further validated by docking Metrnl with its reported KIT receptor, thus establishing the role of each domain in the receptor interaction. Also, we have studied the effect of non-synonymous SNPs on the structure and function of these proteins using an array of bioinformatics tools and selected 16 missense variants in Metrn and 10 in Metrnl that can affect the protein stability. This is the first study to comprehensively characterize the functional domains of Metrn and Metrnl at their structural level and identify the functional domains, and protein binding regions. This study also highlights the interaction mechanism of the KIT receptor and Metrnl. The predicted deleterious SNPs will allow further understanding of the role of these variants in modulating the plasma levels of these proteins in disease conditions such as diabetes.Communicated by Ramaswamy H. Sarma.
Collapse
Affiliation(s)
- S Shiva Shankar
- Proteomics Facility, Division of Biochemical Sciences, CSIR-National Chemical Laboratory, Pune, India
- Academy of Scientific and Innovative Research (AcSIR), Ghaziabad, India
| | - Reema Banarjee
- Proteomics Facility, Division of Biochemical Sciences, CSIR-National Chemical Laboratory, Pune, India
| | - Swaraj M Jathar
- Proteomics Facility, Division of Biochemical Sciences, CSIR-National Chemical Laboratory, Pune, India
- Academy of Scientific and Innovative Research (AcSIR), Ghaziabad, India
| | - S Rajesh
- Proteomics Facility, Division of Biochemical Sciences, CSIR-National Chemical Laboratory, Pune, India
| | - Sureshkumar Ramasamy
- Proteomics Facility, Division of Biochemical Sciences, CSIR-National Chemical Laboratory, Pune, India
| | - Mahesh J Kulkarni
- Proteomics Facility, Division of Biochemical Sciences, CSIR-National Chemical Laboratory, Pune, India
- Academy of Scientific and Innovative Research (AcSIR), Ghaziabad, India
| |
Collapse
|
32
|
Sagendorf JM, Mitra R, Huang J, Chen XS, Rohs R. Structure-based prediction of protein-nucleic acid binding using graph neural networks. Biophys Rev 2024; 16:297-314. [PMID: 39345796 PMCID: PMC11427629 DOI: 10.1007/s12551-024-01201-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2024] [Accepted: 05/28/2024] [Indexed: 10/01/2024] Open
Abstract
Protein-nucleic acid (PNA) binding plays critical roles in the transcription, translation, regulation, and three-dimensional organization of the genome. Structural models of proteins bound to nucleic acids (NA) provide insights into the chemical, electrostatic, and geometric properties of the protein structure that give rise to NA binding but are scarce relative to models of unbound proteins. We developed a deep learning approach for predicting PNA binding given the unbound structure of a protein that we call PNAbind. Our method utilizes graph neural networks to encode the spatial distribution of physicochemical and geometric properties of protein structures that are predictive of NA binding. Using global physicochemical encodings, our models predict the overall binding function of a protein, and using local encodings, they predict the location of individual NA binding residues. Our models can discriminate between specificity for DNA or RNA binding, and we show that predictions made on computationally derived protein structures can be used to gain mechanistic understanding of chemical and structural features that determine NA recognition. Binding site predictions were validated against benchmark datasets, achieving AUROC scores in the range of 0.92-0.95. We applied our models to the HIV-1 restriction factor APOBEC3G and showed that our model predictions are consistent with and help explain experimental RNA binding data. Supplementary information The online version contains supplementary material available at 10.1007/s12551-024-01201-w.
Collapse
Affiliation(s)
- Jared M. Sagendorf
- Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA 90089 USA
- Present Address: Department of Bioengineering and Therapeutic Sciences, University of California San Francisco, San Francisco, CA 94158 USA
| | - Raktim Mitra
- Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA 90089 USA
| | - Jiawei Huang
- Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA 90089 USA
| | - Xiaojiang S. Chen
- Molecular and Computational Biology Section, Department of Biological Sciences, University of Southern California, Los Angeles, CA 90089 USA
- Department of Chemistry, University of Southern California, Los Angeles, CA 90089 USA
| | - Remo Rohs
- Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA 90089 USA
- Department of Chemistry, University of Southern California, Los Angeles, CA 90089 USA
- Department of Physics and Astronomy, University of Southern California, Los Angeles, CA 90089 USA
- Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA 90089 USA
| |
Collapse
|
33
|
Yang Q, Jin X, Zhou H, Ying J, Zou J, Liao Y, Lu X, Ge S, Yu H, Min X. SurfPro-NN: A 3D point cloud neural network for the scoring of protein-protein docking models based on surfaces features and protein language models. Comput Biol Chem 2024; 110:108067. [PMID: 38714420 DOI: 10.1016/j.compbiolchem.2024.108067] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2024] [Revised: 03/18/2024] [Accepted: 04/01/2024] [Indexed: 05/09/2024]
Abstract
Protein-protein interactions (PPI) play a crucial role in numerous key biological processes, and the structure of protein complexes provides valuable clues for in-depth exploration of molecular-level biological processes. Protein-protein docking technology is widely used to simulate the spatial structure of proteins. However, there are still challenges in selecting candidate decoys that closely resemble the native structure from protein-protein docking simulations. In this study, we introduce a docking evaluation method based on three-dimensional point cloud neural networks named SurfPro-NN, which represents protein structures as point clouds and learns interaction information from protein interfaces by applying a point cloud neural network. With the continuous advancement of deep learning in the field of biology, a series of knowledge-rich pre-trained models have emerged. We incorporate protein surface representation models and language models into our approach, greatly enhancing feature representation capabilities and achieving superior performance in protein docking model scoring tasks. Through comprehensive testing on public datasets, we find that our method outperforms state-of-the-art deep learning approaches in protein-protein docking model scoring. Not only does it significantly improve performance, but it also greatly accelerates training speed. This study demonstrates the potential of our approach in addressing protein interaction assessment problems, providing strong support for future research and applications in the field of biology.
Collapse
Affiliation(s)
- Qianli Yang
- Institute of Artifical Intelligence, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China.
| | - Xiaocheng Jin
- National Institute of Diagnostics and Vaccine Development in Infectious Diseases, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China; State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China; School of Public Health, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China
| | - Haixia Zhou
- School of Public Health, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China
| | - Junjie Ying
- Institute of Artifical Intelligence, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China
| | - JiaJun Zou
- School of Informatics, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China
| | - Yiyang Liao
- School of Informatics, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China
| | - Xiaoli Lu
- Information and Networking Center, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China
| | - Shengxiang Ge
- National Institute of Diagnostics and Vaccine Development in Infectious Diseases, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China; State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China; School of Public Health, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China
| | - Hai Yu
- National Institute of Diagnostics and Vaccine Development in Infectious Diseases, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China; State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China; School of Public Health, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China.
| | - Xiaoping Min
- School of Informatics, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China; National Institute of Diagnostics and Vaccine Development in Infectious Diseases, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China; State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics, XiaMen University, No. 422, Siming South Road, XiaMen, 361005, Fujian, China.
| |
Collapse
|
34
|
Rao J, Xie J, Yuan Q, Liu D, Wang Z, Lu Y, Zheng S, Yang Y. A variational expectation-maximization framework for balanced multi-scale learning of protein and drug interactions. Nat Commun 2024; 15:4476. [PMID: 38796523 DOI: 10.1038/s41467-024-48801-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Accepted: 05/14/2024] [Indexed: 05/28/2024] Open
Abstract
Protein functions are characterized by interactions with proteins, drugs, and other biomolecules. Understanding these interactions is essential for deciphering the molecular mechanisms underlying biological processes and developing new therapeutic strategies. Current computational methods mostly predict interactions based on either molecular network or structural information, without integrating them within a unified multi-scale framework. While a few multi-view learning methods are devoted to fusing the multi-scale information, these methods tend to rely intensively on a single scale and under-fitting the others, likely attributed to the imbalanced nature and inherent greediness of multi-scale learning. To alleviate the optimization imbalance, we present MUSE, a multi-scale representation learning framework based on a variant expectation maximization to optimize different scales in an alternating procedure over multiple iterations. This strategy efficiently fuses multi-scale information between atomic structure and molecular network scale through mutual supervision and iterative optimization. MUSE outperforms the current state-of-the-art models not only in molecular interaction (protein-protein, drug-protein, and drug-drug) tasks but also in protein interface prediction at the atomic structure scale. More importantly, the multi-scale learning framework shows potential for extension to other scales of computational drug discovery.
Collapse
Affiliation(s)
- Jiahua Rao
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Jiancong Xie
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Qianmu Yuan
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Deqin Liu
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Zhen Wang
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Yutong Lu
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China.
| | - Shuangjia Zheng
- Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China.
| | - Yuedong Yang
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China.
- Key Laboratory of Machine Intelligence and Advanced Computing (MOE), Sun Yat-sen University, Guangzhou, China.
- State Key Laboratory of Oncology in South China, Sun Yat-sen University, Guangzhou, China.
| |
Collapse
|
35
|
Joubbi S, Micheli A, Milazzo P, Maccari G, Ciano G, Cardamone D, Medini D. Antibody design using deep learning: from sequence and structure design to affinity maturation. Brief Bioinform 2024; 25:bbae307. [PMID: 38960409 PMCID: PMC11221890 DOI: 10.1093/bib/bbae307] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2024] [Revised: 05/20/2024] [Accepted: 06/12/2024] [Indexed: 07/05/2024] Open
Abstract
Deep learning has achieved impressive results in various fields such as computer vision and natural language processing, making it a powerful tool in biology. Its applications now encompass cellular image classification, genomic studies and drug discovery. While drug development traditionally focused deep learning applications on small molecules, recent innovations have incorporated it in the discovery and development of biological molecules, particularly antibodies. Researchers have devised novel techniques to streamline antibody development, combining in vitro and in silico methods. In particular, computational power expedites lead candidate generation, scaling and potential antibody development against complex antigens. This survey highlights significant advancements in protein design and optimization, specifically focusing on antibodies. This includes various aspects such as design, folding, antibody-antigen interactions docking and affinity maturation.
Collapse
Affiliation(s)
- Sara Joubbi
- Department of Computer Science, University of Pisa, Largo B. Pontecorvo, 3, 56127, Pisa, Italy
- Data Science for Health (DaScH) Lab, Fondazione Toscana Life Sciences, Via Fiorentina, 1, 53100, Siena, Italy
| | - Alessio Micheli
- Department of Computer Science, University of Pisa, Largo B. Pontecorvo, 3, 56127, Pisa, Italy
| | - Paolo Milazzo
- Department of Computer Science, University of Pisa, Largo B. Pontecorvo, 3, 56127, Pisa, Italy
| | - Giuseppe Maccari
- Data Science for Health (DaScH) Lab, Fondazione Toscana Life Sciences, Via Fiorentina, 1, 53100, Siena, Italy
| | - Giorgio Ciano
- Data Science for Health (DaScH) Lab, Fondazione Toscana Life Sciences, Via Fiorentina, 1, 53100, Siena, Italy
| | - Dario Cardamone
- Data Science for Health (DaScH) Lab, Fondazione Toscana Life Sciences, Via Fiorentina, 1, 53100, Siena, Italy
| | - Duccio Medini
- Data Science for Health (DaScH) Lab, Fondazione Toscana Life Sciences, Via Fiorentina, 1, 53100, Siena, Italy
| |
Collapse
|
36
|
Du W, Zhao L, Wu R, Huang B, Liu S, Liu Y, Huang H, Shi G. Predicting drug-Protein interaction with deep learning framework for molecular graphs and sequences: Potential candidates against SAR-CoV-2. PLoS One 2024; 19:e0299696. [PMID: 38728335 PMCID: PMC11086825 DOI: 10.1371/journal.pone.0299696] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2023] [Accepted: 02/14/2024] [Indexed: 05/12/2024] Open
Abstract
The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) caused the COVID-19 disease, which represents a new life-threatening disaster. Regarding viral infection, many therapeutics have been investigated to alleviate the epidemiology such as vaccines and receptor decoys. However, the continuous mutating coronavirus, especially the variants of Delta and Omicron, are tended to invalidate the therapeutic biological product. Thus, it is necessary to develop molecular entities as broad-spectrum antiviral drugs. Coronavirus replication is controlled by the viral 3-chymotrypsin-like cysteine protease (3CLpro) enzyme, which is required for the virus's life cycle. In the cases of severe acute respiratory syndrome coronavirus (SARS-CoV) and middle east respiratory syndrome coronavirus (MERS-CoV), 3CLpro has been shown to be a promising therapeutic development target. Here we proposed an attention-based deep learning framework for molecular graphs and sequences, training from the BindingDB 3CLpro dataset (114,555 compounds). After construction of such model, we conducted large-scale screening the in vivo/vitro dataset (276,003 compounds) from Zinc Database and visualize the candidate compounds with attention score. geometric-based affinity prediction was employed for validation. Finally, we established a 3CLpro-specific deep learning framework, namely GraphDPI-3CL (AUROC: 0.958) achieved superior performance beyond the existing state of the art model and discovered 10 molecules with a high binding affinity of 3CLpro and superior binding mode.
Collapse
Affiliation(s)
- Weian Du
- Department of Dermatology, Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
| | - Liang Zhao
- Shenzhen Health Development Research and Data Management Center, Shenzhen, China
| | - Rong Wu
- Department of Dermatology, Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
| | - Boning Huang
- School of Finance, Shanghai University of Finance and Economics, Shanghai, China
| | - Si Liu
- Department of Cosmetic and Plastic Surgery, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Yufeng Liu
- Department of Cosmetic and Plastic Surgery, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Huaiqiu Huang
- Department of Dermatology, Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
| | - Ge Shi
- Department of Cosmetic and Plastic Surgery, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| |
Collapse
|
37
|
Wilson E, Cava JK, Chowell D, Raja R, Mangalaparthi KK, Pandey A, Curtis M, Anderson KS, Singharoy A. The electrostatic landscape of MHC-peptide binding revealed using inception networks. Cell Syst 2024; 15:362-373.e7. [PMID: 38554709 DOI: 10.1016/j.cels.2024.03.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Revised: 11/24/2023] [Accepted: 03/05/2024] [Indexed: 04/02/2024]
Abstract
Predictive modeling of macromolecular recognition and protein-protein complementarity represents one of the cornerstones of biophysical sciences. However, such models are often hindered by the combinatorial complexity of interactions at the molecular interfaces. Exemplary of this problem is peptide presentation by the highly polymorphic major histocompatibility complex class I (MHC-I) molecule, a principal component of immune recognition. We developed human leukocyte antigen (HLA)-Inception, a deep biophysical convolutional neural network, which integrates molecular electrostatics to capture non-bonded interactions for predicting peptide binding motifs across 5,821 MHC-I alleles. These predictions of generated motifs correlate strongly with experimental peptide binding and presentation data. Beyond molecular interactions, the study demonstrates the application of predicted motifs in analyzing MHC-I allele associations with HIV disease progression and patient response to immune checkpoint inhibitors. A record of this paper's transparent peer review process is included in the supplemental information.
Collapse
Affiliation(s)
- Eric Wilson
- School of Molecular Sciences, Arizona State University, Tempe, AZ 85207, USA; The Precision Immunology Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA
| | - John Kevin Cava
- School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85207, USA
| | - Diego Chowell
- The Precision Immunology Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA
| | - Remya Raja
- Department of Immunology, Mayo Clinic, Scottsdale, AZ 85259, USA
| | - Kiran K Mangalaparthi
- Department of Laboratory Medicine and Pathology, Mayo Clinic, 200 First St SW, Rochester, MN 55905, USA
| | - Akhilesh Pandey
- Department of Laboratory Medicine and Pathology, Mayo Clinic, 200 First St SW, Rochester, MN 55905, USA; Center for Individualized Medicine, Mayo Clinic, 200 First St SW, Rochester, MN 55905, USA; Manipal Academy of Higher Education, Manipal 576104, Karnataka, India
| | - Marion Curtis
- Department of Immunology, Mayo Clinic, Scottsdale, AZ 85259, USA; College of Medicine and Science, Mayo Clinic, Scottsdale, AZ 85259, USA; Department of Cancer Biology, Mayo Clinic, Scottsdale, AZ 85259, USA
| | - Karen S Anderson
- School of Life Sciences, Arizona State University, Tempe, AZ 85207, USA.
| | - Abhishek Singharoy
- School of Molecular Sciences, Arizona State University, Tempe, AZ 85207, USA.
| |
Collapse
|
38
|
Yuan Q, Tian C, Yang Y. Genome-scale annotation of protein binding sites via language model and geometric deep learning. eLife 2024; 13:RP93695. [PMID: 38630609 PMCID: PMC11023698 DOI: 10.7554/elife.93695] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/19/2024] Open
Abstract
Revealing protein binding sites with other molecules, such as nucleic acids, peptides, or small ligands, sheds light on disease mechanism elucidation and novel drug design. With the explosive growth of proteins in sequence databases, how to accurately and efficiently identify these binding sites from sequences becomes essential. However, current methods mostly rely on expensive multiple sequence alignments or experimental protein structures, limiting their genome-scale applications. Besides, these methods haven't fully explored the geometry of the protein structures. Here, we propose GPSite, a multi-task network for simultaneously predicting binding residues of DNA, RNA, peptide, protein, ATP, HEM, and metal ions on proteins. GPSite was trained on informative sequence embeddings and predicted structures from protein language models, while comprehensively extracting residual and relational geometric contexts in an end-to-end manner. Experiments demonstrate that GPSite substantially surpasses state-of-the-art sequence-based and structure-based approaches on various benchmark datasets, even when the structures are not well-predicted. The low computational cost of GPSite enables rapid genome-scale binding residue annotations for over 568,000 sequences, providing opportunities to unveil unexplored associations of binding sites with molecular functions, biological processes, and genetic variants. The GPSite webserver and annotation database can be freely accessed at https://bio-web1.nscc-gz.cn/app/GPSite.
Collapse
Affiliation(s)
- Qianmu Yuan
- School of Computer Science and Engineering, Sun Yat-sen UniversityGuangzhouChina
| | - Chong Tian
- School of Computer Science and Engineering, Sun Yat-sen UniversityGuangzhouChina
| | - Yuedong Yang
- School of Computer Science and Engineering, Sun Yat-sen UniversityGuangzhouChina
| |
Collapse
|
39
|
Grassmann G, Miotto M, Desantis F, Di Rienzo L, Tartaglia GG, Pastore A, Ruocco G, Monti M, Milanetti E. Computational Approaches to Predict Protein-Protein Interactions in Crowded Cellular Environments. Chem Rev 2024; 124:3932-3977. [PMID: 38535831 PMCID: PMC11009965 DOI: 10.1021/acs.chemrev.3c00550] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Revised: 02/20/2024] [Accepted: 02/21/2024] [Indexed: 04/11/2024]
Abstract
Investigating protein-protein interactions is crucial for understanding cellular biological processes because proteins often function within molecular complexes rather than in isolation. While experimental and computational methods have provided valuable insights into these interactions, they often overlook a critical factor: the crowded cellular environment. This environment significantly impacts protein behavior, including structural stability, diffusion, and ultimately the nature of binding. In this review, we discuss theoretical and computational approaches that allow the modeling of biological systems to guide and complement experiments and can thus significantly advance the investigation, and possibly the predictions, of protein-protein interactions in the crowded environment of cell cytoplasm. We explore topics such as statistical mechanics for lattice simulations, hydrodynamic interactions, diffusion processes in high-viscosity environments, and several methods based on molecular dynamics simulations. By synergistically leveraging methods from biophysics and computational biology, we review the state of the art of computational methods to study the impact of molecular crowding on protein-protein interactions and discuss its potential revolutionizing effects on the characterization of the human interactome.
Collapse
Affiliation(s)
- Greta Grassmann
- Department
of Biochemical Sciences “Alessandro Rossi Fanelli”, Sapienza University of Rome, Rome 00185, Italy
- Center
for Life Nano & Neuro Science, Istituto
Italiano di Tecnologia, Rome 00161, Italy
| | - Mattia Miotto
- Center
for Life Nano & Neuro Science, Istituto
Italiano di Tecnologia, Rome 00161, Italy
| | - Fausta Desantis
- Center
for Life Nano & Neuro Science, Istituto
Italiano di Tecnologia, Rome 00161, Italy
- The
Open University Affiliated Research Centre at Istituto Italiano di
Tecnologia, Genoa 16163, Italy
| | - Lorenzo Di Rienzo
- Center
for Life Nano & Neuro Science, Istituto
Italiano di Tecnologia, Rome 00161, Italy
| | - Gian Gaetano Tartaglia
- Center
for Life Nano & Neuro Science, Istituto
Italiano di Tecnologia, Rome 00161, Italy
- Department
of Neuroscience and Brain Technologies, Istituto Italiano di Tecnologia, Genoa 16163, Italy
- Center
for Human Technologies, Genoa 16152, Italy
| | - Annalisa Pastore
- Experiment
Division, European Synchrotron Radiation
Facility, Grenoble 38043, France
| | - Giancarlo Ruocco
- Center
for Life Nano & Neuro Science, Istituto
Italiano di Tecnologia, Rome 00161, Italy
- Department
of Physics, Sapienza University, Rome 00185, Italy
| | - Michele Monti
- RNA
System Biology Lab, Department of Neuroscience and Brain Technologies, Istituto Italiano di Tecnologia, Genoa 16163, Italy
| | - Edoardo Milanetti
- Center
for Life Nano & Neuro Science, Istituto
Italiano di Tecnologia, Rome 00161, Italy
- Department
of Physics, Sapienza University, Rome 00185, Italy
| |
Collapse
|
40
|
Oliveira PF, Guedes RC, Falcao AO. Inferring molecular inhibition potency with AlphaFold predicted structures. Sci Rep 2024; 14:8252. [PMID: 38589418 PMCID: PMC11001998 DOI: 10.1038/s41598-024-58394-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2023] [Accepted: 03/28/2024] [Indexed: 04/10/2024] Open
Abstract
Even though in silico drug ligand-based methods have been successful in predicting interactions with known target proteins, they struggle with new, unassessed targets. To address this challenge, we propose an approach that integrates structural data from AlphaFold 2 predicted protein structures into machine learning models. Our method extracts 3D structural protein fingerprints and combines them with ligand structural data to train a single machine learning model. This model captures the relationship between ligand properties and the unique structural features of various target proteins, enabling predictions for never before tested molecules and protein targets. To assess our model, we used a dataset of 144 Human G-protein Coupled Receptors (GPCRs) with over 140,000 measured inhibition constants (Ki) values. Results strongly suggest that our approach performs as well as state-of-the-art ligand-based methods. In a second modeling approach that used 129 targets for training and a separate test set of 15 different protein targets, our model correctly predicted interactions for 73% of targets, with explained variances exceeding 0.50 in 22% of cases. Our findings further verified that the usage of experimentally determined protein structures produced models that were statistically indistinct from the Alphafold synthetic structures. This study presents a proteo-chemometric drug screening approach that uses a simple and scalable method for extracting protein structural information for usage in machine learning models capable of predicting protein-molecule interactions even for orphan targets.
Collapse
Affiliation(s)
- Pedro F Oliveira
- Lasige, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal
| | - Rita C Guedes
- Research Institute for Medicines (iMed.ULisboa), Faculdade de Farmácia, Universidade de Lisboa, Av. Prof. Gama Pinto, 1649-003 Lisboa, Portugal
| | - Andre O Falcao
- Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, 1749-016, Lisboa, Portugal.
| |
Collapse
|
41
|
Lu L, Gou X, Tan SK, Mann SI, Yang H, Zhong X, Gazgalis D, Valdiviezo J, Jo H, Wu Y, Diolaiti ME, Ashworth A, Polizzi NF, DeGrado WF. De novo design of drug-binding proteins with predictable binding energy and specificity. Science 2024; 384:106-112. [PMID: 38574125 PMCID: PMC11290694 DOI: 10.1126/science.adl5364] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2023] [Accepted: 02/28/2024] [Indexed: 04/06/2024]
Abstract
The de novo design of small molecule-binding proteins has seen exciting recent progress; however, high-affinity binding and tunable specificity typically require laborious screening and optimization after computational design. We developed a computational procedure to design a protein that recognizes a common pharmacophore in a series of poly(ADP-ribose) polymerase-1 inhibitors. One of three designed proteins bound different inhibitors with affinities ranging from <5 nM to low micromolar. X-ray crystal structures confirmed the accuracy of the designed protein-drug interactions. Molecular dynamics simulations informed the role of water in binding. Binding free energy calculations performed directly on the designed models were in excellent agreement with the experimentally measured affinities. We conclude that de novo design of high-affinity small molecule-binding proteins with tuned interaction energies is feasible entirely from computation.
Collapse
Affiliation(s)
- Lei Lu
- Department of Pharmaceutical Chemistry & Cardiovascular Research Institute, University of California, San Francisco, CA 94158, USA
| | - Xuxu Gou
- Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, CA 94158, USA
| | - Sophia K Tan
- Department of Pharmaceutical Chemistry & Cardiovascular Research Institute, University of California, San Francisco, CA 94158, USA
| | - Samuel I Mann
- Department of Pharmaceutical Chemistry & Cardiovascular Research Institute, University of California, San Francisco, CA 94158, USA
- Department of Chemistry, University of California, Riverside, CA 92521, USA
| | - Hyunjun Yang
- Department of Pharmaceutical Chemistry & Cardiovascular Research Institute, University of California, San Francisco, CA 94158, USA
| | - Xiaofang Zhong
- Department of Cellular and Molecular Pharmacology, University of California, San Francisco, CA 94158, USA
| | - Dimitrios Gazgalis
- Department of Cancer Biology, Dana-Farber Cancer Institute, Boston, MA 02215, USA
- Department of Biological Chemistry and Molecular Pharmacology, Harvard Medical School, Boston, MA 02215, USA
| | - Jesús Valdiviezo
- Department of Cancer Biology, Dana-Farber Cancer Institute, Boston, MA 02215, USA
- Department of Biological Chemistry and Molecular Pharmacology, Harvard Medical School, Boston, MA 02215, USA
| | - Hyunil Jo
- Department of Pharmaceutical Chemistry & Cardiovascular Research Institute, University of California, San Francisco, CA 94158, USA
| | - Yibing Wu
- Department of Pharmaceutical Chemistry & Cardiovascular Research Institute, University of California, San Francisco, CA 94158, USA
| | - Morgan E Diolaiti
- Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, CA 94158, USA
| | - Alan Ashworth
- Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, CA 94158, USA
| | - Nicholas F Polizzi
- Department of Cancer Biology, Dana-Farber Cancer Institute, Boston, MA 02215, USA
- Department of Biological Chemistry and Molecular Pharmacology, Harvard Medical School, Boston, MA 02215, USA
| | - William F DeGrado
- Department of Pharmaceutical Chemistry & Cardiovascular Research Institute, University of California, San Francisco, CA 94158, USA
| |
Collapse
|
42
|
Joshi CK, Liu F, Xun X, Lin J, Foo CS. On Representation Knowledge Distillation for Graph Neural Networks. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:4656-4667. [PMID: 36459610 DOI: 10.1109/tnnls.2022.3223018] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/17/2023]
Abstract
Knowledge distillation (KD) is a learning paradigm for boosting resource-efficient graph neural networks (GNNs) using more expressive yet cumbersome teacher models. Past work on distillation for GNNs proposed the local structure preserving (LSP) loss, which matches local structural relationships defined over edges across the student and teacher's node embeddings. This article studies whether preserving the global topology of how the teacher embeds graph data can be a more effective distillation objective for GNNs, as real-world graphs often contain latent interactions and noisy edges. We propose graph contrastive representation distillation (G-CRD), which uses contrastive learning to implicitly preserve global topology by aligning the student node embeddings to those of the teacher in a shared representation space. Additionally, we introduce an expanded set of benchmarks on large-scale real-world datasets where the performance gap between teacher and student GNNs is non-negligible. Experiments across four datasets and 14 heterogeneous GNN architectures show that G-CRD consistently boosts the performance and robustness of lightweight GNNs, outperforming LSP (and a global structure preserving (GSP) variant of LSP) as well as baselines from 2-D computer vision. An analysis of the representational similarity among teacher and student embedding spaces reveals that G-CRD balances preserving local and global relationships, while structure preserving approaches are best at preserving one or the other.
Collapse
|
43
|
Wei J, Xiao J, Chen S, Zong L, Gao X, Li Y. ProNet DB: a proteome-wise database for protein surface property representations and RNA-binding profiles. Database (Oxford) 2024; 2024:baae012. [PMID: 38557634 PMCID: PMC10984565 DOI: 10.1093/database/baae012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Revised: 01/08/2024] [Accepted: 02/17/2024] [Indexed: 04/04/2024]
Abstract
The rapid growth in the number of experimental and predicted protein structures and more complicated protein structures poses a significant challenge for computational biology in leveraging structural information and accurate representation of protein surface properties. Recently, AlphaFold2 released the comprehensive proteomes of various species, and protein surface property representation plays a crucial role in protein-molecule interaction predictions, including those involving proteins, nucleic acids and compounds. Here, we proposed the first extensive database, namely ProNet DB, that integrates multiple protein surface representations and RNA-binding landscape for 326 175 protein structures. This collection encompasses the 16 model organism proteomes from the AlphaFold Protein Structure Database and experimentally validated structures from the Protein Data Bank. For each protein, ProNet DB provides access to the original protein structures along with the detailed surface property representations encompassing hydrophobicity, charge distribution and hydrogen bonding potential as well as interactive features such as the interacting face and RNA-binding sites and preferences. To facilitate an intuitive interpretation of these properties and the RNA-binding landscape, ProNet DB incorporates visualization tools like Mol* and an Online 3D Viewer, allowing for the direct observation and analysis of these representations on protein surfaces. The availability of pre-computed features enables instantaneous access for users, significantly advancing computational biology research in areas such as molecular mechanism elucidation, geometry-based drug discovery and the development of novel therapeutic approaches. Database URL: https://proj.cse.cuhk.edu.hk/aihlab/pronet/.
Collapse
Affiliation(s)
- Junkang Wei
- Department of Computer Science and Engineering (CSE), The Chinese University of Hong Kong (CUHK), Chung Chi Rd, Ma Liu Shui, Hong Kong SAR 999077, China
| | - Jin Xiao
- Department of Computer Science and Engineering (CSE), The Chinese University of Hong Kong (CUHK), Chung Chi Rd, Ma Liu Shui, Hong Kong SAR 999077, China
| | - Siyuan Chen
- Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955, Kingdom of Saudi Arabia
- KAUST Computational Bioscience Research Center (CBRC), King Abdullah University of Science and Technology, Thuwal 23955, Kingdom of Saudi Arabia
| | - Licheng Zong
- Department of Computer Science and Engineering (CSE), The Chinese University of Hong Kong (CUHK), Chung Chi Rd, Ma Liu Shui, Hong Kong SAR 999077, China
| | - Xin Gao
- Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955, Kingdom of Saudi Arabia
- KAUST Computational Bioscience Research Center (CBRC), King Abdullah University of Science and Technology, Thuwal 23955, Kingdom of Saudi Arabia
| | - Yu Li
- Department of Computer Science and Engineering (CSE), The Chinese University of Hong Kong (CUHK), Chung Chi Rd, Ma Liu Shui, Hong Kong SAR 999077, China
- The CUHK Shenzhen Research Institute, 4 Gaoxin Ave Nanshan, Shenzhen 518057, China
- Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 45 Carleton Street, Cambridge, MA 02142, USA
- Wyss Institute for Biologically Inspired Engineering, Harvard University, 201 Brookline Avenue, Boston, MA 02215, USA
- Broad Institute of MIT and Harvard, Merkin Building, 415 Main Street, Cambridge, MA 02142, USA
| |
Collapse
|
44
|
Terranova N, Renard D, Shahin MH, Menon S, Cao Y, Hop CECA, Hayes S, Madrasi K, Stodtmann S, Tensfeldt T, Vaddady P, Ellinwood N, Lu J. Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices. Clin Pharmacol Ther 2024; 115:658-672. [PMID: 37716910 DOI: 10.1002/cpt.3053] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2023] [Accepted: 09/11/2023] [Indexed: 09/18/2023]
Abstract
Recent breakthroughs in artificial intelligence (AI) and machine learning (ML) have ushered in a new era of possibilities across various scientific domains. One area where these advancements hold significant promise is model-informed drug discovery and development (MID3). To foster a wider adoption and acceptance of these advanced algorithms, the Innovation and Quality (IQ) Consortium initiated the AI/ML working group in 2021 with the aim of promoting their acceptance among the broader scientific community as well as by regulatory agencies. By drawing insights from workshops organized by the working group and attended by key stakeholders across the biopharma industry, academia, and regulatory agencies, this white paper provides a perspective from the IQ Consortium. The range of applications covered in this white paper encompass the following thematic topics: (i) AI/ML-enabled Analytics for Pharmacometrics and Quantitative Systems Pharmacology (QSP) Workflows; (ii) Explainable Artificial Intelligence and its Applications in Disease Progression Modeling; (iii) Natural Language Processing (NLP) in Quantitative Pharmacology Modeling; and (iv) AI/ML Utilization in Drug Discovery. Additionally, the paper offers a set of best practices to ensure an effective and responsible use of AI, including considering the context of use, explainability and generalizability of models, and having human-in-the-loop. We believe that embracing the transformative power of AI in quantitative modeling while adopting a set of good practices can unlock new opportunities for innovation, increase efficiency, and ultimately bring benefits to patients.
Collapse
Affiliation(s)
- Nadia Terranova
- Quantitative Pharmacology, Merck KGaA, Lausanne, Switzerland
| | - Didier Renard
- Full Development Pharmacometrics, Novartis Pharma AG, Basel, Switzerland
| | | | - Sujatha Menon
- Clinical Pharmacology, Pfizer Inc., Groton, Connecticut, USA
| | - Youfang Cao
- Clinical Pharmacology and Translational Medicine, Eisai Inc., Nutley, New Jersey, USA
| | | | - Sean Hayes
- Quantitative Pharmacology & Pharmacometrics, Merck & Co. Inc., Rahway, New Jersey, USA
| | - Kumpal Madrasi
- Modeling & Simulation, Sanofi, Bridgewater, New Jersey, USA
| | - Sven Stodtmann
- Pharmacometrics, AbbVie Deutschland GmbH & Co. KG, Ludwigshafen, Germany
| | | | - Pavan Vaddady
- Quantitative Clinical Pharmacology, Daiichi Sankyo, Inc., Basking Ridge, New Jersey, USA
| | | | - James Lu
- Clinical Pharmacology, Genentech Inc., South San Francisco, California, USA
| |
Collapse
|
45
|
Li C, Yao J, Wei W, Niu Z, Zeng X, Li J, Wang J. Geometry-Based Molecular Generation With Deep Constrained Variational Autoencoder. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:4852-4861. [PMID: 35171779 DOI: 10.1109/tnnls.2022.3147790] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Finding target molecules with specific chemical properties plays a decisive role in drug development. We proposed GEOM-CVAE, a constrained variational autoencoder based on geometric representation for molecular generation with specific properties, which is protein-context-dependent. In terms of machine learning, it includes continuous feature embedding encoder and molecular generation decoder. Our key contribution is to propose an efficient geometric embedding method, including the spatial structure representations of drug molecule (converting the 3-D coordinates into image) and the geometric graph representations of protein target (modeling the protein surface as a mesh). The 3-D geometric information is vital to successful molecular generation, which is different from previous molecular generative methods based on 1-D or 2-D. Our model framework generates specific molecules in two phases, by first generating special image with molecular 3-D information to learn latent representations and generating molecules with constrained condition based on geometric graph convolution for specific protein and then inputting the generated structural molecules into a parser network for obtaining Simplified Molecular Input Line Entry System (SMILES) strings. Our model achieves competitive performance that implies its potential effectiveness to enable the exploration of the vast chemical space for drug discovery.
Collapse
|
46
|
Song FV, Su J, Huang S, Zhang N, Li K, Ni M, Liao M. DeepSS2GO: protein function prediction from secondary structure. Brief Bioinform 2024; 25:bbae196. [PMID: 38701416 PMCID: PMC11066904 DOI: 10.1093/bib/bbae196] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2024] [Revised: 03/31/2024] [Accepted: 04/10/2024] [Indexed: 05/05/2024] Open
Abstract
Predicting protein function is crucial for understanding biological life processes, preventing diseases and developing new drug targets. In recent years, methods based on sequence, structure and biological networks for protein function annotation have been extensively researched. Although obtaining a protein in three-dimensional structure through experimental or computational methods enhances the accuracy of function prediction, the sheer volume of proteins sequenced by high-throughput technologies presents a significant challenge. To address this issue, we introduce a deep neural network model DeepSS2GO (Secondary Structure to Gene Ontology). It is a predictor incorporating secondary structure features along with primary sequence and homology information. The algorithm expertly combines the speed of sequence-based information with the accuracy of structure-based features while streamlining the redundant data in primary sequences and bypassing the time-consuming challenges of tertiary structure analysis. The results show that the prediction performance surpasses state-of-the-art algorithms. It has the ability to predict key functions by effectively utilizing secondary structure information, rather than broadly predicting general Gene Ontology terms. Additionally, DeepSS2GO predicts five times faster than advanced algorithms, making it highly applicable to massive sequencing data. The source code and trained models are available at https://github.com/orca233/DeepSS2GO.
Collapse
Affiliation(s)
- Fu V Song
- Department of Chemical Biology, School of Life Sciences, Southern University of Science and Technology, Xueyuan Avenue, 518055, Shenzhen, China
| | - Jiaqi Su
- Department of Chemical Biology, School of Life Sciences, Southern University of Science and Technology, Xueyuan Avenue, 518055, Shenzhen, China
| | - Sixing Huang
- Gemini Data Japan, Kitaku Oujikamiya 1-11-11, 115-0043, Tokyo, Japan
| | - Neng Zhang
- Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, E1 4NS, London, UK
| | - Kaiyue Li
- Department of Chemical Biology, School of Life Sciences, Southern University of Science and Technology, Xueyuan Avenue, 518055, Shenzhen, China
| | - Ming Ni
- MGI Tech, Beishan Industrial Zone, 518083, Shenzhen, China
| | - Maofu Liao
- Department of Chemical Biology, School of Life Sciences, Southern University of Science and Technology, Xueyuan Avenue, 518055, Shenzhen, China
- Institute for Biological Electron Microscopy, Southern University of Science and Technology, Xueyuan Avenue, 518055, Shenzhen, China
| |
Collapse
|
47
|
Jia P, Zhang F, Wu C, Li M. A comprehensive review of protein-centric predictors for biomolecular interactions: from proteins to nucleic acids and beyond. Brief Bioinform 2024; 25:bbae162. [PMID: 38739759 PMCID: PMC11089422 DOI: 10.1093/bib/bbae162] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/01/2024] [Revised: 02/17/2024] [Accepted: 03/31/2024] [Indexed: 05/16/2024] Open
Abstract
Proteins interact with diverse ligands to perform a large number of biological functions, such as gene expression and signal transduction. Accurate identification of these protein-ligand interactions is crucial to the understanding of molecular mechanisms and the development of new drugs. However, traditional biological experiments are time-consuming and expensive. With the development of high-throughput technologies, an increasing amount of protein data is available. In the past decades, many computational methods have been developed to predict protein-ligand interactions. Here, we review a comprehensive set of over 160 protein-ligand interaction predictors, which cover protein-protein, protein-nucleic acid, protein-peptide and protein-other ligands (nucleotide, heme, ion) interactions. We have carried out a comprehensive analysis of the above four types of predictors from several significant perspectives, including their inputs, feature profiles, models, availability, etc. The current methods primarily rely on protein sequences, especially utilizing evolutionary information. The significant improvement in predictions is attributed to deep learning methods. Additionally, sequence-based pretrained models and structure-based approaches are emerging as new trends.
Collapse
Affiliation(s)
- Pengzhen Jia
- School of Computer Science and Engineering, Central South University, 932 Lushan Road(S), Changsha 410083, China
| | - Fuhao Zhang
- School of Computer Science and Engineering, Central South University, 932 Lushan Road(S), Changsha 410083, China
- College of Information Engineering, Northwest A&F University, No. 3 Taicheng Road, Yangling, Shaanxi 712100, China
| | - Chaojin Wu
- School of Computer Science and Engineering, Central South University, 932 Lushan Road(S), Changsha 410083, China
| | - Min Li
- School of Computer Science and Engineering, Central South University, 932 Lushan Road(S), Changsha 410083, China
| |
Collapse
|
48
|
Kim LJ, Shin D, Leite WC, O’Neill H, Ruebel O, Tritt A, Hura GL. Simple Scattering: Lipid nanoparticle structural data repository. Front Mol Biosci 2024; 11:1321364. [PMID: 38584701 PMCID: PMC10998447 DOI: 10.3389/fmolb.2024.1321364] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2023] [Accepted: 02/19/2024] [Indexed: 04/09/2024] Open
Abstract
Lipid nanoparticles (LNPs) are being intensively researched and developed to leverage their ability to safely and effectively deliver therapeutics. To achieve optimal therapeutic delivery, a comprehensive understanding of the relationship between formulation, structure, and efficacy is critical. However, the vast chemical space involved in the production of LNPs and the resulting structural complexity make the structure to function relationship challenging to assess and predict. New components and formulation procedures, which provide new opportunities for the use of LNPs, would be best identified and optimized using high-throughput characterization methods. Recently, a high-throughput workflow, consisting of automated mixing, small-angle X-ray scattering (SAXS), and cellular assays, demonstrated a link between formulation, internal structure, and efficacy for a library of LNPs. As SAXS data can be rapidly collected, the stage is set for the collection of thousands of SAXS profiles from a myriad of LNP formulations. In addition, correlated LNP small-angle neutron scattering (SANS) datasets, where components are systematically deuterated for additional contrast inside, provide complementary structural information. The centralization of SAXS and SANS datasets from LNPs, with appropriate, standardized metadata describing formulation parameters, into a data repository will provide valuable guidance for the formulation of LNPs with desired properties. To this end, we introduce Simple Scattering, an easy-to-use, open data repository for storing and sharing groups of correlated scattering profiles obtained from LNP screening experiments. Here, we discuss the current state of the repository, including limitations and upcoming changes, and our vision towards future usage in developing our collective knowledge base of LNPs.
Collapse
Affiliation(s)
- Lee Joon Kim
- Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA, United States
| | - David Shin
- David Shin Consulting, Berkeley, CA, United States
| | - Wellington C. Leite
- Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, TN, United States
| | - Hugh O’Neill
- Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, TN, United States
| | - Oliver Ruebel
- Scientific Data Division, Lawrence Berkeley National Laboratory, Berkeley, CA, United States
| | - Andrew Tritt
- Applied Mathematics and Computational Science Division, Lawrence Berkeley National Laboratory, Berkeley, CA, United States
| | - Greg L. Hura
- Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA, United States
- Department of Chemistry and Biochemistry, University of California Santa Cruz, Santa Cruz, CA, United States
| |
Collapse
|
49
|
Wu X, Lin H, Bai R, Duan H. Deep learning for advancing peptide drug development: Tools and methods in structure prediction and design. Eur J Med Chem 2024; 268:116262. [PMID: 38387334 DOI: 10.1016/j.ejmech.2024.116262] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2024] [Revised: 02/06/2024] [Accepted: 02/17/2024] [Indexed: 02/24/2024]
Abstract
Peptides can bind challenging disease targets with high affinity and specificity, offering enormous opportunities for addressing unmet medical needs. However, peptides' unique features, including smaller size, increased structural flexibility, and limited data availability, pose additional challenges to the design process compared to proteins. This review explores the dynamic field of peptide therapeutics, leveraging deep learning to enhance structure prediction and design. Our exploration encompasses various facets of peptide research, ranging from dataset curation handling to model development. As deep learning technologies become more refined, we channel our efforts into peptide structure prediction and design, aligning with the fundamental principles of structure-activity relationships in drug development. To guide researchers in harnessing the potential of deep learning to advance peptide drug development, our insights comprehensively explore current challenges and future directions of peptide therapeutics.
Collapse
Affiliation(s)
- Xinyi Wu
- College of Pharmaceutical Sciences, Zhejiang University of Technology, Hangzhou, 310014, PR China
| | - Huitian Lin
- College of Pharmaceutical Sciences, Zhejiang University of Technology, Hangzhou, 310014, PR China
| | - Renren Bai
- School of Pharmacy, Hangzhou Normal University, Hangzhou, 311121, PR China.
| | - Hongliang Duan
- Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, PR China.
| |
Collapse
|
50
|
Goshisht MK. Machine Learning and Deep Learning in Synthetic Biology: Key Architectures, Applications, and Challenges. ACS OMEGA 2024; 9:9921-9945. [PMID: 38463314 PMCID: PMC10918679 DOI: 10.1021/acsomega.3c05913] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Revised: 01/19/2024] [Accepted: 01/30/2024] [Indexed: 03/12/2024]
Abstract
Machine learning (ML), particularly deep learning (DL), has made rapid and substantial progress in synthetic biology in recent years. Biotechnological applications of biosystems, including pathways, enzymes, and whole cells, are being probed frequently with time. The intricacy and interconnectedness of biosystems make it challenging to design them with the desired properties. ML and DL have a synergy with synthetic biology. Synthetic biology can be employed to produce large data sets for training models (for instance, by utilizing DNA synthesis), and ML/DL models can be employed to inform design (for example, by generating new parts or advising unrivaled experiments to perform). This potential has recently been brought to light by research at the intersection of engineering biology and ML/DL through achievements like the design of novel biological components, best experimental design, automated analysis of microscopy data, protein structure prediction, and biomolecular implementations of ANNs (Artificial Neural Networks). I have divided this review into three sections. In the first section, I describe predictive potential and basics of ML along with myriad applications in synthetic biology, especially in engineering cells, activity of proteins, and metabolic pathways. In the second section, I describe fundamental DL architectures and their applications in synthetic biology. Finally, I describe different challenges causing hurdles in the progress of ML/DL and synthetic biology along with their solutions.
Collapse
Affiliation(s)
- Manoj Kumar Goshisht
- Department of Chemistry, Natural and
Applied Sciences, University of Wisconsin—Green
Bay, Green
Bay, Wisconsin 54311-7001, United States
| |
Collapse
|