Training Sequence Research Articles

HiMolformer: Integrating graph and sequence representations for predicting liver microsome stability with SMILES

In the initial stages of drug discovery or pre-clinical studies, understanding the metabolic stability of new molecules is crucial. Recently, research on pre-trained deep learning for molecular property prediction has been actively progressing, with various models being made open-source. However, most of these models rely on either 2D graph or 1D sequence for training, and the representation varies depending on the data format used. Consequently, combining multiple representations can broaden the scope of learning and may potentially be a manageable and most effective method to enhance performance.Therefore, we propose a novel hybrid model for predicting metabolic stability, which integrates representations from both graph-based and sequence-based models pre-trained for molecular features. This approach utilizes the combined strengths of 2D topological and 1D sequential information of molecules. HiMol, a graph-based graph neural network (GNN) model, and Molformer, a sequence-based Transformer model, were selected for integration, thus we named it HiMolformer. HiMolformer demonstrated superior performance compared to other models. We also focus on regression task for prediction with a empirical dataset from Korea Chemical Bank (KCB), comprising 3,498 molecules with mouse liver microsome (MLM) and human liver microsome (HLM) data obtained from actual metabolic reaction experiments. To the best of our knowledge, it is the first attempt to develop MLM and HLM prediction models using regression with a single SMILES input. The source code of this model is available at https://github.com/YUNSEOKWOO/HiMolformer.

Acute effects of the sequence of concurrent high-intensity resistance and endurance exercises in recreational athletes

This study aimed to assess the acute effects of the sequence of concurrent training (CT) on physiological, neuromuscular, and perceptive parameters in recreational athletes. Eighteen active men (mean ± SD: 22.00 ± 2.00 years; 79.40 ± 9.87 kg and 175.62 ± 6.35 cm) performed two CT sessions consisting of repeated sprint endurance exercise followed by resistance exercise (E-R) or the reverse sequence (R-E) in a randomized order. The E exercise consisted of 6x30s of cycling “all-out” interspersed by 15s of passive recovery, while the R exercise consisted of 3x15 repetitions near failure (1 repetition in reserve) of back squat exercise with rest intervals of 45s. Height in CMJ, heart rate (HR), rating of perceived exertion (RPE) after each exercise, and at the final of the session (sRPE) were recorded. The R-E sequence showed a higher HR at 10s, 1min and 6min (p < .05) post E exercise compared to R exercise. Significant protocol x time interactions were observed for sRPE (p < .001) being higher after the R-E sequence compared to E-R sequence. RPE was significantly higher (p < .01) after E exercise compared to R exercise in both sequences, without differences between the E exercises. However, there were significant differences between the R exercises (p < .01) being higher in the R-E sequence. Our results suggest that the order of exercises during CT affects the second exercise when performed in a R-E sequence, with more cardiovascular stress and higher perceived exertions.

Advanced resistance exercise combined with aerobic rehabilitation training on cardiopulmonary function

Chronic diseases are the number one killer in the world today, and the most common cause of chronic diseases is lack of exercise. Research on the application of artificial intelligence technology in the medical field can shorten the distance between clinical best practice and practical application, and promote the standardized management of clinicians according to specifications. In this paper, three different exercise methods, continuous aerobic, anaerobic, and control, were used to conduct a 12-week study. This paper discussed the effects of three different forms of exercise on the body shape, body composition, and metabolism of patients with chronic diseases, and discussed the intervention effects of the same exercise mode in different periods (0–6 weeks, 6–12 weeks), to provide a theoretical basis for more effective and targeted choice of exercise intervention programs. Through training load, training frequency, training sequence, training interval, and other factors, a training plan can be designed. To avoid mistakes, experts often try to do some items that are prone to mistakes, especially lung function measurement. The scores of self-care, extraction, standing, occupation/housework, social activities, and total scores were significantly lower than those before intervention (P < 0.01). Advanced resistance kinetic energy can significantly improve the exercise and cardiopulmonary function of patients with various types of chronic diseases. Advanced resistance kinetic energy can significantly promote the strength and explosive force of the shoulder, waist, and back muscles in chronic patients, and can significantly promote the muscle adaptability of the shoulder, waist, and back muscles in chronic patients.

Applying Machine Learning and SERS for Precise Typing of DNA Secondary Structures.

Surface-enhanced Raman spectroscopy (SERS) has been demonstrated as an effective method for elucidating secondary structural characteristics of DNA. However, the inherent complexity of the DNA conformation and the lack of SERS samples pose challenges for identifying numerous secondary structures. To address these issues, a synergistic method integrating machine learning with SERS was proposed so as to analyze the SERS spectra of 54 well-defined conformational oligonucleotides, namely, G-quadruplex (G4), i-motif (iM), double-strand (DS), and single-strand (SS) configurations. Principal component analysis (PCA) effectively segregated the oligonucleotides into three distinct conformational groups (G4s, iMs, and others). Furthermore, linear discriminant analysis (LDA), K-nearest neighbor (KNN), and support vector machine (SVM) approaches were utilized to improve the typing accuracy of 54 trained sequences. This enabled the correct classification of the structures of five untrained sequences, as well as the identification of the predominant conformations including G4, iM, and DS formed by two complementary G-rich and C-rich sequences in acidic and neutral pH conditions. The results of this study demonstrated the potential of the proposed methodology for rapid screening and prediction of secondary DNA conformations.

A scheme of combining DFO and channel estimation scheme for mobile OFDM systems

AbstractTo reduce the impact of residual Doppler frequency offset (RDFO), a joint DFO estimation and CE scheme is proposed for the OFDM systems under the high‐speed mobile environment. In the paper, the expression of interference power caused by the RDFO is first derived, and the effect of RDFO on time‐varying characteristic of channel is analysed. Then, a joint DFO and channel estimation scheme is presented. Specifically, a high‐precision DFO estimator based on the convolutional neural network with anti‐noise is firstly designed. Due to its ability to use fewer samples to adapt well to the new environments, the meta learning is adopted to estimate the time‐varying channel. Moreover, to improve the practicality of the algorithm, the non‐ideal values rather than ideal values are used as the training targets in the two neural networks. Additionally, the proposed method is only based on the received signal and does not require any pilots or training sequences, which has higher transmission efficiency compared to the existing algorithms. The research results indicate that the proposed method has good estimation performance and good practicality, and it is suitable for high‐speed mobile scenarios.

Research on Multi-Objective Optimization Methods of Urban Rail Train Automatic Driving Based on NSGA-II

In order to improve the control performance of automatic train operation (ATO) in urban rail trains, five typical operating sequences of urban rail trains were studied. Under the condition of meeting the safety and comfort principles of train operation, a train dynamics model was established to achieve the goals of low energy consumption, short running time, and high stopping accuracy in urban rail transit trains. In the process of finding a multi-objective solution to this problem, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) was used with an elite retention strategy, and the optimal Pareto multi-objective solution set was sought. In the process of optimal solution weight assignment, the hierarchical analysis Mahalanobis distance method, which combines subjective and objective analysis, was used. Finally, taking the Beijing Yizhuang subway line as the background design example, the simulation verified the effectiveness and feasibility of the algorithm and obtained high-quality automatic train driving curves under various working conditions. This research has important reference significance for the actual operation of automatic driving in urban rail trains.

AIPs-DeepEnC-GA: Predicting anti-inflammatory peptides using embedded evolutionary and sequential feature integration with genetic algorithm based deep ensemble model

Inflammation is a biological response to harmful stimuli including infections, damaged cells, tissue injuries, and toxic chemicals. It plays an essential role in facilitating tissue repair by eliminating pathogenic microorganisms. Currently, numerous therapies are applied to treat autoimmune and inflammatory diseases. However, these conventional anti-inflammatory medications are often labor-intensive, costly, and associated with adverse side effects. Recently, researchers have identified anti-inflammatory peptides (AIPs) as a cost-effective alternative for treating several inflammatory diseases, due to their high selectivity for target cells with minimal side effects. In this study, we introduce a novel computational predictor, AIPs-DeepEnC-GA, developed to accurately predict AIP samples. The training sequences are encoded using a novel n-spaced dipeptide-based position-specific scoring matrix (NsDP-PSSM) and Pseudo position-specific scoring matrix (PsePSSM)-based embedded evolutionary features. Additionally, the reduced-amino acid alphabet (RAAA-11), and composite Physiochemical properties (CPP) are employed to capture cluster-physiochemical properties based on structural information. A hybrid feature strategy is then applied, integrating embedded evolutionary features, CPP and RAAA-11 descriptors to overcome the limitations of individual encoding methods. Minimum redundancy and maximum relevance (mRMR) is utilized to select the optimal features. The selected features are trained using four different deep-learning models. The predictive labels generated by these models are provided to a genetic algorithm to form a deep-ensemble training model. The proposed AIPs-DeepEnC-GA model achieved a ∼15 % increase in predictive accuracy, reaching 94.39 %, and a 19 % improvement in the area under the curve (AUC), achieving a value of 0.98 using training sequences. For independent datasets, our method obtained improved accuracies of 91.87 %, and 89.21 %, with AUC values of 0.94 and 0.92 for Ind-I, and Ind-II, respectively. Our proposed AIPs-DeepEnC-GA model demonstrates an 11 % improvement in predictive accuracy over existing AIPs computational models using training samples. The efficacy and reliability of this model make it a promising tool for both in drug development and research academia.

Continuous fake media detection: Adapting deepfake detectors to new generative techniques

Generative techniques continue to evolve at an impressively high rate, driven by the hype about these technologies. This rapid advancement severely limits the application of deepfake detectors, which, despite numerous efforts by the scientific community, struggle to achieve sufficiently robust performance against the ever-changing content. To address these limitations, in this paper, we propose an analysis of two continuous learning techniques on a Short and a Long sequence of fake media. Both sequences include a complex and heterogeneous range of deepfakes (generated images and videos) from GANs, computer graphics techniques, and unknown sources. Our experiments show that continual learning could be important in mitigating the need for generalizability. In fact, we show that, although with some limitations, continual learning methods help to maintain good performance across the entire training sequence. For these techniques to work in a sufficiently robust way, however, it is necessary that the tasks in the sequence share similarities. In fact, according to our experiments, the order and similarity of the tasks can affect the performance of the models over time. To address this problem, we show that it is possible to group tasks based on their similarity. This small measure allows for a significant improvement even in longer sequences. This result suggests that continual techniques can be combined with the most promising detection methods, allowing them to catch up with the latest generative techniques. In addition to this, we propose an overview of how this learning approach can be integrated into a deepfake detection pipeline for continuous integration and continuous deployment (CI/CD). This allows you to keep track of different funds, such as social networks, new generative tools, or third-party datasets, and through the integration of continuous learning, allows constant maintenance of the detectors.

PCP-GC-LM: single-sequence-based protein contact prediction using dual graph convolutional neural network and convolutional neural network

BackgroundRecently, the process of evolution information and the deep learning network has promoted the improvement of protein contact prediction methods. Nevertheless, still remain some bottleneck: (1) One of the bottlenecks is the prediction of orphans and other fewer evolution information proteins. (2) The other bottleneck is the method of predicting single-sequence-based proteins mainly focuses on selecting protein sequence features and tuning the neural network architecture, However, while the deeper neural networks improve prediction accuracy, there is still the problem of increasing the computational burden. Compared with other neural networks in the field of protein prediction, the graph neural network has the following advantages: due to the advantage of revealing the topology structure via graph neural network and being able to take advantage of the hierarchical structure and local connectivity of graph neural networks has certain advantages in capturing the features of different levels of abstraction in protein molecules. When using protein sequence and structure information for joint training, the dependencies between the two kinds of information can be better captured. And it can process protein molecular structures of different lengths and shapes, while traditional neural networks need to convert proteins into fixed-size vectors or matrices for processing.ResultsHere, we propose a single-sequence-based protein contact map predictor PCP-GC-LM, with dual-level graph neural networks and convolution networks. Our method performs better with other single-sequence-based predictors in different independent tests. In addition, to verify the validity of our method against complex protein structures, we will also compare it with other methods in two homodimers protein test sets (DeepHomo test dataset and CASP-CAPRI target dataset). Furthermore, we also perform ablation experiments to demonstrate the necessity of a dual graph network. In all, our framework presents new modules to accurately predict inter-chain contact maps in protein and it’s also useful to analyze interactions in other types of protein complexes.

General knowledge and detailed memory benefit from different training sequences.

General knowledge and detailed memory benefit from different training sequences.

Virtual Array-Based Signal Detection and Carrier Frequency Offset Estimation in a Multistatic Collaborative Passive Detection System

To tackle the problem of difficult signal detection and carrier frequency synchronization faced by wireless communication among stations of the multistatic passive detection system in interference environments, an adaptive signal detection and carrier frequency offset (CFO) estimation method based on a virtual array is proposed in this paper. This is a data-aided method that utilizes a training sequence composed of three segments of sub-training sequences with different symbols. This method first uses spatial spectrum estimation to obtain the coarse frequency estimations of interference signals and CFO from virtual array signals constructed from the first two sub-training sequences. Then, beamforming is conducted accordingly on the virtual array signals constructed from the third sub-training sequence to suppress the in-band interferences and protrude the expected signal. Finally, improved performance of signal detection and CFO estimation is obtained with the beamformed signals. Simulation experiments show that a missed detection probability as low as 1 × 10−4, with a false detection probability of 1 × 10−3, can be obtained under a signal-to-interference ratio (SIR) of −10 dB and Eb/N0 of 1 dB. Moreover, the proposed method can also simultaneously achieve a CFO estimation error that is lower than 3%, with the condition of Eb/N0 being as low as −5 dB under different SIRs. Simulation results validate the proposed method and demonstrate the promising application prospects of the proposed method in networked passive detection scenarios.

Estimation of the Impulse Response of the AWGN Channel with ISI within an Iterative Equalization and Decoding System That Uses LDPC Codes.

In this paper, new schemes have been proposed for the estimation of the additive white Gaussian noise (AWGN) channel with intersymbol interference (ISI) in an iterative equalization and decoding system using low-density parity check (LDPC) codes. This article explores the use of the least squares algorithm in various scenarios. For example, the impulse response of the AWGN channel h was initially estimated using a training sequence. Subsequently, the impulse response was calculated based on the training sequence and then re-estimated once using the sequence estimated from the output of the LDPC decoder. Lastly, the impulse response was calculated based on the training sequence and re-estimated twice using the sequence estimated from the output of the LDPC decoder. Comparisons were made between the performances of the three mentioned situations, with the situation in which a perfect estimate of the impulse response of the channel is assumed. The performance analysis focused on how the bit error rate changes in relation to the signal-to-noise ratio. The BER performance comes close to the scenario of having a perfect estimate of the impulse response when the estimation is performed based on the training sequence and then re-estimated twice from the sequence obtained from the output of the LDPC decoder.

Effect of 3D printed teeth and virtual simulation system on the pre-clinical access cavity preparation training of senior dental undergraduates

BackgroundThe objective of the present study was to evaluate the effect of 3D printed teeth and virtual simulation system on the pre-clinical access cavity preparation training of senior dental undergraduates.MethodsThe 3D printed teeth were manufactured based on the micro-CT data of an extracted lower first molar. Ninety-eight senior dental undergraduate students were required to finish the access cavity preparation of lower first molar within 20 min on plastic and 3D printed teeth on the manikin system as well as on a virtual simulation machine respectively with randomly selected sequences. Expert dentists scored the operated teeth. The scores from the virtual simulation system were also recorded. All the scores were analyzed and compared. Following the procedure, two questionnaires were sent to students to further evaluate the feelings and optimal training sequence.ResultsNo significant differences were found between plastic and 3D printed teeth scores, while virtual simulation achieved a valid/invalid area removal ratio of 96.86% ± 5.08% and 3.97% ± 1.85%, respectively. Most students found plastic teeth training the easiest and favored the three-training combination (36.36%). 71.42% of the students thought the virtual simulation training should be put at the first place of the three trainings. Over 80% of students agreed with incorporating 3D printed teeth and virtual simulation into their routine training courses. In addition, the general advantages and disadvantages of the virtual simulation system and 3D printed teeth training received almost equal recognition by students.ConclusionsVirtual simulation system training + plastic teeth training + 3D printed teeth training might be the optimal training sequence. Virtual simulation system training could not completely replace the traditional training methods on the manikin system at the moment. With further modifications, 3D printed teeth could be expected to replace the plastic teeth for the pre-clinical access cavity preparation training.

Effect of Strength and Endurance Training Sequence on Endurance Performance.

This review investigates the effect of two different concurrent training sequences on endurance performance. The sequences investigated are Endurance-Resistance (ER) and Resistance-Endurance (RE). A literature search is conducted of the SPORTDiscus and Medline databases. The included studies are randomized control trials, which compare the effect of ER and RE on at least one endurance performance variable. A PEDro scale is used to assess the methodological quality of the articles in this review. Of a total of 152 articles identified during the initial screening, 15 studies meet the inclusion criteria. These studies include 426 participants (298 males and 128 females), with 212 of the participants training with ER and 214 with RE. The results are presented as the percentage change of the mean from pre- to post-test. All the studies show an improvement in endurance from pre to post for both interventions, except for the RE group in one study. This review finds small and non-conclusive sequence effects between ER and RE, suggesting that the sequence of concurrent training is not of great importance in relation to endurance performance.

A Subspace-Based Frequency Synchronization Algorithm for Multicarrier Communication Systems

We present a subspace-based polynomial rooting algorithm to estimate the frequency bias (FB) of generalized frequency division multiplexing (GFDM) systems employing null subcarriers and repetitive sub-symbols. The estimation process is classified into fractional FB (FFB) and integer FB (IFB) estimation. The use of repetitive sub-symbols creates a quasi-periodic structure in the FB-distorted received signal, allowing the proposed algorithm to estimate the FFB using the root-MUSIC algorithm. Based on this, the proposed algorithm compensates for the FFB in the received signal and then estimates the null subcarrier pattern (NSP) in the frequency domain. As a result, the IFB estimate can be obtained in a maximum likelihood (ML) manner. Before the NSP estimation, this study uses a sub-symbol combiner to enhance signal strength of the FFB-aligned signal, ensuring the reliability of the IFB estimate. Computer simulations show that the proposed subspace-based algorithm has several advantages over traditional FB estimation methods: 1. Unlike some existing algorithms that use a training sequence to estimate FB, the proposed approach is a semi-blind algorithm because it can deliver information through repeated sub-symbols while estimating FB; 2. The proposed algorithm demonstrates excellent estimation accuracy compared to most traditional FB estimation algorithms; and 3. The proposed algorithm is computationally efficient, making it applicable to real-time applications in future communication systems.

Crossover effect of knee and ankle joint training on knee mechanics after ACL reconstruction: A randomized controlled trial

BackgroundAnterior cruciate ligament (ACL) rehabilitation is a common intervention after ACL reconstruction. Since different types of exercise can influence muscle and kinematic parameters in diverse ways, the training order between the knee and ankle joints may also change gait parameters. PurposeThis study aimed to investigate whether the training sequence of the knee and ankle joints (knee followed by ankle training or vice-versa) in an ACL reconstruction (ACLR) rehabilitation program has any effects on knee extension and flexion torques. MethodsForty-two men (aged 20–30 years) with ACLR participated in this study. They were randomly allocated to receive one of two interventions: (A) knee joint training followed by ankle training or (B) ankle joint training followed by knee training. After five weeks (four weeks of intervention and one-week washout), participants crossed from one group to another for an additional four weeks. Knee extension and flexion torques were assessed during the stance phase of the gait cycle before and after the intervention program. ResultsTwo-way Mixed-design MANOVA showed that knee extension torque improved significantly in both groups after training (p = 0.001, Cohen’s D = 0.65), while the knee flexion torque increased significantly only in group B (p= 0.001, Cohen’s D = 0.97). When comparing both groups, patients of group B presented significant improvements in the post-training mean values of all tested variables compared with group A. ConclusionStarting a post-ACLR rehabilitation program with ankle training followed by knee training is better to improve knee flexion and extension torques during the stance phase of the gait cycle than starting the program by training the knee first, followed by the ankle. Future studies using a mixed-gender sample and different types of ACLR operations are necessary to examine whether similar improvements will happen as well as to test their effects on many sports activities.

A Long Short-Term Memory Neural Network Algorithm for Data-Driven Spatial Load Forecasting

Based on the LSTM neural network, the author proposes a new data-driven spatial load prediction method to analyze the time series within the neural network, avoid data depression, and determine the correlation of the training data space. Establish prediction models based on different neurons, reduce the dimensionality of collected data through data preprocessing, and ensure data integrity. At the same time, provide data management base, control model input and output, unify process model, ensure training sequence model, combine LSTM neural network model, select prediction method, and finish data-driven related transportation. Experimental results show that the data driven global load forecasting model based on LSTM neural network proposed in this paper takes 1.23 seconds to complete 8000 training data, when traditional data drive spatial load forecasting method based on CNN neural network takes 3.56 seconds to finish 8000 training data. It can be seen that the prediction method proposed in this article has a good prediction accuracy.

StackedEnC-AOP: prediction of antioxidant proteins using transform evolutionary and sequential features based multi-scale vector with stacked ensemble learning

BackgroundAntioxidant proteins are involved in several biological processes and can protect DNA and cells from the damage of free radicals. These proteins regulate the body's oxidative stress and perform a significant role in many antioxidant-based drugs. The current invitro-based medications are costly, time-consuming, and unable to efficiently screen and identify the targeted motif of antioxidant proteins.MethodsIn this model, we proposed an accurate prediction method to discriminate antioxidant proteins namely StackedEnC-AOP. The training sequences are formulation encoded via incorporating a discrete wavelet transform (DWT) into the evolutionary matrix to decompose the PSSM-based images via two levels of DWT to form a Pseudo position-specific scoring matrix (PsePSSM-DWT) based embedded vector. Additionally, the Evolutionary difference formula and composite physiochemical properties methods are also employed to collect the structural and sequential descriptors. Then the combined vector of sequential features, evolutionary descriptors, and physiochemical properties is produced to cover the flaws of individual encoding schemes. To reduce the computational cost of the combined features vector, the optimal features are chosen using Minimum redundancy and maximum relevance (mRMR). The optimal feature vector is trained using a stacking-based ensemble meta-model.ResultsOur developed StackedEnC-AOP method reported a prediction accuracy of 98.40% and an AUC of 0.99 via training sequences. To evaluate model validation, the StackedEnC-AOP training model using an independent set achieved an accuracy of 96.92% and an AUC of 0.98.ConclusionOur proposed StackedEnC-AOP strategy performed significantly better than current computational models with a ~ 5% and ~ 3% improved accuracy via training and independent sets, respectively. The efficacy and consistency of our proposed StackedEnC-AOP make it a valuable tool for data scientists and can execute a key role in research academia and drug design.

Impact of concurrent training sequence on heart rate variability, glycemic control, body composition, lipid profile, and cardiorespiratory fitness in type 2 diabetes patients with cardiac autonomic neuropathy: A randomized controlled trial

BackgroundType 2 Diabetes Mellitus (T2DM) is a global health concern, with cardiac autonomic neuropathy (CAN) being a significant complication that exacerbates cardiovascular risks. Aerobic and resistance exercises are recognized for their benefits in managing T2DM, but the optimal integration of these modalities, especially for patients with T2DM, requires further exploration. ObjectiveTo investigate the effects of the sequence of aerobic and resistance training in a concurrent training regimen on heart rate variability (HRV), glycemic control, body composition, lipid profile, and cardiorespiratory fitness (CRF) in patients with T2DM. MethodsIn this randomized controlled trial, 45 T2DM patients with CAN were allocated to three groups: a control group, an aerobic then resistance training (ART) group, and a resistance then aerobic training (RAT) group. Measurements were taken at baseline and after a 13-week intervention, assessing HRV, glycemic control, body composition, lipid profile, and CRF. ResultsBoth ART and RAT groups showed significant improvements in HRV, glycemic control, body composition, lipid profile, and CRF compared to the control group. Notably, there were no significant differences between ART and RAT groups in these outcomes, suggesting that the sequence of aerobic and resistance exercises in concurrent training does not significantly affect the health benefits attained. ConclusionConcurrent aerobic and resistance training, irrespective of the sequence, effectively improves HRV, glycemic control, body composition, lipid profile, and CRF in T2DM patients with CAN. This study supports the inclusion of concurrent training in exercise prescriptions for managing T2DM and its complications.

Integrative effects of resistance training and endurance training on mitochondrial remodeling in skeletal muscle.

Resistance training activates mammalian target of rapamycin (mTOR) pathway of hypertrophy for strength gain, while endurance training increases peroxisome proliferator-activated receptor γ coactivator 1α (PGC-1α) pathway of mitochondrial biogenesis benefiting oxidative phosphorylation. The conventional view suggests that resistance training-induced hypertrophy signaling interferes with endurance training-induced mitochondrial remodeling. However, this idea has been challenged because acute leg press and knee extension in humans enhance both muscle hypertrophy and mitochondrial remodeling signals. Thus, we first examined the muscle mitochondrial remodeling and hypertrophy signals with endurance training and resistance training, respectively. In addition, we discussed the influence of resistance training on muscle mitochondria, demonstrating that the PGC-1α-mediated muscle mitochondrial adaptation and hypertrophy occur simultaneously. The second aim was to discuss the integrative effects of concurrent training, which consists of endurance and resistance training sessions on mitochondrial remodeling. The study found that the resistance training component does not reduce muscle mitochondrial remodeling signals in concurrent training. On the contrary, concurrent training has the potential to amplify skeletal muscle mitochondrial biogenesis compared to a single exercise model. Concurrent training involving differential sequences of resistance and endurance training may result in varied mitochondrial biogenesis signals, which should be linked to the pre-activation of mTOR or PGC-1α signaling. Our review proposed a mechanism for mTOR signaling that promotes PGC-1α signaling through unidentified pathways. This mechanism may be account for the superior muscle mitochondrial remodeling change following the concurrent training. Our review suggested an interaction between resistance training and endurance training in skeletal muscle mitochondrial adaptation.