1
|
Ghazikhani H, Butler G. Exploiting protein language models for the precise classification of ion channels and ion transporters. Proteins 2024; 92:998-1055. [PMID: 38656743 DOI: 10.1002/prot.26694] [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: 08/31/2023] [Revised: 03/26/2024] [Accepted: 04/08/2024] [Indexed: 04/26/2024]
Abstract
This study introduces TooT-PLM-ionCT, a comprehensive framework that consolidates three distinct systems, each meticulously tailored for one of the following tasks: distinguishing ion channels (ICs) from membrane proteins (MPs), segregating ion transporters (ITs) from MPs, and differentiating ICs from ITs. Drawing upon the strengths of six Protein Language Models (PLMs)-ProtBERT, ProtBERT-BFD, ESM-1b, ESM-2 (650M parameters), and ESM-2 (15B parameters), TooT-PLM-ionCT employs a combination of traditional classifiers and deep learning models for nuanced protein classification. Originally validated on an existing dataset by previous researchers, our systems demonstrated superior performance in identifying ITs from MPs and distinguishing ICs from ITs, with the IC-MP discrimination achieving state-of-the-art results. In light of recommendations for additional validation, we introduced a new dataset, significantly enhancing the robustness and generalization of our models across bioinformatics challenges. This new evaluation underscored the effectiveness of TooT-PLM-ionCT in adapting to novel data while maintaining high classification accuracy. Furthermore, this study explores critical factors affecting classification accuracy, such as dataset balancing, the impact of using frozen versus fine-tuned PLM representations, and the variance between half and full precision in floating-point computations. To facilitate broader application and accessibility, a web server (https://tootsuite.encs.concordia.ca/service/TooT-PLM-ionCT) has been developed, allowing users to evaluate unknown protein sequences through our specialized systems for IC-MP, IT-MP, and IC-IT classification tasks.
Collapse
Affiliation(s)
- Hamed Ghazikhani
- Department of Computer Science and Software Engineering, Concordia University, Montréal, Québec, Canada
| | - Gregory Butler
- Centre for Structural and Functional Genomics, Concordia University, Montréal, Québec, Canada
| |
Collapse
|
2
|
Le VT, Malik MS, Tseng YH, Lee YC, Huang CI, Ou YY. DeepPLM_mCNN: An approach for enhancing ion channel and ion transporter recognition by multi-window CNN based on features from pre-trained language models. Comput Biol Chem 2024; 110:108055. [PMID: 38555810 DOI: 10.1016/j.compbiolchem.2024.108055] [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: 12/24/2023] [Revised: 02/28/2024] [Accepted: 03/19/2024] [Indexed: 04/02/2024]
Abstract
Accurate classification of membrane proteins like ion channels and transporters is critical for elucidating cellular processes and drug development. We present DeepPLM_mCNN, a novel framework combining Pretrained Language Models (PLMs) and multi-window convolutional neural networks (mCNNs) for effective classification of membrane proteins into ion channels and ion transporters. Our approach extracts informative features from protein sequences by utilizing various PLMs, including TAPE, ProtT5_XL_U50, ESM-1b, ESM-2_480, and ESM-2_1280. These PLM-derived features are then input into a mCNN architecture to learn conserved motifs important for classification. When evaluated on ion transporters, our best performing model utilizing ProtT5 achieved 90% sensitivity, 95.8% specificity, and 95.4% overall accuracy. For ion channels, we obtained 88.3% sensitivity, 95.7% specificity, and 95.2% overall accuracy using ESM-1b features. Our proposed DeepPLM_mCNN framework demonstrates significant improvements over previous methods on unseen test data. This study illustrates the potential of combining PLMs and deep learning for accurate computational identification of membrane proteins from sequence data alone. Our findings have important implications for membrane protein research and drug development targeting ion channels and transporters. The data and source codes in this study are publicly available at the following link: https://github.com/s1129108/DeepPLM_mCNN.
Collapse
Affiliation(s)
- Van-The Le
- Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan
| | - Muhammad-Shahid Malik
- Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan; Department of Computer Science and Engineering, Karakoram International University, Pakistan
| | - Yi-Hsuan Tseng
- Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan
| | - Yu-Cheng Lee
- Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan
| | - Cheng-I Huang
- Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan
| | - Yu-Yen Ou
- Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan; Graduate Program in Biomedical Informatics, Yuan Ze University, Chung-Li, 32003, Taiwan.
| |
Collapse
|
3
|
Richter-Laskowska M, Wawrzkiewicz-Jalowiecka A, Bies A, Trybek P. Machine Learning Methods for the Analysis of the Patch-Clamp Signals. Methods Mol Biol 2024; 2796:249-270. [PMID: 38856906 DOI: 10.1007/978-1-0716-3818-7_15] [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] [Indexed: 06/11/2024]
Abstract
Patch-clamp technique provides a unique possibility to record the ion channels' activity. This method enables tracking the changes in their functional states at controlled conditions on a real-time scale. Kinetic parameters evaluated for the patch-clamp signals form the fundamentals of electrophysiological characteristics of the channel functioning. Nevertheless, the noisy series of ionic currents flowing through the channel protein(s) seem to be bountiful of information, and the standard data processing techniques likely unravel only its part. Rapid development of artificial intelligence (AI) techniques, especially machine learning (ML), gives new prospects for whole channelology. Here we consider the question of the AI applications in the patch-clamp signal analysis. It turns out that the AI methods may not only enable for automatizing of signal analysis, but also they can be used in finding inherent patterns of channel gating and allow the researchers to uncover the details of gating machinery, which had been never considered before. In this work, we outline the currently known AI methods that turned out to be utilizable and useful in the analysis of patch-clamp signals. This chapter can be considered an introductory guide to the application of AI methods in the analysis of the time series of channel currents (together with its advantages, disadvantages, and limitations), but we also propose new possible directions in this field.
Collapse
Affiliation(s)
- Monika Richter-Laskowska
- Lukasiewicz Research Network - Krakow Institute of Technology, The Centre for Biomedical Engineering, Kraków, Poland.
| | | | - Aleksander Bies
- Faculty of Science and Technology, Institute of Computer Science, University of Silesia, Sosnowiec, Poland
| | - Paulina Trybek
- Faculty of Science and Technology, Institute of Physics, University of Silesia in Katowice, Chorzow, Poland
| |
Collapse
|
4
|
Hasanzadeh A, Hamblin MR, Kiani J, Noori H, Hardie JM, Karimi M, Shafiee H. Could artificial intelligence revolutionize the development of nanovectors for gene therapy and mRNA vaccines? NANO TODAY 2022; 47:101665. [PMID: 37034382 PMCID: PMC10081506 DOI: 10.1016/j.nantod.2022.101665] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
Gene therapy enables the introduction of nucleic acids like DNA and RNA into host cells, and is expected to revolutionize the treatment of a wide range of diseases. This growth has been further accelerated by the discovery of CRISPR/Cas technology, which allows accurate genomic editing in a broad range of cells and organisms in vitro and in vivo. Despite many advances in gene delivery and the development of various viral and non-viral gene delivery vectors, the lack of highly efficient non-viral systems with low cellular toxicity remains a challenge. The application of cutting-edge technologies such as artificial intelligence (AI) has great potential to find new paradigms to solve this issue. Herein, we review AI and its major subfields including machine learning (ML), neural networks (NNs), expert systems, deep learning (DL), computer vision and robotics. We discuss the potential of AI-based models and algorithms in the design of targeted gene delivery vehicles capable of crossing extracellular and intracellular barriers by viral mimicry strategies. We finally discuss the role of AI in improving the function of CRISPR/Cas systems, developing novel nanobots, and mRNA vaccine carriers.
Collapse
Affiliation(s)
- Akbar Hasanzadeh
- Cellular and Molecular Research Center, Iran University of Medical Sciences, Tehran 1449614535, Iran
- Department of Medical Nanotechnology, Faculty of Advanced Technologies in Medicine, Iran University of Medical Sciences, Tehran 1449614535, Iran
| | - Michael R Hamblin
- Laser Research Centre, Faculty of Health Science, University of Johannesburg, Doornfontein 2028, South Africa
- Radiation Biology Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Jafar Kiani
- Oncopathology Research Center, Iran University of Medical Sciences, Tehran 1449614535, Iran
- Department of Molecular Medicine, Faculty of Advanced Technologies in Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Hamid Noori
- Cellular and Molecular Research Center, Iran University of Medical Sciences, Tehran 1449614535, Iran
- Department of Medical Nanotechnology, Faculty of Advanced Technologies in Medicine, Iran University of Medical Sciences, Tehran 1449614535, Iran
| | - Joseph M. Hardie
- Division of Engineering in Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, 02139 USA
| | - Mahdi Karimi
- Cellular and Molecular Research Center, Iran University of Medical Sciences, Tehran 1449614535, Iran
- Department of Medical Nanotechnology, Faculty of Advanced Technologies in Medicine, Iran University of Medical Sciences, Tehran 1449614535, Iran
- Oncopathology Research Center, Iran University of Medical Sciences, Tehran 1449614535, Iran
- Research Center for Science and Technology in Medicine, Tehran University of Medical Sciences, Tehran 141556559, Iran
- Applied Biotechnology Research Centre, Tehran Medical Science, Islamic Azad University, Tehran 1584743311, Iran
| | - Hadi Shafiee
- Division of Engineering in Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, 02139 USA
| |
Collapse
|
5
|
To what extent naringenin binding and membrane depolarization shape mitoBK channel gating—A machine learning approach. PLoS Comput Biol 2022; 18:e1010315. [PMID: 35857767 PMCID: PMC9342765 DOI: 10.1371/journal.pcbi.1010315] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2021] [Revised: 08/01/2022] [Accepted: 06/16/2022] [Indexed: 11/19/2022] Open
Abstract
The large conductance voltage- and Ca2+-activated K+ channels from the inner mitochondrial membrane (mitoBK) are modulated by a number of factors. Among them flavanones, including naringenin (Nar), arise as a promising group of mitoBK channel regulators from a pharmacological point of view. It is well known that in the presence of Nar the open state probability (pop) of mitoBK channels significantly increases. Nevertheless, the molecular mechanism of the mitoBK-Nar interactions remains still unrevealed. It is also not known whether the effects of naringenin administration on conformational dynamics can resemble those which are exerted by the other channel-activating stimuli. In aim to answer this question, we examine whether the dwell-time series of mitoBK channels which were obtained at different voltages and Nar concentrations (yet allowing to reach comparable pops) are discernible by means of artificial intelligence methods, including k-NN and shapelet learning. The obtained results suggest that the structural complexity of the gating dynamics is shaped both by the interaction of channel gate with the voltage sensor (VSD) and the Nar-binding site. For a majority of data one can observe stimulus-specific patterns of channel gating. Shapelet algorithm allows to obtain better prediction accuracy in most cases. Probably, because it takes into account the complexity of local features of a given signal. About 30% of the analyzed time series do not sufficiently differ to unambiguously distinguish them from each other, which can be interpreted in terms of the existence of the common features of mitoBK channel gating regardless of the type of activating stimulus. There exist long-range mutual interactions between VSD and the Nar-coordination site that are responsible for higher levels of Nar-activation (Δpop) at deeply depolarized membranes. These intra-sensor interactions are anticipated to have an allosteric nature.
Collapse
|
6
|
Guardiani C, Cecconi F, Chiodo L, Cottone G, Malgaretti P, Maragliano L, Barabash ML, Camisasca G, Ceccarelli M, Corry B, Roth R, Giacomello A, Roux B. Computational methods and theory for ion channel research. ADVANCES IN PHYSICS: X 2022; 7:2080587. [PMID: 35874965 PMCID: PMC9302924 DOI: 10.1080/23746149.2022.2080587] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Accepted: 05/15/2022] [Indexed: 06/15/2023] Open
Abstract
Ion channels are fundamental biological devices that act as gates in order to ensure selective ion transport across cellular membranes; their operation constitutes the molecular mechanism through which basic biological functions, such as nerve signal transmission and muscle contraction, are carried out. Here, we review recent results in the field of computational research on ion channels, covering theoretical advances, state-of-the-art simulation approaches, and frontline modeling techniques. We also report on few selected applications of continuum and atomistic methods to characterize the mechanisms of permeation, selectivity, and gating in biological and model channels.
Collapse
Affiliation(s)
- C. Guardiani
- Dipartimento di Ingegneria Meccanica e Aerospaziale, Sapienza Università di Roma, Rome, Italy
| | - F. Cecconi
- CNR - Istituto dei Sistemi Complessi, Rome, Italy and Istituto Nazionale di Fisica Nucleare, INFN, Roma1 section. 00185, Roma, Italy
| | - L. Chiodo
- Department of Engineering, Campus Bio-Medico University, Rome, Italy
| | - G. Cottone
- Department of Physics and Chemistry-Emilio Segrè, University of Palermo, Palermo, Italy
| | - P. Malgaretti
- Helmholtz Institute Erlangen-Nürnberg for Renewable Energy (IEK-11), Forschungszentrum Jülich, Erlangen, Germany
| | - L. Maragliano
- Department of Life and Environmental Sciences, Polytechnic University of Marche, Ancona, Italy, and Center for Synaptic Neuroscience and Technology, Istituto Italiano di Tecnologia, Genova, Italy
| | - M. L. Barabash
- Department of Materials Science and Nanoengineering, Rice University, Houston, TX 77005, USA
| | - G. Camisasca
- Dipartimento di Ingegneria Meccanica e Aerospaziale, Sapienza Università di Roma, Rome, Italy
- Dipartimento di Fisica, Università Roma Tre, Rome, Italy
| | - M. Ceccarelli
- Department of Physics and CNR-IOM, University of Cagliari, Monserrato 09042-IT, Italy
| | - B. Corry
- Research School of Biology, The Australian National University, Canberra, ACT 2600, Australia
| | - R. Roth
- Institut Für Theoretische Physik, Eberhard Karls Universität Tübingen, Tübingen, Germany
| | - A. Giacomello
- Dipartimento di Ingegneria Meccanica e Aerospaziale, Sapienza Università di Roma, Rome, Italy
| | - B. Roux
- Department of Biochemistry & Molecular Biology, University of Chicago, Chicago IL, USA
| |
Collapse
|