Kinesitherapy for Knee Osteoarthritis Patients Physical and Psychological Health Based on "Traditional Chinese Exercise" Management Modalities: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.

Traditional Chinese exercise ("TCE" management modalities), including but not limited to Tai Chi, Baduanjin, and Yijinjing, has a good effect on improving the physical function of patients with knee osteoarthritis, but less attention has been paid to the impact on the psychological health of patients, and currently there is insufficient evidence to support it. We conducted this study to provide a systematic synthesis of best evidence regarding the physical and mental health of patients with knee osteoarthritis treated by traditional Chinese exercise. Literature on the effectiveness of traditional Chinese exercise (Tai Chi, Baduanjin, Yijinjing, Qigong, etc.) versus conventional therapy (muscle-strength training of the lower extremity and aerobic training, wellness education, quadriceps strengthening exercises, etc.) on Western Ontario and McMaster Universities Arthritis Index (WOMAC), visual analog scale (VAS), Short Form-36 (SF-36), Timed Up and Go Test (TUG), and Berg Balance Scale (BBS) in knee osteoarthritis (KOA) from Pubmed, Web of Science, Ovid Technologies, China National Knowledge Infrastructure (CNKI), Chinese Science and Technology Periodical Database (VIP), Wanfang Database, and SinoMed were collected from their inception to April 2022. Thirty-three studies with 2621 cases were included in this study. The study's results indicated that compared with conventional therapy, traditional Chinese exercise had more advantages on patients' WOMAC score, significantly reducing patients' overall WOMAC score (SMD = -0.99; 95% CI: -1.38, -0.60; p < 0.00001) and relieving pain (SMD = -0.76; 95% CI: -1.11, -0.40; p < 0.0001) in patients with KOA. It also has advantages over conventional therapy in improving mental component score (MCS) (SMD = 0.32; 95% CI: -0.00, 0.65; p = 0.05) and physical component score (PCS) (SMD = 0.34; 95% CI: 0.05, 0.62; p = 0.02). Compared with conventional therapy, traditional Chinese exercise can significantly reduce the effect on timed up and go test (TUG) score (SMD = -0.30; 95% CI: -0.50, -0.11; p = 0.002), beck depression inventory (DBI) score (SMD = -0.62; 95% CI: -1.03, -0.22; p = 0.002), and increase the impact on Berg Balance Scale (BBS) score (SMD = 0.60; 95% CI: 0.37, 0.83; p < 0.00001). The findings of this study indicated that traditional Chinese exercise improved body function and mental health in patients with knee osteoarthritis significantly. More high-quality clinical evidence-based data was needed to confirm the therapeutic effect of traditional Chinese exercise on the physical and mental health in KOA patients.

Identification of membrane protein types via deep residual hypergraph neural network.

A membrane protein's functions are significantly associated with its type, so it is crucial to identify the types of membrane proteins. Conventional computational methods for identifying the species of membrane proteins tend to ignore two issues: High-order correlation among membrane proteins and the scenarios of multi-modal representations of membrane proteins, which leads to information loss. To tackle those two issues, we proposed a deep residual hypergraph neural network (DRHGNN), which enhances the hypergraph neural network (HGNN) with initial residual and identity mapping in this paper. We carried out extensive experiments on four benchmark datasets of membrane proteins. In the meantime, we compared the DRHGNN with recently developed advanced methods. Experimental results showed the better performance of DRHGNN on the membrane protein classification task on four datasets. Experiments also showed that DRHGNN can handle the over-smoothing issue with the increase of the number of model layers compared with HGNN. The code is available at https://github.com/yunfighting/Identification-of-Membrane-Protein-Types-via-deep-residual-hypergraph-neural-network.

Application of the cortical bone trajectory technique in posterior lumbar fixation.

The cortical bone trajectory (CBT) is a novel technique in lumbar fixation and fusion. The unique caudocephalad and medial-lateral screw trajectories endow it with excellent screw purchase for vertebral fixation via a minimally invasive method. The combined use of CBT screws with transforaminal or posterior lumbar interbody fusion can treat a variety of lumbar diseases, including spondylolisthesis or stenosis, and can also be used as a remedy for revision surgery when the pedicle screw fails. CBT has obvious advantages in terms of surgical trauma, postoperative recovery, prevention and treatment of adjacent vertebral disease, and the surgical treatment of obese and osteoporosis patients. However, the concept of CBT internal fixation technology appeared relatively recently; consequently, there are few relevant clinical studies, and the long-term clinical efficacy and related complications have not been reported. Therefore, large sample and prospective studies are needed to further reveal the long-term complications and fusion rate. As a supplement to the traditional pedicle trajectory fixation technique, the CBT technique is a good choice for the treatment of lumbar diseases with accurate screw placement and strict indications and is thus deserving of clinical recommendation.

Research on DNA-Binding Protein Identification Method Based on LSTM-CNN Feature Fusion.

Protein is closely related to life activities. As a kind of protein, DNA-binding protein plays an irreplaceable role in life activities. Therefore, it is very important to study DNA-binding protein, which is a subject worthy of study. Although traditional biotechnology has high precision, its cost and efficiency are increasingly unable to meet the needs of modern society. Machine learning methods can make up for the deficiencies of biological experimental techniques to a certain extent, but they are not as simple and fast as deep learning for data processing. In this paper, a deep learning framework based on parallel long and short-term memory(LSTM) and convolutional neural networks(CNN) was proposed to identify DNA-binding protein. This model can not only further extract the information and features of protein sequences, but also the features of evolutionary information. Finally, the two features are combined for training and testing. On the PDB2272 dataset, compared with PDBP_Fusion model, Accuracy(ACC) and Matthew's Correlation Coefficient (MCC) increased by 3.82% and 7.98% respectively. The experimental results of this model have certain advantages.

Application of DNA-Binding Protein Prediction Based on Graph Convolutional Network and Contact Map.

DNA contains the genetic information for the synthesis of proteins and RNA, and it is an indispensable substance in living organisms. DNA-binding proteins are an enzyme, which can bind with DNA to produce complex proteins, and play an important role in the functions of a variety of biological molecules. With the continuous development of deep learning, the introduction of deep learning into DNA-binding proteins for prediction is conducive to improving the speed and accuracy of DNA-binding protein recognition. In this study, the features and structures of proteins were used to obtain their representations through graph convolutional networks. A protein prediction model based on graph convolutional network and contact map was proposed. The method had some advantages by testing various indexes of PDB14189 and PDB2272 on the benchmark dataset.

G Protein-Coupled Receptor Interaction Prediction Based on Deep Transfer Learning.

G protein-coupled receptors (GPCRs) account for about 40% to 50% of drug targets. Many human diseases are related to G protein coupled receptors. Accurate prediction of GPCR interaction is not only essential to understand its structural role, but also helps design more effective drugs. At present, the prediction of GPCR interaction mainly uses machine learning methods. Machine learning methods generally require a large number of independent and identically distributed samples to achieve good results. However, the number of available GPCR samples that have been marked is scarce. Transfer learning has a strong advantage in dealing with such small sample problems. Therefore, this paper proposes a transfer learning method based on sample similarity, using XGBoost as a weak classifier and using the TrAdaBoost algorithm based on JS divergence for data weight initialization to transfer samples to construct a data set. After that, the deep neural network based on the attention mechanism is used for model training. The existing GPCR is used for prediction. In short-distance contact prediction, the accuracy of our method is 0.26 higher than similar methods.

Lymphocyte subsets as a predictor of severity and prognosis in COVID-19 patients.

BACKGROUND: Coronavirus disease 2019 (COVID-19) had become a worldwide health threat. Early prediction of the severity of COVID-19 patients was important for reducing death rate and controlling this disease. METHODS AND MATERIALS: A total of 301 patients confirmed with COVID-19 in Wuhan from 8 February to 10 April 2020 were included. Clinical data were collected and analyzed. Diagnostic and prognostic utility of blood cell counts and lymphocyte subsets in COVID-19 patients were investigated. The receiver operator characteristic curve (ROC) was used in discriminating the mild and severe/critical cases. RESULTS: There were difference in blood cell counts and lymphocyte subsets among mild, severe and critical patients, which were also influenced by comorbidities and duration of disease. The area under the ROC of lymphocyte, CD3+ T cells, CD4+ T cells, and CD8+ T cells were 0.718, 0.721, 0.718, and 0.670, which were higher than that of other hematological parameters. The optimal threshold was 1205, 691, 402, and 177 per µl, respectively. Patients with higher counts of lymphocyte, CD3+ T cells, CD4+ T cells, or CD8+ T cells were correlated with shorter length of stay in hospital (p < 0.05). Multivariable Cox regression analysis showed disease severity, CD3+ T cells counts and time when the nucleic acid turned negative were independent risk factors for in-hospital death of COVID-19 patients (p < 0.05). CONCLUSION: Blood cell counts and lymphocyte subsets correlated with severity of COVID-19.

Research on RNA secondary structure predicting via bidirectional recurrent neural network.

BACKGROUND: RNA secondary structure prediction is an important research content in the field of biological information. Predicting RNA secondary structure with pseudoknots has been proved to be an NP-hard problem. Traditional machine learning methods can not effectively apply protein sequence information with different sequence lengths to the prediction process due to the constraint of the self model when predicting the RNA secondary structure. In addition, there is a large difference between the number of paired bases and the number of unpaired bases in the RNA sequences, which means the problem of positive and negative sample imbalance is easy to make the model fall into a local optimum. To solve the above problems, this paper proposes a variable-length dynamic bidirectional Gated Recurrent Unit(VLDB GRU) model. The model can accept sequences with different lengths through the introduction of flag vector. The model can also make full use of the base information before and after the predicted base and can avoid losing part of the information due to truncation. Introducing a weight vector to predict the RNA training set by dynamically adjusting each base loss function solves the problem of balanced sample imbalance. RESULTS: The algorithm proposed in this paper is compared with the existing algorithms on five representative subsets of the data set RNA STRAND. The experimental results show that the accuracy and Matthews correlation coefficient of the method are improved by 4.7% and 11.4%, respectively. CONCLUSIONS: The flag vector introduced allows the model to effectively use the information before and after the protein sequence; the introduced weight vector solves the problem of unbalanced sample balance. Compared with other algorithms, the LVDB GRU algorithm proposed in this paper has the best detection results.

Epidural gas-containing pseudocyst leading to lumbar radiculopathy: A case report.

BACKGROUND: Lumbar radiculopathy is a common symptom in the clinic and is often caused by lumbar disc herniation or osteophytes compressing the nerve root; however, it is rare for nerve roots to be compressed by epidural gas. Few symptomatic epidural gas-containing pseudocyst cases have been reported. Furthermore, the reported cases were due to a mix of gas and obvious osteophytes; therefore, it was hard to rigorously conclude that gas was the factor responsible for radiculopathy. We provide evidence that because no epidural gas accumulated before radiculopathy occurred and the symptoms were relieved after removal of the gas, the epidural gas-containing pseudocyst was the root cause of radiculopathy in this case. CASE SUMMARY: An 87-year-old man with a 3-wk history of right radiating pain was admitted to our hospital. Computed tomography (CT) and magnetic resonance imaging (MRI) examinations showed a vacuum phenomenon and huge lesions with low signal intensity located in the same area where the pain occurred. After carefully checking the images acquired in the last 3 mo, we found an abdominal CT examination performed 40 d prior because of abdominal pain. The CT images showed no gas-containing pseudocyst in the epidural space and notably, he had no leg pain at the time. To ensure a low-intensity intervention and complete decompression of the nerve, percutaneous endoscopic lumbar nerve decompression surgery was advised. A gas-containing pseudocyst was identified under endoscopy. The symptoms were relieved after surgery, and the postoperative images showed total disappearance of the vacuum phenomenon and lesions with low signal intensity on CT and MRI. Histological examination showed that the sampled gas-containing pseudocyst tissue was fibrous connective tissue. CONCLUSION: This case thoroughly illustrates that an epidural gas-containing pseudocyst can result in radiculopathic pain through a comprehensive evidence chain. Percutaneous endoscopic decompression is a minimally invasive and effective treatment method.

A Three-in-One Strategy: Injectable Biomimetic Porous Hydrogels for Accelerating Bone Regeneration via Shape-Adaptable Scaffolds, Controllable Magnesium Ion Release, and Enhanced Osteogenic Differentiation.

The repair of bone defects with irregular shapes, particularly in a minimally invasive manner, remains a major challenge. For synthetic bone grafts, injectable hydrogels are superior to conventional scaffolds because they can adapt satisfactorily to the defect margins and can be injected into deeper areas of injury via a minimally invasive procedure. Based on the poly(lactide-co-glycolide)(PLGA)/1-methyl-2-pyrrolidinone solution reported in our previous study, we successfully synthesized injectable MgO/MgCO3@PLGA (PMM) hydrogels, namely, injectable biomimetic porous hydrogels (IBPHs), to accelerate bone regeneration. In addition to exhibiting excellent injectability, PMM hydrogels could transform into porous scaffolds in situ through a liquid-to-solid phase transition and completely fill irregular bone defects via their superb shape adaptability. Moreover, sustainable and steady release of Mg2+ was achieved by regulating the weight ratio of the incorporated MgO and MgCO3 particles. Via controlled release of Mg2+, PMM hydrogels significantly promoted proliferation, osteogenic differentiation, migration, and biomineral deposition of immortalized mouse embryonic fibroblasts. More importantly, micro-CT imaging and histological analysis indicated that concomitant with their gradual degradation, PMM hydrogels effectively stimulated in situ bone regeneration in rat calvarial defects with an increase in the bone volume fraction of almost 2-fold compared with that in the control group. These findings suggest that injectable PMM hydrogels can satisfactorily match bone defects and form porous scaffolds in situ and can significantly promote bone regeneration via controllable Mg2+ release. The remarkable features of IPBHs may open a new avenue for the exploration of in situ repair systems for irregular bone defects to accelerate bone regeneration and have great potential for clinical translation.

Identifying Membrane Protein Types Based on Lifelong Learning With Dynamically Scalable Networks.

Membrane proteins are an essential part of the body's ability to maintain normal life activities. Further research into membrane proteins, which are present in all aspects of life science research, will help to advance the development of cells and drugs. The current methods for predicting proteins are usually based on machine learning, but further improvements in prediction effectiveness and accuracy are needed. In this paper, we propose a dynamic deep network architecture based on lifelong learning in order to use computers to classify membrane proteins more effectively. The model extends the application area of lifelong learning and provides new ideas for multiple classification problems in bioinformatics. To demonstrate the performance of our model, we conducted experiments on top of two datasets and compared them with other classification methods. The results show that our model achieves high accuracy (95.3 and 93.5%) on benchmark datasets and is more effective compared to other methods.

Empirical Potential Energy Function Toward ab Initio Folding G Protein-Coupled Receptors.

Approximately 40-50 percent of all drugs targets are G protein-coupled receptors (GPCRs). Three-dimensional structure of GPCRs is important to probe their biophysical and biochemical functions and their pharmaceutical applications. Lacking reliable and high quality free function is one of the ugent problems of computational predicting the three-dimensional structure in this community. We proposed a GPCR-specified energy function composed of four novel empirical potential energy terms: a two-dimensional contact energy force field, knowledge-based helix pair connection distance energy term, knowledge-based helix pair angle restraint energy term and a disulfide bond energy term. To validate the energy function, we employed an ab initio GPCR three-dimensional structure predictor to test if the energy function improved the accuracy of prediction. We evaluated 28 solved GPCRs and found that 21(75 percent) targets were correctly folded (TM-score>0.5). Also, the average TM-score using the energy function was 0.54, which was improved 134 percent than the TM-score 0.23 for MODELLER energy function and 170 percent than the TM-score 0.20 for Rosetta membrane energy function. The results confirmed that our empirical potential energy function toward ab initio folding is competitive to state-of-the-art solutions for structural prediction of GPCRs.

Analysis of the Point Prevalence and Influencing Factors of Acute Stress Disorder in Elderly Patients with Osteoporotic Fractures.

BACKGROUND: Increasing attention has been paid to posttraumatic affective disorders. However, orthopedic surgeons dealing with trauma often ignore the harm of such diseases. OBJECTIVE: To investigate the point prevalence and influencing factors of acute stress disorder (ASD) in elderly patients with osteoporotic fractures (EPOFs) from the perspective of orthopedic surgeons. PATIENTS AND METHODS: A total of 595 cases of EPOFs were treated at our hospital from January 1, 2018, to June 30, 2019. The patients meeting our inclusion criteria were assessed using a structured interview based on the fifth edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM-V) criteria to verify the presence of ASD. After diagnosis, the participants were divided into two groups (those with and without ASD). The sociodemographic characteristics, disease characteristics, and Social Support Rating Scale (SSRS) scores were assessed. The chi-square test was used for univariate analysis, and multivariate analysis was performed using binary logistic regression. RESULTS: Of the 524 participants, 32 (6.1%) met the criteria for the diagnosis of ASD. The results of the univariate analysis showed that gender, personality, living alone, monthly family income, initial fear, poor prognosis expectation, anxiety/depression, pain, and social support were associated with ASD in EPOFs (P<0.05). The multivariate regression analysis showed that isolation, low monthly family income, introversion, poor prognosis expectation, previous traumatic history, and intense pain were the main influencing factors and risk factors (OR>1) for ASD in EPOFs. CONCLUSION: Being female, living alone, introversion, poor family income, intense initial fear, poor prognosis expectation, anxiety/depression, intense pain perception and low social support were significantly related to the occurrence of ASD in EPOFs. To achieve optimal recovery in EPOFs, orthopedic surgeons should meet both the physiological and psychological needs of the patients.

Posterior Percutaneous Transpedicular Endoscopic Approach for Treating Single-Segment Cervical Myelopathy.

BACKGROUND: Standard posterior percutaneous endoscopic cervical discectomy (PECD) is considered an effective minimally invasive surgery. Although standard PECD can be used to treat radiculopathy with relatively minimal trauma, it is still a challenge to use this approach for treating myelopathy. OBJECTIVE: This report is aimed at first describing a posterior transpedicular approach under endoscopy for myelopathy and evaluating the feasibility and short-term clinical effects of this approach. METHODS: In our retrospective analysis between Feb. 2016 to Mar. 2017, 16 patients managed with PECD using the posterior transpedicular approach for symptomatic single-segment myelopathy. Surgery involved drilling 1/2 to 2/3 of the medial portion of the pedicle under endoscopy to provide sufficient space and an appropriate angle for inserting the endoscope into the spinal canal, followed by ventral decompression of the spinal cord. Computed tomography and magnetic resonance imaging were used to evaluate pedicle healing and spinal cord decompression. The primary outcomes included a visual analog scale (VAS) scores of axial neck pain and Japanese Orthopaedic Association (JOA) scores of neurological conditions. RESULTS: All patients completed a 1-year follow-up examination. The mean duration of surgery was 95.44 ± 19.44 min (52-130 min). The fluoroscopy duration was 5.88 ± 1.05 (4-7). The VAS scores of axial pain significantly improved from 6.94 ± 0.75 preoperatively to 2.88 ± 1.22 postoperatively (P < 0.05). The mean JOA scores improved from 8.50 ± 1.12 preoperatively to 14.50 ± 1.46 at the final follow-up (P < 0.05). The effects were excellent in 8 cases, good in 6 cases, and fair in 2 cases. After partial pedicle excision, the width of the remaining pedicle was 1.70 ± 0.22 mm postoperatively and significantly recovered to 3.38 ± 0.49 mm at the 1-year follow-up. There were no surgery-related complications, such as dural tearing, spinal cord injury, nerve root injury, pedicle fracture, and cervical hematocele or infection. CONCLUSIONS: The posterior transpedicular approach is an effective method for the treatment of myelopathy in select patients and is a supplement to the described surgical approach for PECD.

Effect of Zhongyi paste on inflammatory pain in mice by regulation of the extracellular regulated protein kinases 1/2-cyclooxygenase-2-prostaglandin E2 pathway.

BACKGROUND: Zhongyi paste is a traditional Chinese medicine herbal paste that is externally applied to reduce inflammation and relieve pain. METHODS: An acute foot swelling inflammation model in C57BL/6J mice was established by carrageenan-induced pathogenesis. Zhongyi paste raised the pain threshold and also reduced the degree of swelling in mice with carrageenan-induced foot swelling. RESULTS: Analysis indicated that serum tumor necrosis factor-alpha, interleukin-1 beta, and prostaglandin E2 (PGE2) cytokine levels and PGE2 levels in the paw tissue of the mice were decreased by Zhongyi paste treatment. The quantitative polymerase chain reaction and western blot results showed that Zhongyi paste downregulated the mRNA and protein expression of extracellular signal-regulated kinase 1/2 (ERK1/2), and cyclooxygenase-2 (COX-2), and also downregulated the mRNA expression of PGE2. At the same time, the Zhongyi paste exerted a stronger effect as an external drug than that of indomethacin, which is an oral drug, and voltaren, which is an externally applied drug. CONCLUSIONS: Our results indicated that Zhongyi paste is a very effective drug to reduce inflammatory swelling of the foot, and its mechanism of action is related to regulation of the ERK1/2-COX-2-PGE2 pathway.

Use Chou's 5-Step Rule to Predict DNA-Binding Proteins with Evolutionary Information.

The knowledge of DNA-binding proteins would help to understand the functions of proteins better in cellular biological processes. Research on the prediction of DNA-binding proteins can promote the research of drug proteins and computer acidified drugs. In recent years, methods based on machine learning are usually used to predict proteins. Although great predicted performance can be achieved via current methods, researchers still need to invest more research in terms of the improvement of predicted performance. In this study, the prediction of DNA-binding proteins is studied from the perspective of evolutionary information and the support vector machine method. One machine learning model for predicting DNA-binding proteins based on evolutionary features by using Chou's 5-step rule is put forward. The results show that great predicted performance is obtained on benchmark dataset PDB1075 and independent dataset PDB186, achieving the accuracy of 86.05% and 75.30%, respectively. Thus, the method proposed is comparable to a certain degree, and it may work even better than other methods to some extent.

Ranking near-native candidate protein structures via random forest classification.

BACKGROUND: In ab initio protein-structure predictions, a large set of structural decoys are often generated, with the requirement to select best five or three candidates from the decoys. The clustered central structures with the most number of neighbors are frequently regarded as the near-native protein structures with the lowest free energy; however, limitations in clustering methods and three-dimensional structural-distance assessments make identifying exact order of the best five or three near-native candidate structures difficult. RESULTS: To address this issue, we propose a method that re-ranks the candidate structures via random forest classification using intra- and inter-cluster features from the results of the clustering. Comparative analysis indicated that our method was better able to identify the order of the candidate structures as comparing with current methods SPICKR, Calibur, and Durandal. The results confirmed that the identification of the first model were closer to the native structure in 12 of 43 cases versus four for SPICKER, and the same as the native structure in up to 27 of 43 cases versus 14 for Calibur and up to eight of 43 cases versus two for Durandal. CONCLUSIONS: In this study, we presented an improved method based on random forest classification to transform the problem of re-ranking the candidate structures by an binary classification. Our results indicate that this method is a powerful method for the problem and the effect of this method is better than other methods.

Predicting RNA secondary structure via adaptive deep recurrent neural networks with energy-based filter.

BACKGROUND: RNA secondary structure prediction is an important issue in structural bioinformatics, and RNA pseudoknotted secondary structure prediction represents an NP-hard problem. Recently, many different machine-learning methods, Markov models, and neural networks have been employed for this problem, with encouraging results regarding their predictive accuracy; however, their performances are usually limited by the requirements of the learning model and over-fitting, which requires use of a fixed number of training features. Because most natural biological sequences have variable lengths, the sequences have to be truncated before the features are employed by the learning model, which not only leads to the loss of information but also destroys biological-sequence integrity. RESULTS: To address this problem, we propose an adaptive sequence length based on deep-learning model and integrate an energy-based filter to remove the over-fitting base pairs. CONCLUSIONS: Comparative experiments conducted on an authoritative dataset RNA STRAND (RNA secondary STRucture and statistical Analysis Database) revealed a 12% higher accuracy relative to three currently used methods.

Research on predicting 2D-HP protein folding using reinforcement learning with full state space.

BACKGROUND: Protein structure prediction has always been an important issue in bioinformatics. Prediction of the two-dimensional structure of proteins based on the hydrophobic polarity model is a typical non-deterministic polynomial hard problem. Currently reported hydrophobic polarity model optimization methods, greedy method, brute-force method, and genetic algorithm usually cannot converge robustly to the lowest energy conformations. Reinforcement learning with the advantages of continuous Markov optimal decision-making and maximizing global cumulative return is especially suitable for solving global optimization problems of biological sequences. RESULTS: In this study, we proposed a novel hydrophobic polarity model optimization method derived from reinforcement learning which structured the full state space, and designed an energy-based reward function and a rigid overlap detection rule. To validate the performance, sixteen sequences were selected from the classical data set. The results indicated that reinforcement learning with full states successfully converged to the lowest energy conformations against all sequences, while the reinforcement learning with partial states folded 50% sequences to the lowest energy conformations. Reinforcement learning with full states hits the lowest energy on an average 5 times, which is 40 and 100% higher than the three and zero hit by the greedy algorithm and reinforcement learning with partial states respectively in the last 100 episodes. CONCLUSIONS: Our results indicate that reinforcement learning with full states is a powerful method for predicting two-dimensional hydrophobic-polarity protein structure. It has obvious competitive advantages compared with greedy algorithm and reinforcement learning with partial states.

Combined Application of Modified Three-Dimensional Printed Anatomic Templates and Customized Cutting Blocks in Pelvic Reconstruction After Pelvic Tumor Resection.

BACKGROUND: Common three-dimensional (3D)-printed anatomic templates have generally been used to reconstruct the pelvis after zone II and III borderline pelvic tumor resection. However, gradual increases in postoperative implant complications and the tumor recurrence rate have been observed. This study aimed to introduce the innovative application of a modified 3D-printed anatomic template with a customized cutting block for pelvic reconstruction and to comparatively analyze the common and modified 3D-printed anatomic templates. METHODS: A total of 38 patients were included in this study and were allocated to 2 groups (19 patients/group). Group A received innovative therapy, and Group B received traditional therapy. All patients were questioned in detail about age, location, and duration of the mass and associated symptoms, and routine blood tests, such as serological tests, were administered. RESULTS: We found that the modified 3D-printed anatomic template with a customized cutting block resulted in a shorter operating time, smaller bleeding loss, and simpler operation than the common 3D-printed anatomic template. Additionally, the tumor recurrence rate was lower and the accuracy of tumor resection was much greater for the modified 3D-printed anatomic template with a customized cutting block. However, compared with the traditional therapy, the innovative therapy had a significantly higher rate of implant loosening. CONCLUSION: The innovative therapy can increase surgical safety and reduce recurrence after tumor resection relative to the traditional therapy. Additionally, the innovative therapy reconstructs the pelvis of zone III to improve the quality of patient life. However, the innovative therapy with implant loosening should be improved.