Loading [MathJax]/jax/element/mml/optable/GreekAndCoptic.js
Review Special Issues

The ubiquitous role of mitochondria in Parkinson and other neurodegenerative diseases

  • Orderly mitochondrial life cycle, plays a key role in the pathology of neurodegenerative diseases. Mitochondria are ubiquitous in neurons as they respond to an ever-changing demand for energy supply. Mitochondria constantly change in shape and location, feature of their dynamic nature, which facilitates a quality control mechanism. Biological studies in mitochondria dynamics are unveiling the mechanisms of fission and fusion, which essentially arrange morphology and motility of these organelles. Control of mitochondrial network homeostasis is a critical factor for the proper function of neurons. Disease-related genes have been reported to be implicated in mitochondrial dysfunction. Increasing evidence implicate mitochondrial perturbation in neuronal diseases, such as AD, PD, HD, and ALS. The intricacy involved in neurodegenerative diseases and the dynamic nature of mitochondria point to the idea that, despite progress toward detecting the biology underlying mitochondrial disorders, its link to these diseases is difficult to be identified in the laboratory. Considering the need to model signaling pathways, both in spatial and temporal level, there is a challenge to use a multiscale modeling framework, which is essential for understanding the dynamics of a complex biological system. The use of computational models in order to represent both a qualitative and a quantitative structure of mitochondrial homeostasis, allows to perform simulation experiments so as to monitor the conformational changes, as well as the intersection of form and function.

    Citation: Georgia Theocharopoulou. The ubiquitous role of mitochondria in Parkinson and other neurodegenerative diseases[J]. AIMS Neuroscience, 2020, 7(1): 43-65. doi: 10.3934/Neuroscience.2020004

    Related Papers:

    [1] Chaofan Li, Qiong Liu, Kai Ma . DCCL: Dual-channel hybrid neural network combined with self-attention for text classification. Mathematical Biosciences and Engineering, 2023, 20(2): 1981-1992. doi: 10.3934/mbe.2023091
    [2] Peng An, Xiumei Li, Ping Qin, YingJian Ye, Junyan Zhang, Hongyan Guo, Peng Duan, Zhibing He, Ping Song, Mingqun Li, Jinsong Wang, Yan Hu, Guoyan Feng, Yong Lin . Predicting model of mild and severe types of COVID-19 patients using Thymus CT radiomics model: A preliminary study. Mathematical Biosciences and Engineering, 2023, 20(4): 6612-6629. doi: 10.3934/mbe.2023284
    [3] Jingyao Liu, Qinghe Feng, Yu Miao, Wei He, Weili Shi, Zhengang Jiang . COVID-19 disease identification network based on weakly supervised feature selection. Mathematical Biosciences and Engineering, 2023, 20(5): 9327-9348. doi: 10.3934/mbe.2023409
    [4] Natalya Shakhovska, Vitaliy Yakovyna, Valentyna Chopyak . A new hybrid ensemble machine-learning model for severity risk assessment and post-COVID prediction system. Mathematical Biosciences and Engineering, 2022, 19(6): 6102-6123. doi: 10.3934/mbe.2022285
    [5] Feng Li, Mingfeng Jiang, Hongzeng Xu, Yi Chen, Feng Chen, Wei Nie, Li Wang . Data governance and Gensini score automatic calculation for coronary angiography with deep-learning-based natural language extraction. Mathematical Biosciences and Engineering, 2024, 21(3): 4085-4103. doi: 10.3934/mbe.2024180
    [6] Akansha Singh, Krishna Kant Singh, Michal Greguš, Ivan Izonin . CNGOD-An improved convolution neural network with grasshopper optimization for detection of COVID-19. Mathematical Biosciences and Engineering, 2022, 19(12): 12518-12531. doi: 10.3934/mbe.2022584
    [7] Yugui Jiang, Qifang Luo, Yuanfei Wei, Laith Abualigah, Yongquan Zhou . An efficient binary Gradient-based optimizer for feature selection. Mathematical Biosciences and Engineering, 2021, 18(4): 3813-3854. doi: 10.3934/mbe.2021192
    [8] Xiaodan Zhang, Shuyi Wang, Kemeng Xu, Rui Zhao, Yichong She . Cross-subject EEG-based emotion recognition through dynamic optimization of random forest with sparrow search algorithm. Mathematical Biosciences and Engineering, 2024, 21(3): 4779-4800. doi: 10.3934/mbe.2024210
    [9] Ziyu Jin, Ning Li . Diagnosis of each main coronary artery stenosis based on whale optimization algorithm and stacking model. Mathematical Biosciences and Engineering, 2022, 19(5): 4568-4591. doi: 10.3934/mbe.2022211
    [10] Pavithra Latha Kumaresan, Subbulakshmi Pasupathi, Sindhia Lingaswamy, Sreesharmila Thangaswamy, Vimal Shunmuganathan, Danilo Pelusi . Fruit-Fly optimization based feature integration in image retrieval. Mathematical Biosciences and Engineering, 2021, 18(5): 6178-6197. doi: 10.3934/mbe.2021309
  • Orderly mitochondrial life cycle, plays a key role in the pathology of neurodegenerative diseases. Mitochondria are ubiquitous in neurons as they respond to an ever-changing demand for energy supply. Mitochondria constantly change in shape and location, feature of their dynamic nature, which facilitates a quality control mechanism. Biological studies in mitochondria dynamics are unveiling the mechanisms of fission and fusion, which essentially arrange morphology and motility of these organelles. Control of mitochondrial network homeostasis is a critical factor for the proper function of neurons. Disease-related genes have been reported to be implicated in mitochondrial dysfunction. Increasing evidence implicate mitochondrial perturbation in neuronal diseases, such as AD, PD, HD, and ALS. The intricacy involved in neurodegenerative diseases and the dynamic nature of mitochondria point to the idea that, despite progress toward detecting the biology underlying mitochondrial disorders, its link to these diseases is difficult to be identified in the laboratory. Considering the need to model signaling pathways, both in spatial and temporal level, there is a challenge to use a multiscale modeling framework, which is essential for understanding the dynamics of a complex biological system. The use of computational models in order to represent both a qualitative and a quantitative structure of mitochondrial homeostasis, allows to perform simulation experiments so as to monitor the conformational changes, as well as the intersection of form and function.


    A new coronavirus (COVID-19) emerged in Wuhan in December 2019 and quickly swept worldwide [1]. The COVID-19 epidemic was declared a Public Health Emergency of International Concern by the World Health Organization in January 2020 [2]. To counteract, control, lessen, and confine the COVID-19 virus's effects and consequences, several studies are still being done in a variety of fields. A number of models based on artificial intelligence have been developed to diagnose COVID-19 disease [3]. However, there are still a few models based on the machine to diagnosis of infectious epidemics.

    This study is focused on clinical text mining related to COVID-19 and applying machine learning algorithms to categorize COVID-19 patients. Individual symptoms, demographic information, diagnosis, laboratory test results, chest x-ray reports, treatments, etc., can all be found in clinical texts, which are narrative texts providing a great deal of information regarding afflicted patients. However, the data in clinical texts are often high dimensional and include uninformative features, that significantly affect the accuracy of the classifier. As a result, the dimensionality of the data must be decreased [4]. Due to the vast amount of the clinical documents size, Feature Selection (FS) is an essential step before the classification process [5]. Their main advantages involve finding a subset of relevant features that will be useful in categorization. In addition to delivering high recognition, easing data comprehension, shortening training time, and resolving the curse of dimensionality problem [6,7]. FS is a challenging and complex problem because it necessitates striking a balance between lowering features and maintaining high classifier accuracy, so it requires an effective search strategy, especially when dealing with clinical text. Complicated issues, such as those involving feature selection, are often tackled with the help of algorithms that take inspiration from nature. In recent years, numerous novel swarm intelligence optimization algorithms have been proposed, such as the binary horse herd optimization algorithm [8], moth flame optimization [9], Binary Particle Swarm Optimization [10,11], binary grey wolf optimizer [12], binary aquila optimizer [13], artificial gorilla troop optimization [14].

    For the first time, the flamingo search algorithm (FSA), for handling FS tasks in the healthcare sector, is presented in this work. FSA is an efficient new method for a novel swarm intelligence optimization inspired by the flamingo's lifestyle in the migratory and foraging behavior. Figure 1 depicts flamingo communities and individuals in their natural habitat. Flamingos are known for their foraging and migratory behaviors. To the best of our knowledge, it has not been used in feature selection issues; consequently, in this research, the proposed IBFSA has been developed to minimize the number of features chosen from the clinical text related to COVID-19 while maximizing classification accuracy. The proposed method is a wrapper-based approach. Hence a learning algorithm should be part of the evaluation process. In this investigation, SVMs are used [15,16]. The most important contributions of this study are:

    Figure 1.  Flamingo population (a) flamingo group; (b) flamingo individuals.

    ● Development of a swarm algorithm called IBFSA to deal with feature selection process by an improved binary version of FSA is introduced.

    ● A novel modified Initialization approach has been proposed to enhance diversity and convergence during the research process.

    ● Levy flight has been incorporated into FSA to increase the diversity of solutions and offer a high level of randomization.

    ● The local search algorithm is incorporated before and after each iteration of FSA to prevent becoming stuck in local optima.

    ● Combining term weighting schema (RTF-C-IEF) with IBFSA.

    ● Propose a new clinical text categorizer by combining IBFSA and SVM.

    ● Use Two datasets to compare the state-of-the-art techniques with our proposed method.

    The remaining parts of the paper are structured as follows. Section 2 the related works of clinical of COVID-19 and the FS procedure. Section 3: An overview about the FSA. The proposed methodology is outlined in Section 4. The experimental and findings are presented and discussed in Section 5. Finally, Section 6, concludes the paper.

    Comparatively few attempts have been made to create intelligent classifiers, including feature selection, for the clinical text categorization of COVID-19 patients than for other topics. To correctly identify COVID-19 patients, the authors of this paper [17] employed Binary Particle Swarm Optimization (BPSO) as a wrapper approach for critical feature selection. According to experiments, it not only beats other methods but also introduces the highest possible degree of accuracy with the lowest possible time overhead. The COVID-19 dataset in [18] to disease diagnosis based on Grasshopper Optimization Algorithm (GOA), was used. The experimental findings demonstrate that the suggested method provides high classification accuracy. In this paper [19], presents an intelligent strategy for predicting SARS-CoV2 (COVID-19) using genetic feature selection techniques. The proposed model appears to have substantially lower prediction errors than conventional techniques. In this paper [20], the authors propose using a hybrid strategy based on the BOA algorithm and particle swarm optimization (PSO). The suggested methodology has been tested using the COVID-19 dataset. The experimental results show that the proposed model BOAPSO outperforms the PSO, BOA and GWO in terms of improving performance precision and reducing the number of chosen features by 91.07, 87.2, 87.8 and 87.3%, respectively. This paper [14] aims to introduce a unique discrete artificial gorilla troop optimization (DAGTO) approach for dealing with FS challenges in the healthcare sector. After completing a case study on COVID-19 samples and ten medical data sets were using to demonstrate the method's influence in practice. Evidence from statistically shows that it performs the best. In this study [13], the single Aquila optimizer (AO) is suggested as a search technique to find the optimal feature subset. The COVID-19 real-world dataset is used to evaluate the proposed method. Results showed that AO is superior to competing algorithms in terms of accuracy attained with the fewest features. The novel Caledonian crow learning algorithm is used in this study [21] to propose a strategy for selecting features relevant to the COVID-19 illness. The suggested approach for detecting COVID-19 patients is more accurate than a competing method, as demonstrated by experimental findings on the COVID-19 disease dataset at a Brazilian hospital. The best feature subset may be chosen with the help of a mix of the brainstorm optimization algorithm and the firefly algorithm, as described in this article [22]. For the dataset of coronavirus-related diseases, the proposed technique was used. The experimental findings produced demonstrated superior classification accuracy compared to previous approaches. Table 1 provides a brief comparison of earlier works on the COVID-19 detection method.

    Table 1.  A summary comparison of earlier works on the COVID-19 detection method.
    Method Advantages Disadvantages
    Aquila Optimizer (AO) and ML [13] AO significantly outperforms other comparison algorithms and has been shown to be more effective in terms of predictive accuracy and reducing the number of features selected. The COVID-19 patient data set used is small, and was not of very high dimensionality for the method to be explored effectively
    AGTO and ML [14] Efficient in reducing the number of features used with better accuracy, also this approach has been demonstrated to be successful in real-world practical applications using real-world COVID-19 datasets. The majority of the time, AGTO takes longer to implement. In addition, the database is not very highly dimensional. However, different approaches can be used to enhance the efficiency of the algorithm by applying advanced initialization procedures.
    PSO and DBNB classification [17] The suggested method attempts to accurately identify infected patients with the least time penalty based on the more effective features elected by APSO. Even though it is effective at diagnosing COVID-19 patients, the suggested method is only based on numerical data. Additionally, the dataset used is not insufficient to diagnose COVID-19 and is limited just to clinical laboratory data. However, analyzing CT scan reports may be helpful to confirm infection.
    GOA and CNN [18] Easy to implement and takes little time by optimizing CNN by GOA. By utilizing a more detailed dataset with more images from all three classes, the proposed method can be further enhanced.
    BOA, PSO and ML [20] Compared to conventional classification methods, the proposed hybrid model is more effective at classifying COVID-19 patients. The COVID-19 patient data set used is small, and was not of very high dimensionality.
    CA and ANN [21]
    ANN is a powerful classification technique. The patient election has potential bias because the database is so unbalanced that only the number of infected people in it is 10% of the total number.
    BSO, FA and ML [22] Compared to conventional classification methods, the proposed hybrid model is more effective at classifying COVID-19 patients. The COVID-19 dataset contains limited data limited only to symptoms and its small size, plus a lot of missing data. So, it needs other methods of pre-processing.

     | Show Table
    DownLoad: CSV

    In conclusion, when comparing machine learning and globally intelligent algorithms to conventional methodologies, most of the experiments on COVID-19 Classification showed good classification results. In addition, swarm intelligence algorithms have been effectively used in the feature selection problem to manage various domains, but they are not extremely applied in clinical text related to COVID-19 categorization. As a result, there is a need and substantial motivation to present a new approach, which includes a weighting scheme, an intelligent feature selection method based on IBFSA, and SVM classifier for classification of the COVID-19 patients from clinical texts.

    The FSA is an evolutionary algorithm with biological inspiration that is modeled after how flamingos in nature find food. Each candidate solution to the optimization issue in this algorithm is represented by a flamingo, and each flamingo has two primary characteristics, namely, its foraging and migrating patterns. Flamingos have no idea where most of the food is in the present (the globally ideal) search region. Therefore, flamingos look for a food site with more plentiful food than the known food in the search region by sharing information with each other, updating the location of each flamingo, and affecting changes in the locations of other flamingos in the group (the optimal solution Global). Identifying the globally best solution inside a specified search area is a significant aim of the swarm intelligence algorithm, and the flamingos' behavior is a fitting metaphor for this purpose [23].

    The fundamental steps of this algorithm are described below:

    Step 1. The population is initialized, set as P, the maximum number of iterations is IterMax, and the proportion of migrating flamingos in the first part is MPb.

    Step 2. The number of foraging flamingos in the ith iteration of flamingo population renewal is MPr=rand[0,1]×P×(1MPb). The number of migrating flamingos in the first part of this iteration is MPo=MPb×P. The number of migratory flamingos in the second part of this iteration is MPt=PMPoMPr. Individual flamingo fitness levels are calculated, and the entire flamingo population is then ranked by fitness. The flamingos with low fitness MPb and high fitness MPt are classified as migrants, while the others are classified as foraging flamingos.

    Step 3. Migrating flamingos are modified based on Eq (2), and foraging flamingos are modified based on Eq (1).

    xt+1ij=(xtij+ε1×xbtj+G2×|G1×xbtj+ε2×xtij|)/K (1)

    In Eq (2), xt+1ij presents the location of the ith flamingo in the ith dimension of the population in the (t+1)th iteration, xtij represents the location of the ith flamingo in the jth dimension in the t iteration of the flamingo population, namely, the location of the flamingo's feet. xbtj represents the jth dimension location of the flamingo with the best fitness in the population in the t iteration. K=K(n) is a diffusion factor, which is a random number that follows the chi-square distribution of n degrees of freedom. It is utilized to increase the size of the foraging-group for flamingos and simulate the possibility of individual selection in nature, enhancing its the global ability to search for the best opportunity. The random numbers G1=N(0,1) and G1=N(0,1) have a conventional normal distribution, ε1 and ε2 are determined by −1 or 1 at random.

    xt+1ij=xtij+β×(xbtjxtij) (2)

    In Eq (2), xt+1ij and xbtj represents same meaning as the previous Eq (1). β=N(0,1) is a set of random integers with the same distribution across all trials; it is employed to broaden the search area during flamingo migration and simulate the randomness of individual flamingo behaviors during the particular migration process.

    Step 4. Make sure there are no flamingos that are off-bounds.

    Step 5. Move to Step 6 if the allotted number of iterations has been used; otherwise, go to Step 2.

    Step 6. Result in the ideal solution and optimal value.

    The FSA pseudo code is displayed in Algorithm 1.

    Algorithm 1: Standard Flamingo Search Algorithm
    Input:
    Mmaximumnumberofiterations
    Ntotalnumberofflamingo
    MPbnumberofmigratingflamingo
    Output:
    XbestGlobaloptimalposition
    fbestFitnessofglobaloptimalposition
    1 Start
    2 Initialize a swarm of N flamingo s and its relevant parameters;
    3 t1;
    4 While t<M do
    30 end while
    31   Return Xbest, fg /*Xbest is top optimal of a solution got by the algorithm */

     | Show Table
    DownLoad: CSV

    In order to predict a COVID-19 diagnosis from clinical texts, our strategy described in this work includes six processing stages, namely collection and describe the dataset, text pre-processing, extract features, features selection, use of machine learning methods, and performance evaluation. The suggested model's block diagram is shown in Figure 2.

    Figure 2.  Diagram of the workflow of the study.

    Two sets of clinical data related to Coronavirus (COVID-19) were collected to validate the effectiveness of the suggested method. First Dataset (DS1) was collected from several hospitals in Iraq of patients with SARS-CoV2. In contrast, other clinical text reports were collected to form the second data set (DS2) from various sources, including includes GitHub (https://github.com/Akibkhanday/Meta-data-of-Coronavirus.), the Italian Society of Medical and Interventional Radiology (SIRM) (https://www.sirm.org/category/senza-categoria/covid-19/), in addition to other cases reports, that were collected from medical publications related to COVID-19 on some websites such as Hindawi (https://www.hindawi.com/), Infection and Chemotherapy (https://www.jiac-j.com/), NIH (https://www.ncbi.nlm.nih.gov/pmc/), and ScienceDirect (https://www.sciencedirect.com/science/article/pii/S1477893921002106).

    Both datasets contain "demographic" information, such as age, sex, and comorbidities, in addition to other needed diagnostics information and related tests, including symptoms, vital signs, lab results, values from routine blood tests, and chest CT imaging results, disposition, admission to an ICU, and survival to hospital discharge. The two datasets consist of 3053 and 1446 patients, respectively. Table 2 summarizes the used datasets comprising varying samples and attributes.

    Table 2.  Details of datasets.
    No Type No. of records Label Rate of Occurrences
    DS1 Clinical Text 3053 Severe
    Non-Severe
    55%
    45%
    DS2 Clinical Text 1446 COVID-19 Positive
    COVID-19 Negative
    62%
    38%

     | Show Table
    DownLoad: CSV

    Clinical texts present a difficult challenge to extract the hidden features from, since they are always presented in an unstructured format. Thus, to train a classifier, data must be presented in a readable manner and undergo pre-processing. Since some symbols and words may not be beneficial for categorization, the pre-processing method aims to improve the data's quality and clean it up. Several pre-processing steps were used to convert unstructured clinical texts into a word vector. It includes removing punctuation, and numbers, stopping words and other characters, converting letters, short-word removal, tokenization, parts-of-speech tagging, stemming, and lemmatization.

    In order to complete NLP tasks, it is crucial to identify an effective text representation system [24]. From the pre-processed clinical texts, different features are extracted. The feature engineering described here relies on the use of two steps. SpaCy and ScispaCy were employed in the first step to extract medical entities from clinical text. Symptoms with more than one word were then converted into a single expression (e.g., "shortness of breath") in some reports. ScispaCy provides a robust rule-matching engine and Fast Models for Biomedical Natural Language Processing [25].

    In the second stage, the RTF-C-IEF weighting method [26] is used to transform the extracted concepts, which are features, into probability values to be ready for the feature selection model. This procedure drastically decreases the number of features while preserving the informative features. RTF-C-IEF is a statistical weighting method to retrieve a term's significance within a document as the first stage of feature selection strategy for text mining. It was used for feature extraction instead of Bag of Word (BoW) and TF-IDF classical since RTF-C-IEF provides more accurate results [26].

    A higher RTF-C-IEF feature score indicates more significance for that feature within the text's clinical context. The RTF-C-IEF formula is written as follows:

    RTFCIEF=(tfij)rtf×(1+txN)×edt(tj)N (3)

    Where tfij is the term frequency, tx represents the frequency count of the word x in the core corpus, N is the total of dataset, and dt(tj) corresponds to the frequency of documents that term tj appears in the collection.

    Prior to performing the classification, feature selection is a crucial step to choosing the important features, eliminating the irrelevant ones, minimizing the feature dimensions, and shortening the computing time required to complete the classification [10,27,28]. To realize that, FSA [29] is implemented. FSA is a new algorithm that simulates the behavior of flamingos searching for the best possible solution within a given search region (where food is most plentiful). Since FS is a binary issue, the native optimizer needs to be tweaked so that FSA may optimize in a high-dimensional binary search space, thereby improving the algorithm's efficiency. Many significant steps in updating the FSA algorithm are detailed in this study. Introducing a new operator into the algorithm's structure is the most common method for enhancing FSA exploration as well as correcting the typical roaming behavior of swarm members. In the first step, transfer functions from S-shaped families are used to convert the FSA to binary. Secondly, A novel initialization modification (MIA) approach was incorporated into the standard FSA algorithm to obtain high-quality individuals in beginning and thus increase the likelihood of discovering the best solution, which may increase the optimization's performance. In the third stage, the Levy flight operator is added to each flamingo to boost its variability and the optimizer's capacity to probe further into underexplored portions of the search space. Finally, enhancing the exploitation by Local Search Algorithm (LSA). These promising improvements are discussed in this sub-section. The architecture of the suggested feature selection approach is depicted in Figure 4, and the pseudocode of IBFSA is presented in Algorithm 4.

    Figure 3.  S-shaped function used in FSA algorithm.
    Figure 4.  Simulated Levy flight.
    Figure 5.  The sequential steps of IBFSA-FS method.

    Modeling the FS problem as a binary one, which can only take values 0 or 1 in the feature-subset selection issue. Thereby, FSA cannot be utilized to directly resolve a feature selection problem because the final solution it produces using Eqs (1) and (2) is made up of continuous values (real number domain). As a result, a transfer function (TF) must be used to convert the values from continuous to binary (0 or 1). TF specifies the rate at which the values of the decision variables change from 1 to 0 and back. That is, when choosing a TF to convert the continuous values into binary (0, 1), the range of values the TF produces should fall within the range [0, 1]. The S-shaped family of logistic transformation functions is perfect for mapping processes since it produces output in the [0, 1] range. The purpose of this discovery is to identify features that have been omitted or elected. In this case, the flamingo stands for features set, and its binary values indicate whether or not that feature was chosen for inclusion in the final model, where 1 represents a selected feature and 0 means discard. An individual's value range is now mapped to [0, 1] by the following function [10]:

    TF(xdi(t))=11+e2xdi(t) (4)

    Where xdi denotes the ith flamingo location in the dth dimension at the tth iteration, xi is computed by Eqs (1) and (2). In Eq (4), the output of the S-shaped function is still displayed continuously as illustrated in Figure 3. Thus, to obtain the binary value the ith position is modified as follows:

    xdi(t+1)={0rand<TF(xdi(t))1randTF(xdi(t)) (5)

    Where xdi(t+1) represents the ith element in the X solution at dimension d in iteration t+1, and rand[0,1].

    Figure 4 depicts Levy flight, a mathematical representation of a random motion that follows a heavy-tailed probability distribution [30]. Levy flight was recently introduced as a solution to optimization problems. It has since been incorporated into the design of many optimization algorithms to improve their performance in areas including speed of convergence, preventing premature convergence, leaping from local minima, and striking a balance between exploration and exploitation [8,9,30]. This research aims to improve the FS process used in the COVID-19 diagnosis from clinical texts by proposing for the first time that Levy flight be included in the FSA structure to enhance the performance of the FSA optimizer. An equation that represents the flamingo location update based on Levy's flying improvement is Eq (6). So, in order to increase the variety of search spaces, it has been planned that each upgraded flamingo would employ Levy flight once, resulting in a higher level of exploration.

    xt+1ij=(xtij+ε1×xbtj+levy(β)|G1×xbtj+ε2×xtij|)/K (6)
    Levy(β) μ=t1β0β2 (7)
    levy(β)ϕ×μ|V1/β| (8)
    ϕ=[Γ(1+β)×sin(π×β/2)Γ((1+β2)×β×2β12)]1β (9)

    Where Xti indicates the ith flamingo at iteration t, rand indicates a random number in the range [0, 1], represents the dot product, and α represents the step control parameter. Levy flight, as previously mentioned, is a random walk where the leap size supports a Levy distribution as given in Eq (7). Using Eq (8), Levy is computed as random numbers; µ and ν are common random distributions. Eq (9) shows how to calculate φ, where Γ represents a typical Gamma function, and β = 1.5, mentioned in [31].

    Evolutionary algorithms rely heavily on the variety and convergence of their populations, and population initialization is a crucial aspect of this. This step's purpose is to offer an initial guess at potential solutions. These initially hypothesized solutions will then be iteratively enhanced throughout the optimization process until a stopping requirement is fulfilled. In most cases, having a high-quality initial population can help an algorithm converge more quickly and find the optimal solution. On the other hand, it is possible that an algorithm will not be able to locate the optimal solution if it has based on poor guesses [32,33]. In recent years, researches has shown that proper initialization approaches can improve the likelihood of locating global optimum solutions and decrease the variance of the final search outcomes [34]. In this paper, the performance of FSA is expanded to make it appropriate for the optimization problem by introducing a new initialization algorithm named MIA. Its basic idea is to create a population based on the initial population in a sporting way without any complex equation or making much change in the original FSA algorithm and its structure. Next, the better individuals will be selected out of the initial population, resulting in the creation of a new initial population made up of outstanding individuals. Thus, the MIA managed to manage part of this algorithm and correctly cover the possible space. Additionally, the suggested initialization technique significantly impacts solution quality, finds the optimal solution with high precision, and has helped boost the likelihood of starting with a global optimum. The whole pseudo code of MIA is displayed as Algorithm2.

    Algorithm 2: The proposed MIA algorithm
    Xij = position of flamingos; /* Randomly generate the positions of N flamingo;
    Xbin= After Convert to binary_map (Xij);
    Fitold= Find all Fitness to Population size(flamingos);
    Dmax= maximum of number of local iterations;
    Mmax= maximum of number of local iterations;
    N (Population size).
    1 for d=1To Dmax do
    21 end for
    22 Return Xbin, Xij, Fitold

     | Show Table
    DownLoad: CSV

    The LSA algorithm was created and presented in Algorithm3 by [35]. In the original FSA, in each iteration of the migratory flamingo MPb, LSA is called to enhance the local location obtained by the Eq (3). After the migratory flamingos have moved to their best position, LSA is again called to improve finding the best solution Xt+1ij currently obtained by still removing any more potentially pointless features. At first, LSA stores, in a variable Temp, the value of Xt+1best produced at the end of each IBFSA iteration. To improve Temp, LSA runs iteratively LT times. At each iteration Lt of LSA, four features' randfeat are randomly selected from Temp. Every variable in the randfeat is reversed by LSA. Then, the value of fitness f(Temp) of the new solution (the new Temp) is evaluated; if it is best than (Xt+1best), then Xt+1best is set to Temp; otherwise, Xt+1best and fg are kept unaltered.

    Algorithm 3: The proposed LSA algorithm
    LT maximum of number of local iterations;
    Xt+1best /* the best position so far at the end of IBFSA current iteration t+1;
    TempXt+1best
    Lt0;
    1 While Lt<LT do
    13 end while
    14 Return Xbest, fg

     | Show Table
    DownLoad: CSV

    In addition, in order not to lose the distinctive sites that the flamingo passes through in its journey during the search for the optimal global solution, we added a parameter to help it maintain its sites that have the best fitness value appropriate that it has currently reached, and this prevents the flamingo from moving away from the optimal position and moving to a worse position.

    After the flamingo is converted into a binary vector with the same number of rows and columns of the dataset in TF. The fitness function of the IBFSA is used to quantify each flamingo's level of fitness by combining two seemingly opposing goals. These goals are the number of chosen features and the accuracy. The FS problem seeks to maximize classification accuracy (minimize error rate) with a minimum of specified features. Then, the model performance was optimized with the SVM technique, and the optimal set of features for detecting COVID-19 was determined by identifying the best flamingo. IBFSA uses the following fitness function to evaluate the solutions and achieve an equilibrium between the two main goals:

    FitFS=α×E+β×dD (10)

    Where E is the classifier's error rate, d is the number of features used to make a decision, and D is the total number of features. In addition, the values of α and β are the weights employed to strike a balance between these two goals.

    Algorithm 4: The proposed IBFSA based on MIA, TF, Levy flight and RSA
    Input:
    Mmaximumnumberofiterations
    Ntotalnumberofflamingo
    MPbnumberofmigratingflamingo
    Output:
    XbestGlobaloptimalposition
    fbestFitnessofglobaloptimalposition
    1 Start
    2 Initialize a swarm of N flamingo s and its relevant parameters;
    3 Apply MIA to Xij using Algorithm (2);
    4 t1;
    5 While t<M do
    48 end while
    49 end
    50 Return Xbest, fg /*Xbest is the best solution obtained by the algorithm*/

     | Show Table
    DownLoad: CSV

    The proposed method is a wrapper-based approach. Hence a learning algorithm should be part of the assessment process. In this research, SVMs are used as classifiers in the fitness evaluation process [36,37,38] because they are so efficient, mainly when dealing with data sets that only have two classes. In addition, the other classifiers are utilized in all other cases. Each dataset was divided at random into 20% for testing and 80% for training. Multiple metrics, including precision, sensitivity, F-measure, Macro-F1, and Macro-Recall, are used to assess the results of our tests and verify the efficacy of the suggested method. Are defined as follows:

    Precision=TPTP+FP,Recall=TPTP+FN (11)
    F1_score=2×Precision×RecallPrecision+Recall (12)
    MacroF=1TTj=1Fj (13)
    MacroR=1TTj=1Rj (14)

    Where T denotes the total number of categorized classes and, Fj, Rj are F, R values in the jth category of class. In order to increase the statistically significant of the empirical results, we independently test each optimization technique 20 times across all datasets. For each assessment, the following metrics are calculated and used: average classification accuracy, features election ratio, average fitness, and standard deviation (STD) and adopted as follows:

    μμfeat=12020k=1dkD (15)
    μμfit=12020k=1fk (16)
    SD=11920k=1(YkμY) (17)

    This section offers a comprehensive empirical examination of the IBFSA optimization algorithm's behavior based on several improvements. Two datasets of patient medical records from COVID-19 are utilized for experiments. Table 1 details the specifics of these data collections.

    It is well-known that it is challenging for a metaheuristics method to achieve optimal performance across all possible optimization situations, especially when employing the same parameter settings. Therefore, to obtain optimal performance, it is preferable to fine-tune the critical parameters for each optimization issue independently. Parameters must be established when the IBFSA has been defined, and its procedure explained (the number of flamingos, the number of iterations, and the number of runs). The iterations provide the flamingos the chance to achieve the best intensity during one generation. When the number of iterations is repeated multiple times, the runs get their best intensity. Although the runs take more time, they ensure that the solution produced is optimal. Keep in mind that only a subset (80%) of the COVID-19 datasets is used in the experiments for parameter setup. At the same time, the remaining data is held for assessment and validation at the end (testing data). To prevent random bias, each combination is separately run 20 times, and the average results are then shown. In addition, the state-of-the-art wrapper approaches, such as BPSO, BGWO, BWOA, BMFO and BFFA, were compared to the suggested method. All algorithms have been built with the same computer platform and settings for all algorithm parameters to ensure that comparisons are fairness. Table 3 displays how finely tuned the parameters got.

    Table 3.  Parameter settings for IBFSA.
    IBFSA Parameters Description Setting
    N Run Time 20
    Pop. Size(N) Number of flamingo search agents 50
    Itermax Maximum number of iterations 500
    Dim Dimension Number of features
    β Significance of the feature subset 0.01
    α Importance of classification accuracy 0.99
    MPb Proportion of migrating flamingo 0.1

     | Show Table
    DownLoad: CSV

    Here, we show the results we got from applying our method to test datasets associated with Covid-19, measuring how well our system did at classifying the data. In two stages, experiments are conducted. In stage one, the term weighting schema's impact is investigated on datasets to categories Covid-19 patients as we look for the best performance by including it in the suggested strategy. In the second stage, the proposed IBFSA is compared to numerous alternative wrapper FS methods to demonstrate the proposed method's efficacy. The IBFSA result, which consists of clinical texts with decreased feature sizes, is used as input for classifiers to categorize the patients into the appropriate classes. Take note, the phase of feature selection was separated from the phase of categorization. SVM with a linear kernel function as baseline classifier, Random Forest, the logistic recursion Nave Bayes classifier, and the multi-layer perceptron are all used to assess the quality of the feature subsets. These experiments are based on two key metrics: 1) The total number of features chosen; 2) Secondly, the accuracy of the classification. Measures such as best fitness value, worst fitness value, mean fitness value, STD for the average fitness values, the average number of the elected features, average accuracy score, and maximum accuracy value obtained are used to evaluate IBFSA performance on the FS issue in this section. For ease of understanding, the optimal results of a particular method are presented in bold.

    Table 4 displays the total number of features extracted during pre-processing before the feature selection procedure. Tables 7 and 8 display the total number of features chosen from the datasets generated using various techniques. The tables show that, on average, the number of features is picked by using IBFSA better than any other technique tested (for both DS1 and DS2) from 20 iterations. Keep in mind that the accuracy and the number of selected features is tradeoffs. Thus, it may be challenging to get the best results in both of these objectives for any dataset. In light of this, we can conclude that the proposed IBFSA outperforms other algorithms in terms of feature selections in the chosen datasets, as shown in Figures 6 and 7.

    Table 4.  Number of the extracted features from pre-processing.
    Dataset Number of features
    DS1 of Covid-19 377
    DS2 of Covid-19 2367

     | Show Table
    DownLoad: CSV
    Table 5.  Fitness values from various algorithms on DS1.
    Algorithm Best Worst SD Mean
    PSO 11.9508 13.3517 3.6424 12.9468
    WOA 13.1452 14.6777 3.7754 13.7407
    MFO 12.8370 13.7504 2.1992 13.2715
    GWO 15.1563 16.8318 4.8170 16.1638
    FFA 13.8441 14.8428 2.7810 14.3461
    IBFSA 13.2032 18.6477 13.1204 15.2640

     | Show Table
    DownLoad: CSV
    Table 6.  Fitness values from various algorithms on DS2.
    Algorithm Best Worst SD Mean
    PSO 4.6866 5.4455 2.067 5.0539
    WOA 4.8834 5.9688 2.5784 5.6351
    MFO 4.7724 5.5376 2.6126 5.3095
    GWO 6.8914 9.0156 5.8036 8.0924
    FFA 4.9955 6.1279 3.5989 5.7708
    IBFSA 2.3806 5.3688 8.9300 3.9802

     | Show Table
    DownLoad: CSV
    Table 7.  Number of selected features from various algorithms on DS1.
    Algorithm Best Worst SD Selection Ratio Removal Ratio
    PSO 267 302 8.5006 73.5941 26.4058
    WOA 181 324 29.0923 79.1909 20.809
    MFO 270 304 10.8204 75.557 24.4429
    GWO 175 208 8.8317 50.1326 49.8673
    FFA 197 225 8.5230 56.3129 43.6870
    IBFSA 54 86 7.6461 17.9310 82.0689

     | Show Table
    DownLoad: CSV
    Table 8.  Number of selected features from various algorithms on DS2.
    Algorithm Best Worst SD Selection Ratio Removal Ratio
    PSO 1681 1773 2.5576 72.858 27.1419
    WOA 1156 1951 28.1438 72.3595 27.6404
    MFO 1669 1830 3.8661 74.4592 25.5407
    GWO 1128 1245 2.7217 49.8183 50.1816
    FFA 1299 1377 1.9534 56.2251 43.7748
    IBFSA 225 312 2.2832 11.2568 88.7431

     | Show Table
    DownLoad: CSV
    Figure 6.  Average features removal ratio from DS1.
    Figure 7.  Average features removal ratio from DS2.

    The boxplots for both datasets are seen in Figures 8 and 9 to measure the number of features selected and algorithms performance. It should be noted that the boxplots reflect outcomes of classification and the number of FS, and are displayed after each method has been executed 20 times. These figures allow us to visually see the minimum, median, and maximum values of the data. As shown in these figures, IBFSA has higher boxplots than the other approaches in both datasets.

    Figure 8.  Boxplots of IBFSA compared with other algorithms in number of FS for both datasets.
    Figure 9.  Boxplots of IBFSA compared with other performance of algorithms by F-score of SVM classifier for both datasets.

    Tables 9 and 10 show that when comparing LR and RF performance, IBFSA performs best in terms of accuracy, precision, and F-measure index. However, there is no significant difference in average recall values between IBFSA and others. In the MLP classifier, Table 11 shows that the IBFSA has the best mean performance measured by the F-measure index. On the other hand, show Table 12 that compared to the performance of other models, the combination of Naive Bayes and IBFSA can categorize the texts with higher sensitivity. Moreover, in Table 13, we see that the SVM with IBFSA has a superior efficacy and outperforms all other algorithms regarding classifier performance, see Figure 10.

    Table 9.  Comparison results of Classification performance obtained by LR algorithm with DS1.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 79.5247 76.5082 78.9809 75.9353 85.3741 82.4489 81.5780 79.0423
    WOA 78.7934 77.0658 77.9874 76.0964 85.034 83.6054 81.0450 79.6699
    MFO 77.3309 76.4533 76.3975 75.4018 84.6939 83.4183 79.8700 79.2028
    GWO 77.6965 75.6307 77.3885 73.7182 88.7755 85.0850 80.5030 78.9576
    FFA 79.7075 76.1791 79.4212 74.6162 87.4150 84.4387 81.6520 79.2132
    IBFSA 83.6996 80.1190 87.3494 80.8904 88.9262 83.6409 85.3377 81.8920

     | Show Table
    DownLoad: CSV
    Table 10.  Comparison results of Classification performance obtained by RF algorithm with DS1.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 78.9762 77.1755 77.2871 75.3667 85.3741 83.1632 80.3226 79.0642
    WOA 79.5247 77.989 77.7429 75.7595 87.0748 83.8775 80.9135 79.6005
    MFO 79.159 77.5502 76.8519 75.0723 86.3946 84.3027 80.5825 79.4137
    GWO 77.5137 76.1152 75.3943 73.6087 89.1156 83.4524 80.4992 78.1753
    FFA 79.8903 77.0292 79.0323 74.6154 86.7347 83.7925 81.1258 78.9211
    IBFSA 80.9524 78.7912 79.6774 76.0975 94.2953 89.2953 84.2579 82.1315

     | Show Table
    DownLoad: CSV
    Table 11.  Comparison results of Classification performance obtained by MLP algorithm with DS1.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 79.8903 75.6307 80.0654 76.9761 88.7755 78.1292 81.6667 77.3871
    WOA 79.159 76.8098 79.4118 75.5138 90.1361 84.4217 81.2102 79.6115
    MFO 77.5137 76.0603 78.5156 75.1362 90.8163 83.1632 80.3709 78.8295
    GWO 77.8793 75.4936 78.5441 73.9967 89.1156 84.3367 80.4314 78.6784
    FFA 79.3419 75.5393 78.6184 74.8233 90.4762 82.6700 81.5057 78.3134
    IBFSA 79.7075 77.5686 81.2287 76.6963 92.8571 83.8946 82.0350 80.0531

     | Show Table
    DownLoad: CSV
    Table 12.  Comparison results of Classification performance obtained by NM algorithm with DS1.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 76.782 73.7842 72.8814 70.4028 90.8163 88.5204 80.7284 78.4110
    WOA 76.416 74.6618 73.5043 71.6316 89.4558 87.5680 80.0000 78.7926
    MFO 76.051 74.6343 72.5762 71.4047 89.7959 88.0952 80.0000 78.8734
    GWO 76.416 73.6380 71.6535 69.5449 93.5374 90.7993 80.8889 78.7455
    FFA 76.234 74.4698 71.5847 70.5987 92.5170 90.0000 80.7122 79.1192
    IBFSA 76.5996 74.0859 72.3118 69.6321 93.8776 92.3129 80.7808 79.3395

     | Show Table
    DownLoad: CSV
    Table 13.  Comparison results of Classification performance obtained by SVM algorithm with DS1.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 79.1590 76.5082 80.2768 75.8037 88.4354 82.9251 81.0631 79.1439
    WOA 78.2450 76.9652 77.7070 76.0817 85.7143 83.3843 80.5873 79.5568
    MFO 77.8793 76.5996 76.8750 75.2367 87.0748 84.1836 80.8847 79.4516
    GWO 77.1481 75.5210 76.0125 72.7785 89.7959 87.1088 80.6107 79.2690
    FFA 79.5247 76.0146 79.3548 73.6135 88.4354 86.4285 81.4570 79.4856
    IBFSA 84.9817 82.0330 83.1288 79.0333 96.3087 91.4933 86.8590 84.7629

     | Show Table
    DownLoad: CSV
    Figure 10.  Average classification F-measure of IBFSA on DS1 compared with other algorithms by SVM Classifier.

    Classifiers results from machine learning's second dataset are displayed in Tables 1418. As it can be seen from Tables 1416 the classifiers achieved a promising performance compared to all methods, however, comparatively there is a marginal difference in accuracy between the classifiers. It is noteworthy, Table 17 shows that a NB classifier trained with IBFSA can prove superior efficacy compared to its other peers, achieving average classification sensitivity of 98.25% and a maximum sensitivity among the 20 runs is 100%. While, Table 18 shows that the IBFSA has the best accurate performance of all of the rivals regarding the SVM classifier, see Figure 11.

    Table 14.  Comparison results of Classification performance obtained by LR algorithm with DS2.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 93.8849 91.6187 94.9721 92.7515 96.0674 94.2977 95.2646 93.5134
    WOA 93.1655 91.8345 94.3820 92.8152 96.6292 94.5786 94.7075 93.6820
    MFO 93.5252 92.3201 94.9153 93.2023 96.6292 94.9438 95.0276 94.0601
    GWO 94.2446 90.9172 96.0227 92.9304 96.0674 92.8932 95.4802 92.9027
    FFA 93.5252 91.4388 93.8889 92.7945 96.6292 93.9325 95.0276 93.3521
    IBFSA 93.1655 90.4676 95.4286 92.5492 94.9438 92.5842 94.6176 92.5574

     | Show Table
    DownLoad: CSV
    Table 15.  Comparison results of Classification performance obtained by RF algorithm with DS2.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 94.2446 92.2302 93.5484 90.621 97.7528 95.9269 95.6044 93.1861
    WOA 93.5252 92.5000 93.7500 91.1323 97.7528 96.0393 94.7368 93.5073
    MFO 93.8849 92.6978 93.4066 91.1925 97.191 96.3202 95.0549 93.6793
    GWO 93.1655 91.5287 94.7977 91.9839 97.7528 93.3988 94.7658 92.6582
    FFA 92.8058 91.7985 94.3503 91.8734 96.6292 94.3258 94.1176 93.0739
    IBFSA 92.8058 91.5468 94.8276 93.3384 93.2584 91.9663 93.7853 92.6419

     | Show Table
    DownLoad: CSV
    Table 16.  Comparison results of Classification performance obtained by MLP algorithm with DS2.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 92.8058 90.4496 94.7977 92.8646 96.0674 92.1909 94.3820 92.5100
    WOA 92.4460 90.7014 94.3503 92.4501 97.1910 93.1460 94.0845 92.7617
    MFO 92.4460 90.7554 95.8824 93.2032 95.5056 92.3595 94.1828 92.7467
    GWO 92.8058 89.4964 95.4023 92.5473 96.6292 90.9550 94.5055 91.7095
    FFA 92.8058 90.5755 94.6429 92.4290 97.1910 92.9213 94.5355 92.6571
    IBFSA 92.4460 90.1798 95.3757 92.9065 94.3820 91.7135 94.0171 92.2804

     | Show Table
    DownLoad: CSV
    Table 17.  Comparison results of Classification performance obtained by NM algorithm with DS2.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 91.3669 88.4172 88.8889 86.6196 98.8764 96.9101 93.617 91.4698
    WOA 89.5683 87.8057 88.601 85.9397 98.8764 96.882 92.2667 91.0656
    MFO 92.446 88.7589 91.9786 87.2246 98.8764 96.6572 94.2466 91.6853
    GWO 88.1295 85.1978 86.4322 82.5656 98.8764 97.528 91.2467 89.4133
    FFA 90.2878 85.9712 88.3249 83.5081 98.8764 97.4157 92.8 89.9095
    IBFSA 83.0935 77.7338 79.638 74.7827 100 98.5674 88.2206 85.0241

     | Show Table
    DownLoad: CSV
    Table 18.  Comparison results of Classification performance obtained by SVM algorithm with DS2.
    Algorithm Accuracy Precision Recall F-measure
    Best Mean Best Mean Best Mean Best Mean
    PSO 94.6043 92.7338 95.4802 93.4127 97.191 95.3932 95.8449 94.3868
    WOA 93.8849 92.7877 94.4444 93.2464 97.191 95.6741 95.2909 94.4405
    MFO 94.2446 93.0395 95 93.7031 97.191 95.5617 95.5801 94.6191
    GWO 93.5252 91.5287 95.9064 93.3714 96.6292 93.4269 94.9438 93.3876
    FFA 93.8849 91.6906 94.9721 93.0589 96.0674 94.0449 95.2646 93.5463
    IBFSA 97.1119 95.0541 97.1098 94.1285 99.4186 98.1613 97.7011 96.0932

     | Show Table
    DownLoad: CSV
    Figure 11.  Average classification F-measure of IBFSA on DS2 compared with other algorithms by SVM Classifier.

    As per results in Tables 13 and 18, it can be seen that the optimizer IBFSA with SVM classifier has demonstrated a greater classification accuracy in comparison to the other variations using LR, RF, MLP and NB classifiers in handling all selected datasets. One of the causes is that the SVM classifier uses over-fitting protection and does not depend primarily on the total number of processed features. So, it has better potential than previously studied classifiers in dealing with bigger text feature spaces. As seen in the results, when dealing with a sparsely of samples, the SVM can demonstrate a steadier efficacy compared to other models. On these particular datasets, the IBFSA algorithm achieves better results than any other competing approaches in terms of feature selection accuracy. The inclusion of new, more efficient components that improve the algorithm's balance between its exploratory and exploitative capacities is one possible explanation for the algorithm's improved performance.

    A new diagnostic model for COVID-19 has been developed that will effectively increase the final prediction accuracy. The suggested approach includes two primary stages. The first stage is utilizing RTF-C-IEF to determine the feature's importance. Next, the modified flamingo search algorithm is then used to choose a collection of pertinent and non-redundant features in the second phase. Finally, the SVM-based classifier is used to predict COVID-19 using the features elected of clinical text. Our experiments were conducted on two sets of data, the first was collected from hospitals in the south of Iraq, and the second was from several sources on websites. In IBFSA, we presented four ways to boost both the global and local search capabilities of the algorithm. In addition, the continuous approach has been adapted to the binary feature selection problem using the binary transformation method. We have compared the suggested technique to state-of-the-art feature selection swarming methods such as PSO, MFO, GWO and FFA. Experiments reveal that the suggested technique is more effective in decreasing sub-features by more than 88% and with an accuracy superior to other methods. As a result, it can be concluded that the suggested approach is a powerful feature selection for COVID-19 patients' classification. Moreover, IBFSA reports that feature selection has decreased the number of diagnostic mistakes for COVID-19 patients. In this way, feature selection helps machine learning zero in on the most relevant information, lessening the likelihood of an incorrect diagnosis while attempting to distinguish between infected and uninfected individuals. In our future work, we'll take into account expanding and diversifying the test datasets to better assess the suggested methodology.

    The original data (first dataset) used and/or processed during current study is part of the health records of a group of hospitals in southern Iraq. Therefore, data (DS1) is not available to the general public. May be made available from the corresponding author upon reasonable request.

    The authors are so pleased to introduce their deep acknowledgment and great thanks to the staff of the hospitals and healthcare providers which supported the clinical data for this study, especially hospitals in Iraq.

    The authors declare no conflict of interest.



    Conflict of interest



    The author declares no conflicts of interest.

    [1] Gonatas N, Shy G (1965) Childhood myopathies with abnormal mitochondria. Proceedings of the Vth International Congress of Neuropathology 100: 606-612.
    [2] Baron M, Kudin AP, Kunz WS (2007) Mitochondrial dysfunction in neurodegenerative disorders. Biochem Soc Trans 35: 1228-1231. doi: 10.1042/BST0351228
    [3] DiMauro S (2011) A history of mitochondrial diseases. J Inherit Metab Dis 34: 261-276. doi: 10.1007/s10545-010-9082-x
    [4] Mattson MP, Gleichmann M, Cheng A (2008) Mitochondria in neuroplasticity and neurological disorders. Neuron 60: 748-766. doi: 10.1016/j.neuron.2008.10.010
    [5] Federico A, Cardaioli E, Da Pozzo P, et al. (2012) Mitochondria, oxidative stress and neurodegeneration. J Neurol Sci 322: 254-262. doi: 10.1016/j.jns.2012.05.030
    [6] De Vos KJ, Grierson AJ, Ackerley S, et al. (2008) Role of axonal transport in neurodegenerative diseases. Annu Rev Neurosci 31: 151-173. doi: 10.1146/annurev.neuro.31.061307.090711
    [7] Chen H, Chan DC (2009) Mitochondrial dynamics–fusion, fission, movement, and mitophagy–in neurodegenerative diseases. Hum Mol Genet 18: R169-R176. doi: 10.1093/hmg/ddp326
    [8] Wang X, Su B, Zheng L, et al. (2009) The role of abnormal mitochondrial dynamics in the pathogenesis of Alzheimer's disease. J Neurochem 109: 153-159. doi: 10.1111/j.1471-4159.2009.05867.x
    [9] Büeler H (2009) Impaired mitochondrial dynamics and function in the pathogenesis of Parkinson's disease. Exp Neurol 218: 235-246. doi: 10.1016/j.expneurol.2009.03.006
    [10] Park JS, Davis RL, Sue CM (2018) Mitochondrial dysfunction in Parkinson's disease: new mechanistic insights and therapeutic perspectives. Curr Neurol Neurosci Rep 18: 21. doi: 10.1007/s11910-018-0829-3
    [11] Alexiou A, Vlamos P, Volikas K (2010) A Theoretical Artificial Approach on Reducing Mitochondrial Abnormalities in Alzheimer Disease. Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicin IEEE, 1-4.
    [12] Benard G, Karbowski M (2009) Mitochondrial fusion and division: regulation and role in cell viability. Semin Cell Dev Biol 20: 365-374. doi: 10.1016/j.semcdb.2008.12.012
    [13] Zorov DB, Vorobjev IA, Popkov VA, et al. (2019) Lessons from the Discovery of Mitochondrial Fragmentation (Fission): A Review and Update. Cells 8: 175. doi: 10.3390/cells8020175
    [14] Sheng ZH (2017) The interplay of axonal energy homeostasis and mitochondrial trafficking and anchoring. Trends Cell Biol 27: 403-416. doi: 10.1016/j.tcb.2017.01.005
    [15] Lin MY, Sheng ZH (2015) Regulation of mitochondrial transport in neurons. Expe Cell Res 334: 35-44. doi: 10.1016/j.yexcr.2015.01.004
    [16] Mishra P, Chan DC (2016) Metabolic regulation of mitochondrial dynamics. J Cell Biol 212: 379-387. doi: 10.1083/jcb.201511036
    [17] Dickey AS, Strack S (2011) PKA/AKAP1 and PP2A/Bβ2 regulate neuronal morphogenesis via Drp1 phosphorylation and mitochondrial bioenergetics. J Neurosci 31: 15716-15726. doi: 10.1523/JNEUROSCI.3159-11.2011
    [18] Kuznetsov AV, Hermann M, Saks V, et al. (2009) The cell-type specificity of mitochondrial dynamics. Int J Biochem Cell B 41: 1928-1939. doi: 10.1016/j.biocel.2009.03.007
    [19] Palmer CS, Osellame LD, Stojanovski D, et al. (2011) The regulation of mitochondrial morphology: intricate mechanisms and dynamic machinery. Cell Signal 23: 1534-1545. doi: 10.1016/j.cellsig.2011.05.021
    [20] Chen H, McCaffery JM, Chan DC (2007) Mitochondrial Fusion Protects against Neurodegeneration in the Cerebellum. Cell 130: 548-562. doi: 10.1016/j.cell.2007.06.026
    [21] Twig G, Elorza A, Molina AJ, et al. (2008) Fission and selective fusion govern mitochondrial segregation and elimination by autophagy. EMBO J 27: 433-446. doi: 10.1038/sj.emboj.7601963
    [22] Meeusen S, DeVay R, Block J, et al. (2006) Mitochondrial inner-membrane fusion and crista maintenance requires the dynamin-related GTPase Mgm1. Cell 127: 383-395. doi: 10.1016/j.cell.2006.09.021
    [23] Liesa M, Palacín M, Zorzano A (2009) Mitochondrial dynamics in mammalian health and disease. Physiol Rev 89: 799-845. doi: 10.1152/physrev.00030.2008
    [24] Alexander C, Votruba M, Pesch U, et al. (2000) OPA1, encoding a dynamin-related GTPase, is mutated in autosomal dominant optic atrophy linked to chromosome 3q28. Nat Genet 26: 211-215. doi: 10.1038/79944
    [25] Detmer S, Chan D (2007) Functions and dysfunctions of mitochondrial dynamics. Nat Rev Mol Cell Biol 8: 870-879. doi: 10.1038/nrm2275
    [26] Ono T, Isobe K, Nakada K, et al. (2001) Human cells are protected from mitochondrial dysfunction by complementation of DNA products in fused mitochondria. Exp Neurol 28: 272-275.
    [27] Delettre C, Lenaers G, Griffoin JM, et al. (2000) Nuclear gene OPA1, encoding a mitochondrial dynamin-related protein, is mutated in dominant optic atrophy. Nat Genet 26: 207-210. doi: 10.1038/79936
    [28] Hudson G, Amati-Bonneau P, Blakely EL, et al. (2008) Mutation of OPA1 causes dominant optic atrophy with external ophthalmoplegia, ataxia, deafness and multiple mitochondrial DNA deletions: a novel disorder of mtDNA maintenance. Brain 131: 329-337. doi: 10.1093/brain/awm272
    [29] Uo T, Dworzak J, Kinoshita C, et al. (2009) Drp1 levels constitutively regulate mitochondrial dynamics and cell survival in cortical neurons. Exp Neurol 218: 274-285. doi: 10.1016/j.expneurol.2009.05.010
    [30] Ishihara N, Nomura M, Jofuku A, et al. (2009) Mitochondrial fission factor Drp1 is essential for embryonic development and synapse formation in mice. Nat Cell Biol 11: 958-966. doi: 10.1038/ncb1907
    [31] Darshi M, Mendiola VL, Mackey MR, et al. (2011) ChChd3, an inner mitochondrial membrane protein, is essential for maintaining crista integrity and mitochondrial function. J Biol Chem 286: 2918-2932. doi: 10.1074/jbc.M110.171975
    [32] Koch A, Yoon Y, Bonekamp NA, et al. (2005) A Role for Fis1 in Both Mitochondrial and Peroxisomal Fission in Mammalian Cells. Mol Biol Cell 16: 5077-5086. doi: 10.1091/mbc.e05-02-0159
    [33] Serasinghe M, Yoon Y (2008) The mitochondrial outer membrane protein hFis1 regulates mitochondrial morphology and fission through self-interaction. Exp Cell Res 314: 3494-3507. doi: 10.1016/j.yexcr.2008.09.009
    [34] Otera H, Wang C, Cleland MM, et al. (2010) Mff is an essential factor for mitochondrial recruitment of Drp1 during mitochondrial fission in mammalian cells. J Cell Biol 191: 1141-1158. doi: 10.1083/jcb.201007152
    [35] Knott AB, Perkins G, Schwarzenbacher R, et al. (2008) Mitochondrial fragmentation in neurodegeneration. Nat Rev Neurosci 9: 505-518. doi: 10.1038/nrn2417
    [36] Niemann A, Ruegg M, Padula VL, et al. (2005) Ganglioside-induced differentiation associated protein 1 is a regulator of the mitochondrial network: new implications for Charcot-Marie-Tooth disease. J Cell Biol 170: 1067-1078. doi: 10.1083/jcb.200507087
    [37] Wagner KM, Rüegg M, Niemann A, et al. (2009) Targeting and function of the mitochondrial fission factor GDAP1 are dependent on its tail-anchor. PloS One 4: e5160. doi: 10.1371/journal.pone.0005160
    [38] Chen H, Detmer SA, Ewald AJ, et al. (2003) Mitofusins Mfn1 and Mfn2 coordinately regulate mitochondrial fusion and are essential for embryonic development. J Cell Biol 160: 189-200. doi: 10.1083/jcb.200211046
    [39] Wakabayashi J, Zhang Z, Wakabayashi N, et al. (2009) The dynamin-related GTPase Drp1 is required for embryonic and brain development in mice. J Cell Biol 186: 805-816. doi: 10.1083/jcb.200903065
    [40] Chu CT (2019) Mechanisms of selective autophagy and mitophagy: Implications for neurodegenerative diseases. Neurobiol Dis 122: 23-34. doi: 10.1016/j.nbd.2018.07.015
    [41] Kageyama Y, Zhang Z, Roda R, et al. (2012) Mitochondrial division ensures the survival of postmitotic neurons by suppressing oxidative damage. J Cell Biol 197: 535-551. doi: 10.1083/jcb.201110034
    [42] Lutz AK, Exner N, Fett ME, et al. (2009) Loss of parkin or PINK1 function increases Drp1-dependent mitochondrial fragmentation. J Biol Chem 284: 22938-22951. doi: 10.1074/jbc.M109.035774
    [43] Matsuda N, Sato S, Shiba K, et al. (2010) PINK1 stabilized by mitochondrial depolarization recruits Parkin to damaged mitochondria and activates latent Parkin for mitophagy. J Cell Biol 189: 211-221. doi: 10.1083/jcb.200910140
    [44] Narendra DP, Jin SM, Tanaka A, et al. (2010) PINK1 is selectively stabilized on impaired mitochondria to activate Parkin. PLoS Biol 8: e1000298. doi: 10.1371/journal.pbio.1000298
    [45] Zhu J, Dagda RK, CHu CT (2011) Monitoring mitophagy in neuronal cell cultures. Methods Mol Biol 793: 325-339. doi: 10.1007/978-1-61779-328-8_21
    [46] Knott AB, Bossy-Wetzel E (2009) Impairing the Mitochondrial Fission and Fusion Balance: A New Mechanism of Neurodegeneration. Ann N Y Acad Sci 1147: 283-292. doi: 10.1196/annals.1427.030
    [47] Martin LJ (2010) Mitochondrial and Cell Death Mechanisms in Neurodegenerative Diseases. Pharmaceuticals 3: 839-915. doi: 10.3390/ph3040839
    [48] Corrado M, Scorrano L, Campello S (2012) Mitochondrial Dynamics in Cancer and Neurodegenerative and Neuroinflammatory Disease. Int J Cell Biol 2012. doi: 10.1155/2012/729290
    [49] Su B, Wang X, Zheng L, et al. (2010) Abnormal mitochondrial dynamics and neurodegenerative diseases. Biochim Biophys Acta 1802: 135-142. doi: 10.1016/j.bbadis.2009.09.013
    [50] Dauer W, Przedborski S (2003) Parkinson's disease: mechanisms and models. Neuron 39: 889-909. doi: 10.1016/S0896-6273(03)00568-3
    [51] Chang D, Nalls MA, Hallgrmsdóttir IB, et al. (2017) A meta-analysis of genome-wide association studies identifies 17 new Parkinson's disease risk loci. Nat Genet 49: 1511. doi: 10.1038/ng.3955
    [52] Olanow C, Tatton W (1999) Etiology and pathogenesis of Parkinson's disease. Annu Rev Neurosci 22: 123-144. doi: 10.1146/annurev.neuro.22.1.123
    [53] Koh H, Chung J (2010) PINK1 and Parkin to control mitochondria remodeling. Anat Cell Biol 43: 179-184. doi: 10.5115/acb.2010.43.3.179
    [54] Narendra D, Tanaka A, Suen DF, et al. (2008) Parkin is recruited selectively to impaired mitochondria and promotes their autophagy. J Cell Biol 183: 795-803. doi: 10.1083/jcb.200809125
    [55] Billingsley KJ, Barbosa IA, Bandrés-Ciga S, et al. (2019) Mitochondria function associated genes contribute to Parkinson's Disease risk and later age at onset. NPJ Parkinson's Dis 5: 8. doi: 10.1038/s41531-019-0080-x
    [56] Panayiotou C, Solaroli N, Johansson M, et al. (2010) Evidence of an intact N-terminal translocation sequence of human mitochondrial adenylate kinase 4. Int J Biochem Cell Biol 42: 62-69. doi: 10.1016/j.biocel.2009.09.007
    [57] Sai Y, Zou Z, Peng K, et al. (2012) The Parkinson's disease-related genes act in mitochondrial homeostasis. Neurosci Biobehav Rev 36: 2034-2043. doi: 10.1016/j.neubiorev.2012.06.007
    [58] Perier C, Vila M (2012) Mitochondrial biology and Parkinson's disease. Cold Spring Harb Perspect Med 2: a009332. doi: 10.1101/cshperspect.a009332
    [59] Comellas G, Lemkau LR, Nieuwkoop AJ, et al. (2011) Structured regions of α-synuclein fibrils include the early-onset Parkinson's disease mutation sites. J Mol Biol 411: 881-895. doi: 10.1016/j.jmb.2011.06.026
    [60] Ulmer TS, Bax A (2005) Comparison of structure and dynamics of micelle-bound human α-synuclein and Parkinson disease variants. J Biol Chem 280: 43179-43187. doi: 10.1074/jbc.M507624200
    [61] Nakamura K, Nemani VM, Azarbal F, et al. (2011) Direct membrane association drives mitochondrial fission by the Parkinson disease-associated protein α-synuclein. J Biol Chem 286: 20710-20726. doi: 10.1074/jbc.M110.213538
    [62] Mori H, Kondo T, Yokochi M, et al. (1998) Pathologic and biochemical studies of juvenile parkinsonism linked to chromosome 6q. Neurology 51: 890-892. doi: 10.1212/WNL.51.3.890
    [63] Mizuno Y, Hattori N, Yoshino H, et al. (2006) Progress in familial Parkinson's disease. Parkinson's Disease and Related Disorders Springer, 191-204. doi: 10.1007/978-3-211-45295-0_30
    [64] Lodi R, Tonon C, Valentino M, et al. (2004) Deficit of in vivo mitochondrial ATP production in OPA1-related dominant optic atrophy. Ann Neurol 56: 719-723. doi: 10.1002/ana.20278
    [65] Mayorov V, Lowrey A, Biousse V, et al. (2008) Mitochondrial oxidative phosphorylation in autosomal dominant optic atrophy. BMC Biochem 9: 22. doi: 10.1186/1471-2091-9-22
    [66] Zanna C, Ghelli A, Porcelli AM, et al. (2008) OPA1 mutations associated with dominant optic atrophy impair oxidative phosphorylation and mitochondrial fusion. Brain 131: 352-367. doi: 10.1093/brain/awm335
    [67] Krajewski K, Lewis R, Fuerst D, et al. (2000) Neurological dysfunction and axonal degeneration in Charcot-Marie-Tooth disease type 1A. Brain 44: 1299-1304.
    [68] Berger P, Young P, Suter U (2002) Molecular cell biology of Charcot-Marie-Tooth disease. Neurogenetics 4: 1-15. doi: 10.1007/s10048-002-0130-z
    [69] Baloh R, Schmidt R, Pestronk A, et al. (2007) Altered axonal mitochondrial transport in the pathogenesis of Charcot-Marie-Tooth disease from mitofusin 2 mutations. J Neurosci 27: 422-430. doi: 10.1523/JNEUROSCI.4798-06.2007
    [70] Züchner S, Vance J (2006) Molecular genetics of autosomal-dominant axonal Charcot-Marie-Tooth disease. Neuromolecular Med 8: 63-74. doi: 10.1385/NMM:8:1-2:63
    [71] Sme F (2010) MFN2 mutations cause severe phenotypes in most patients with CMT2A. Neurology 125: 245-256.
    [72] Cerveny K, Tamura Y (2007) Regulation of mitochondrial fusion and division. Trends Cell Biol 17: 563-569. doi: 10.1016/j.tcb.2007.08.006
    [73] Poole AC, Thomas RE, Andrews LA, et al. (2008) The PINK1/Parkin pathway regulates mitochondrial morphology. Proc Natl Acad Sci U S A 105: 1638-1643. doi: 10.1073/pnas.0709336105
    [74] Yang Y, Ouyang Y, Yang L, et al. (2008) Pink1 regulates mitochondrial dynamics through interaction with the fission/fusion machinery. Proc Natl Acad Sci U S A 105: 7070-7075. doi: 10.1073/pnas.0711845105
    [75] Valente EM, Abou-Sleiman PM, Caputo V, et al. (2004) Hereditary early-onset Parkinson's disease caused by mutations in PINK1. Science 304: 1158-1160. doi: 10.1126/science.1096284
    [76] Rothfuss O, Fischer H, Hasegawa T, et al. (2009) Parkin protects mitochondrial genome integrity and supports mitochondrial DNA repair. Hum Mol Genet 18: 3832-3850. doi: 10.1093/hmg/ddp327
    [77] Mortiboys H, Thomas KJ, Koopman WJ, et al. (2008) Mitochondrial function and morphology are impaired in parkin-mutant fibroblasts. Ann Neurol 64: 555-565. doi: 10.1002/ana.21492
    [78] Büttner S, Bitto A, Ring J, et al. (2008) Functional mitochondria are required for α-synuclein toxicity in aging yeast. J Biol Chem 283: 7554-7560. doi: 10.1074/jbc.M708477200
    [79] Banerjee K, Sinha M, Pham CLL, et al. (2010) α-Synuclein induced membrane depolarization and loss of phosphorylation capacity of isolated rat brain mitochondria: Implications in Parkinson's disease. FEBS Lett 584: 1571-1576. doi: 10.1016/j.febslet.2010.03.012
    [80] Yao C, El Khoury R, Wang W, et al. (2010) LRRK2-mediated neurodegeneration and dysfunction of dopaminergic neurons in a Caenorhabditis elegans model of Parkinson's disease. Neurobiol Dis 40: 73-81. doi: 10.1016/j.nbd.2010.04.002
    [81] Wang X, Yan MH, Fujioka H, et al. (2012) LRRK2 regulates mitochondrial dynamics and function through direct interaction with DLP1. Hum Mol Genet 21: 1931-1944. doi: 10.1093/hmg/dds003
    [82] Pich S, Bach D, Briones P, et al. (2005) The Charcot–Marie–Tooth type 2A gene product, Mfn2, up-regulates fuel oxidation through expression of OXPHOS system. Hum Mol Genet 14: 1405-1415. doi: 10.1093/hmg/ddi149
    [83] Detmer SA, Chan DC (2007) Complementation between mouse Mfn1 and Mfn2 protects mitochondrial fusion defects caused by CMT2A disease mutations. J Cell Biol 176: 405-414. doi: 10.1083/jcb.200611080
    [84] Niemann A, Berger P, Suter U (2006) Pathomechanisms of Mutant Proteins in Charcot-Marie-Tooth Disease. NeuroMolecular Med 8: 217-242. doi: 10.1385/NMM:8:1-2:217
    [85] Noack R, Frede S, Albrecht P, et al. (2012) Charcot–Marie–Tooth disease CMT4A: GDAP1 increases cellular glutathione and the mitochondrial membrane potential. Hum Mol Genet 21: 150-162. doi: 10.1093/hmg/ddr450
    [86] Cho D, Nakamura T, Fang J, et al. (2009) S-nitrosylation of Drp1 mediates beta-amyloid-related mitochondrial fission and neuronal injury. Science 324: 102-105. doi: 10.1126/science.1171091
    [87] Olichon A, Baricault L, Gas N (2003) Loss of OPA1 perturbates the mitochondrial inner membrane structure and integrity, leading to cytochrome c release and apoptosis. J Biol Chem 278: 7743-7746. doi: 10.1074/jbc.C200677200
    [88] Lin MT, Beal MF (2006) Mitochondrial dysfunction and oxidative stress in neurodegenerative diseases. Nature 443: 787. doi: 10.1038/nature05292
    [89] Wang X, Wang W, Li L, et al. (2014) Oxidative stress and mitochondrial dysfunction in Alzheimer's disease. Biochim Biophys Acta 1842: 1240-1247. doi: 10.1016/j.bbadis.2013.10.015
    [90] Smith MA, Rottkamp CA, Nunomura A, et al. (2000) Oxidative stress in Alzheimer's disease. Biochim Biophys Acta 1502: 139-144. doi: 10.1016/S0925-4439(00)00040-5
    [91] Hirai K, Aliev G, Nunomura A, et al. (2001) Mitochondrial abnormalities in Alzheimer's disease. J Neurosci 21: 3017-3023. doi: 10.1523/JNEUROSCI.21-09-03017.2001
    [92] Sun A, Chen Y (1998) Oxidative stress and neurodegenerative disorders. J Biomed Sci 5: 401-414. doi: 10.1007/BF02255928
    [93] Islam MT (2017) Oxidative stress and mitochondrial dysfunction-linked neurodegenerative disorders. Neurol Res 39: 73-82. doi: 10.1080/01616412.2016.1251711
    [94] Wang X, Su B, Fujioka H, et al. (2008) Dynamin-like protein 1 reduction underlies mitochondrial morphology and distribution abnormalities in fibroblasts from sporadic Alzheimer's disease patients. Am J Pathol 173: 470-482. doi: 10.2353/ajpath.2008.071208
    [95] Wang X, Su B, Siedlak SL, et al. (2008) Amyloid-β overproduction causes abnormal mitochondrial dynamics via differential modulation of mitochondrial fission/fusion proteins. Proc Natl Acad Sci 105: 19318-19323. doi: 10.1073/pnas.0804871105
    [96] Martin M, Hurd D, Saxton W (1999) Kinesins in the nervous system. Cell Mol Life Sci 56: 200-216. doi: 10.1007/s000180050422
    [97] Schnapp BJ, Reese TS (1989) Dynein is the motor for retrograde axonal transport of organelles. Proc Natl Acad Sci U S A 86: 1548-1552. doi: 10.1073/pnas.86.5.1548
    [98] Tabb JS, Molyneaux BJ, Cohen DL, et al. (1998) Transport of ER vesicles on actin filaments in neurons by myosin V. J Cell Sci 111: 3221-3234.
    [99] Ligon LA, Steward O (2000) Role of microtubules and actin filaments in the movement of mitochondria in the axons and dendrites of culture hippocampal neurons. Journal Comp Neur 427: 351-361. doi: 10.1002/1096-9861(20001120)427:3<351::AID-CNE3>3.0.CO;2-R
    [100] Hirokawa N (1998) Kinesin and dynein superfamily proteins and the mechanism of organelle transport. Science 279: 519-526. doi: 10.1126/science.279.5350.519
    [101] Gross SP (2004) Hither and yon: A review of bi-directional microtubule-based transport. Phys Biol 1: R1-R11. doi: 10.1088/1478-3967/1/2/R01
    [102] Ligon LA, Tokito M, Finklestein JM, et al. (2004) A direct interaction between cytoplasmic dynein and kinesin I may coordinate motor activity. J Biol Chem 279: 19201-19208. doi: 10.1074/jbc.M313472200
    [103] Stowers R, Megeath L, Górska-Andrzejak J, et al. (2002) Axonal transport of mitochondria to synapses depends on milton, a novel Drosophila protein. Neuron 36: 1063-1077. doi: 10.1016/S0896-6273(02)01094-2
    [104] Guo X, Macleod G, Wellington A, et al. (2005) The GTPase dMiro is required for axonal transport of mitochondria to Drosophila synapses. Neuron 47: 379-393. doi: 10.1016/j.neuron.2005.06.027
    [105] Russo G, Louie K, Wellington A, et al. (2009) Drosophila Miro is required for both anterograde and retrograde axonal mitochondrial transport. J Neurosci 29: 5443-5455. doi: 10.1523/JNEUROSCI.5417-08.2009
    [106] Koutsopoulos OS, Laine D, Osellame L, et al. (2010) Human miltons associate with mitochondria and induce microtubule-dependent remodeling of mitochondrial networks. Biochim Biophys Acta 1803: 564-574. doi: 10.1016/j.bbamcr.2010.03.006
    [107] Wang X, Winter D, Ashrafi G, et al. (2011) PINK1 and Parkin target Miro for phosphorylation and degradation to arrest mitochondrial motility. Cell 147: 893-906. doi: 10.1016/j.cell.2011.10.018
    [108] Hsieh CH, Shaltouki A, Gonzalez AE, et al. (2016) Functional impairment in miro degradation and mitophagy is a shared feature in familial and sporadic Parkinson's disease. Cell Stem Cell 19: 709-724. doi: 10.1016/j.stem.2016.08.002
    [109] Baloh RH (2008) Mitochondrial dynamics and peripheral neuropathy. Neuroscientist 14: 12-18. doi: 10.1177/1073858407307354
    [110] Misko A, Jiang S, Wegorzewska I, et al. (2010) Mitofusin 2 is necessary for transport of axonal mitochondria and interacts with the Miro/Milton complex. J Neurosci 30: 4232-4240. doi: 10.1523/JNEUROSCI.6248-09.2010
    [111] Ikenaka K, Katsuno M, Kawai K, et al. (2012) Disruption of axonal transport in motor neuron diseases. Int J Mol Sci 13: 1225-1238. doi: 10.3390/ijms13011225
    [112] Mandal A, Drerup CM (2019) Axonal transport and mitochondrial function in neurons. Front Cell Neurosci 13: 373. doi: 10.3389/fncel.2019.00373
    [113] Ader NR (2016) Seeking an in vivo neuronal context for the PINK1/Parkin pathway. J Neurosci 36: 11165-11167. doi: 10.1523/JNEUROSCI.2525-16.2016
    [114] Metaxakis A, Ploumi C, Tavernarakis N (2018) Autophagy in age-associated neurodegeneration. Cells 7: 37. doi: 10.3390/cells7050037
    [115] Rintoul GL, Reynolds IJ (2010) Mitochondrial trafficking and morphology in neuronal injury. Biochim Biophys Acta 1802: 143-150. doi: 10.1016/j.bbadis.2009.09.005
    [116] Chang DT, Reynolds IJ (2006) Mitochondrial trafficking and morphology in healthy and injured neurons. Prog Neurobiol 80: 241-268. doi: 10.1016/j.pneurobio.2006.09.003
    [117] Weihofen A, Thomas K, Ostaszewski B, et al. (2009) Pink1 forms a multiprotein complex with miro and milton, linking Pink1 function to mitochondrial trafficking. Biochemistry 48: 2045-2052. doi: 10.1021/bi8019178
    [118] Yang F, Jiang Q, Zhao J, et al. (2005) Parkin stabilizes microtubules through strong binding mediated by three independent domains. J Biol Chem 280: 17154-17162. doi: 10.1074/jbc.M500843200
    [119] Lee H, Khoshaghideh F, Lee S, et al. (2006) Impairment of microtubule-dependent trafficking by overexpression of α-synuclein. European J Neurosci 24: 3153-3162. doi: 10.1111/j.1460-9568.2006.05210.x
    [120] Gillardon F (2009) Leucine-rich repeat kinase 2 phosphorylates brain tubulin-beta isoforms and modulates microtubule stability—A point of convergence in Parkinsonian neurodegeneration? J Neurochem 10: 1514-1522. doi: 10.1111/j.1471-4159.2009.06235.x
    [121] Braak E, Sandmann-Keil D, Rüb U, et al. (2001) α-Synuclein immunopositive Parkinson's disease-related inclusion bodies in lower brain stem nuclei. Acta Neuropathol 101: 195-201. doi: 10.1007/s004010000247
    [122] Liu S, Sawada T, Lee S, et al. (2012) Parkinson's disease–associated kinase PINK1 regulates Miro protein level and axonal transport of mitochondria. PLoS Genet 8: e1002537. doi: 10.1371/journal.pgen.1002537
    [123] Chu Y, Morfini GA, Langhamer LB, et al. (2012) Alterations in axonal transport motor proteins in sporadic and experimental Parkinson's disease. Brain 135: 2058-2073. doi: 10.1093/brain/aws133
    [124] Abeliovich A, Gitler AD (2016) Defects in trafficking bridge Parkinson's disease pathology and genetics. Nature 539: 207. doi: 10.1038/nature20414
    [125] Züchner S, Mersiyanova I, Muglia M, et al. (2004) Mutations in the mitochondrial GTPase mitofusin 2 cause Charcot-Marie-Tooth neuropathy type 2A. Nat Genet 36: 449-451. doi: 10.1038/ng1341
    [126] Patzkó A, Shy ME (2011) Update on Charcot-Marie-Tooth Disease. Curr Neurol Neurosci Rep 11: 78-88. doi: 10.1007/s11910-010-0158-7
    [127] Shy M (2004) Charcot-Marie-Tooth disease: An update. Curr Opin Neurol 17: 579-585. doi: 10.1097/00019052-200410000-00008
    [128] Loiseau D, Chevrollier A, Verny C, et al. (2007) Mitochondrial coupling defect in Charcot–Marie–Tooth type 2A disease. Ann Neurol 61: 315-323. doi: 10.1002/ana.21086
    [129] Stokin G, Lillo C, Falzone T, et al. (2005) Axonopathy and transport deficits early in the pathogenesis of Alzheimer's diseases. Science 307: 1282-1288. doi: 10.1126/science.1105681
    [130] Wang X, Su B, Lee H (2009) Impaired balance of mitochondrial fission and fusion in Alzheimer's disease. J Neurosci 29: 9090-9103. doi: 10.1523/JNEUROSCI.1357-09.2009
    [131] Vickers JC, King AE, Woodhouse A, et al. (2009) Axonopathy and cytoskeletal disruption in degenerative diseases of the central nervous system. Brain Res Bull 80: 217-223. doi: 10.1016/j.brainresbull.2009.08.004
    [132] De Vos K, Chapman A, Tennant M, et al. (2007) Familial amyotrophic lateral sclerosis-linked SOD1 mutants perturb fast axonal transport to reduce axonal mitochondria content. Hum Mol Genet 16: 2720-2728. doi: 10.1093/hmg/ddm226
    [133] Shi P, Ström A, Gal J, et al. (2010) Effects of ALS-related SOD1 mutants on dynein- and KIF5-mediated retrograde and anterograde axonal transport. Biochim Biophys Acta 1802: 707-716. doi: 10.1016/j.bbadis.2010.05.008
    [134] Chang D, Rintoul G, Pandipati S, et al. (2006) Mutant huntingtin aggregates impair mitochondrial movement and trafficking in cortical neurons. Neurobiol Dis 22: 388-400. doi: 10.1016/j.nbd.2005.12.007
    [135] Trushina E, Dyer R, Badger J, et al. (2004) Mutant huntingtin impairs axonal trafficking in mammalian neurons in vivo and in vitro. Mol Cell Biol 24: 8195-8209. doi: 10.1128/MCB.24.18.8195-8209.2004
    [136] Bach D, Pich S, Soriano FX (2003) Mitofusin-2 determines mitochondrial network architecture and mitochondrial metabolism: a novel regulatory mechanism altered in obesity. J Biol Chem 278: 17190-17197. doi: 10.1074/jbc.M212754200
    [137] Chen H, Chomyn A, Chan DC (2005) Disruption of fusion results in mitochondrial heterogeneity and dysfunction. J Biol Chem 280: 26185-26192. doi: 10.1074/jbc.M503062200
    [138] Van Laar VS, Berman SB (2013) The interplay of neuronal mitochondrial dynamics and bioenergetics: implications for Parkinson's disease. Neurobiol Dis 51: 43-55. doi: 10.1016/j.nbd.2012.05.015
    [139] Coskun P, Wyrembak J, Schriner SE, et al. (2012) A mitochondrial etiology of Alzheimer and Parkinson disease. Biochim Biophys Acta 1820: 553-564. doi: 10.1016/j.bbagen.2011.08.008
    [140] Ryan BJ, Hoek S, Fon EA, et al. (2015) Mitochondrial dysfunction and mitophagy in Parkinson's: from familial to sporadic disease. Trends Biochem Sci 40: 200-210. doi: 10.1016/j.tibs.2015.02.003
    [141] Van Laar VS, Berman SB (2009) Mitochondrial dynamics in Parkinson's disease. Exp Neurol 218: 247-256. doi: 10.1016/j.expneurol.2009.03.019
    [142] Requejo-Aguilar R, Bolaños JP (2016) Mitochondrial control of cell bioenergetics in Parkinson's disease. Free Radic Biol Med 100: 123-137. doi: 10.1016/j.freeradbiomed.2016.04.012
    [143] Abramov AY, Gegg M, Grunewald A, et al. (2011) Bioenergetic consequences of PINK1 mutations in Parkinson disease. PLoS One 6: e25622. doi: 10.1371/journal.pone.0025622
    [144] Lansbury PT, Lashuel HA (2006) A century-old debate on protein aggregation and neurodegeneration enters the clinic. Nature 443: 774-779. doi: 10.1038/nature05290
    [145] Jain S, Wood NW, Healy DG (2005) Molecular genetic pathways in Parkinson's disease: A review. Clin Sci 109: 355-364. doi: 10.1042/CS20050106
    [146] Winklhofer KF, Haass C (2010) Mitochondrial dysfunction in Parkinson's disease. Biochim Biophy Acta 1802: 29-44. doi: 10.1016/j.bbadis.2009.08.013
    [147] Chen C, Turnbull DM, Reeve AK (2019) Mitochondrial Dysfunction in Parkinson's Disease—Cause or Consequence? Biology 8: 38. doi: 10.3390/biology8020038
    [148] Diot A, Morten K, Poulton J (2016) Mitophagy plays a central role in mitochondrial ageing. Mamm Genome 27: 381-395. doi: 10.1007/s00335-016-9651-x
    [149] Noda S, Sato S, Fukuda T, et al. (2019) Loss of Parkin contributes to mitochondrial turnover and dopaminergic neuronal loss in aged mice. Neurobiol Dis 136: 104717. doi: 10.1016/j.nbd.2019.104717
    [150] Fivenson EM, Lautrup S, Sun N, et al. (2017) Mitophagy in neurodegeneration and aging. Neurochem Int 109: 202-209. doi: 10.1016/j.neuint.2017.02.007
    [151] Ebrahimi-Fakhari D, Wahlster L, McLean PJ (2012) Protein degradation pathways in Parkinson's disease: curse or blessing. Acta Neuropathol 124: 153-172. doi: 10.1007/s00401-012-1004-6
    [152] Wang W, Wang X, Fujioka H, et al. (2016) Parkinson's disease–associated mutant VPS35 causes mitochondrial dysfunction by recycling DLP1 complexes. Nat Med 22: 54. doi: 10.1038/nm.3983
    [153] Singleton A, Farrer M, Johnson J, et al. (2003) α-Synuclein locus triplication causes Parkinson's disease. Science 302: 841-841. doi: 10.1126/science.1090278
    [154] Regev A, Silverman W, Shapiro E (2001) Representation and simulation of biochemical processes using the π-calculus process algebra. Pac Symp Biocomput 459-470.
    [155] Bonzanni N, Feenstra KA, Fokkink W, et al. (2009) What can formal methods bring to systems biology? International Symposium on Formal Methods Springer, 16-22.
    [156] Theocharopoulou G, Giannakis K, Andronikos T (2015) The mechanism of splitting mitochondria in terms of membrane automata. 2015 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) IEEE, 397-402. doi: 10.1109/ISSPIT.2015.7394367
    [157] Theocharopoulou G, Vlamos P (2015) Modeling protein misfolding in Charcot–Marie–Tooth disease. GeNeDis 2014 Springer, 91-102. doi: 10.1007/978-3-319-09012-2_7
    [158] Theocharopoulou G, Bobori C, Vlamos P (2017) Formal models of biological systems. GeNeDis 2016 Springer, 325-338. doi: 10.1007/978-3-319-56246-9_27
    [159] Corona JC, Duchen MR (2015) Impaired mitochondrial homeostasis and neurodegeneration: towards new therapeutic targets? J Bioenerg Biomembr 47: 89-99. doi: 10.1007/s10863-014-9576-6
    [160] Kitada T, Asakawa S, Hattori N, et al. (1998) Mutations in the parkin gene cause autosomal recessive juvenile parkinsonism. Nature 392: 605. doi: 10.1038/33416
    [161] Healy DG, Falchi M, O'Sullivan SS, et al. (2008) Phenotype, genotype, and worldwide genetic penetrance of LRRK2-associated Parkinson's disease: a case-control study. Lancet Neurol 7: 583-590. doi: 10.1016/S1474-4422(08)70117-0
    [162] Peng JY, Lin CC, Chen YJ, et al. (2011) Automatic morphological subtyping reveals new roles of caspases in mitochondrial dynamics. PLoS Comput Biol 7: e1002212. doi: 10.1371/journal.pcbi.1002212
    [163] Tronstad KJ, Nooteboom M, Nilsson LI, et al. (2014) Regulation and quantification of cellular mitochondrial morphology and content. Curr Pharm Des 20: 5634-5652. doi: 10.2174/1381612820666140305230546
    [164] Zamponi N, Zamponi E, Cannas SA, et al. (2018) Mitochondrial network complexity emerges from fission/fusion dynamics. Sci Rep 8: 363. doi: 10.1038/s41598-017-18351-5
    [165] Shah SI, Paine JG, Perez C, et al. (2019) Mitochondrial fragmentation and network architecture in degenerative diseases. PloS One 14: e0223014. doi: 10.1371/journal.pone.0223014
    [166] Toglia P, Demuro A, Mak DOD, et al. (2018) Data-driven modeling of mitochondrial dysfunction in Alzheimer's disease. Cell Calcium 76: 23-35. doi: 10.1016/j.ceca.2018.09.003
    [167] Dukes AA, Bai Q, Van Laar VS, et al. (2016) Live imaging of mitochondrial dynamics in CNS dopaminergic neurons in vivo demonstrates early reversal of mitochondrial transport following MPP+ exposure. Neurobiol Dis 95: 238-249. doi: 10.1016/j.nbd.2016.07.020
    [168] Alexiou A, Vlamos P (2012) Evidence for early identification of Alzheimer's disease. In arXiv preprint arXiv 1209.4223.
    [169] Lundkvist J, Naslund J (2007) Gamma-secretase: A complex target for Alzheimer's disease. Curr Opin Pharmacol 7: 112-118. doi: 10.1016/j.coph.2006.10.002
    [170] Evin G, Kenche V (2007) BACE inhibitors as potential therapeutics for Alzheimer's disease. Recent Pat CNS Drug Discov 2: 188-199. doi: 10.2174/157488907782411783
    [171] Alexiou A, Vlamos P, Rekkas J (2011) Modeling the mitochondrial dysfunction in neurogenerative diseases due to high H+ concentration. Bioinformation 6: 173-175. doi: 10.6026/97320630006173
    [172] Miller KE, Sheetz MP (2004) Axonal mitochondrial transport and potential are correlated. J Cell Sci 117: 2791-2804. doi: 10.1242/jcs.01130
    [173] Oliveira JMA (2011) Techniques to investigate neuronal mitochondrial function and its pharmacological modulation. Curr Drug Targets 12: 762-773. doi: 10.2174/138945011795528895
    [174] Twig G, Hyde B, Shirihai OS (2008) Mitochondrial fusion, fission and autophagy as a quality control axis: the bioenergetic view. Biochim Biophys Acta 1777: 1092-1097. doi: 10.1016/j.bbabio.2008.05.001
    [175] Onyango IG, Dennis J, Khan SM (2016) Mitochondrial dysfunction in Alzheimer's disease and the rationale for bioenergetics based therapies. Aging Dis 7: 201-214. doi: 10.14336/AD.2015.1007
  • This article has been cited by:

    1. Shuhao Jiang, Jiahui Shang, Jichang Guo, Yong Zhang, Multi-Strategy Improved Flamingo Search Algorithm for Global Optimization, 2023, 13, 2076-3417, 5612, 10.3390/app13095612
    2. Ulzhalgas Zhunissova, Róża Dzierżak, Zbigniew Omiotek, Volodymyr Lytvynenko, A Novel COVID-19 Diagnosis Approach Utilizing a Comprehensive Set of Diagnostic Information (CSDI), 2023, 12, 2077-0383, 6912, 10.3390/jcm12216912
    3. Zijiao Zhang, Chong Wu, Shiyou Qu, Jiaming Liu, A hierarchical chain-based Archimedes optimization algorithm, 2023, 20, 1551-0018, 20881, 10.3934/mbe.2023924
    4. Amjad Qtaish, Dheeb Albashish, Malik Braik, Mohammad T. Alshammari, Abdulrahman Alreshidi, Eissa Jaber Alreshidi, Memory-Based Sand Cat Swarm Optimization for Feature Selection in Medical Diagnosis, 2023, 12, 2079-9292, 2042, 10.3390/electronics12092042
    5. Benjamin Danso Kwakye, Yongjun Li, Halima Habuba Mohamed, Evans Baidoo, Theophilus Quachie Asenso, Particle guided metaheuristic algorithm for global optimization and feature selection problems, 2024, 248, 09574174, 123362, 10.1016/j.eswa.2024.123362
    6. Law Kumar Singh, Munish Khanna, Himanshu Monga, Rekha singh, Gaurav Pandey, Nature-Inspired Algorithms-Based Optimal Features Selection Strategy for COVID-19 Detection Using Medical Images, 2024, 42, 0288-3635, 761, 10.1007/s00354-024-00255-4
    7. Maryam Askari, Farid Khoshalhan, Hodjat Hamidi, Boosting Feature Selection Efficiency with IMVO: Integrating MVO and Mutation-Based Local Search Algorithms, 2025, 25901230, 104866, 10.1016/j.rineng.2025.104866
  • Reader Comments
  • © 2020 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(6619) PDF downloads(507) Cited by(15)

Figures and Tables

Figures(2)  /  Tables(2)

Other Articles By Authors

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog