Advancing Adverse Drug Reaction Prediction with Deep Chemical Language Model for Drug Safety Evaluation.

The accurate prediction of adverse drug reactions (ADRs) is essential for comprehensive drug safety evaluation. Pre-trained deep chemical language models have emerged as powerful tools capable of automatically learning molecular structural features from large-scale datasets, showing promising capabilities for the downstream prediction of molecular properties. However, the performance of pre-trained chemical language models in predicting ADRs, especially idiosyncratic ADRs induced by marketed drugs, remains largely unexplored. In this study, we propose MoLFormer-XL, a pre-trained model for encoding molecular features from canonical SMILES, in conjunction with a CNN-based model to predict drug-induced QT interval prolongation (DIQT), drug-induced teratogenicity (DIT), and drug-induced rhabdomyolysis (DIR). Our results demonstrate that the proposed model outperforms conventional models applied in previous studies for predicting DIQT, DIT, and DIR. Notably, an analysis of the learned linear attention maps highlights amines, alcohol, ethers, and aromatic halogen compounds as strongly associated with the three types of ADRs. These findings hold promise for enhancing drug discovery pipelines and reducing the drug attrition rate due to safety concerns.

Extend the benchmarking indel set by manual review using the individual cell line sequencing data from the Sequencing Quality Control 2 (SEQC2) project.

Accurate indel calling plays an important role in precision medicine. A benchmarking indel set is essential for thoroughly evaluating the indel calling performance of bioinformatics pipelines. A reference sample with a set of known-positive variants was developed in the FDA-led Sequencing Quality Control Phase 2 (SEQC2) project, but the known indels in the known-positive set were limited. This project sought to provide an enriched set of known indels that would be more translationally relevant by focusing on additional cancer related regions. A thorough manual review process completed by 42 reviewers, two advisors, and a judging panel of three researchers significantly enriched the known indel set by an additional 516 indels. The extended benchmarking indel set has a large range of variant allele frequencies (VAFs), with 87% of them having a VAF below 20% in reference Sample A. The reference Sample A and the indel set can be used for comprehensive benchmarking of indel calling across a wider range of VAF values in the lower range. Indel length was also variable, but the majority were under 10 base pairs (bps). Most of the indels were within coding regions, with the remainder in the gene regulatory regions. Although high confidence can be derived from the robust study design and meticulous human review, this extensive indel set has not undergone orthogonal validation. The extended benchmarking indel set, along with the indels in the previously published known-positive set, was the truth set used to benchmark indel calling pipelines in a community challenge hosted on the precisionFDA platform. This benchmarking indel set and reference samples can be utilized for a comprehensive evaluation of indel calling pipelines. Additionally, the insights and solutions obtained during the manual review process can aid in improving the performance of these pipelines.

Differentiation of epilepsy and psychogenic nonepileptic events based on body fluid characteristics.

OBJECTIVE: Differential diagnosis between epileptic seizures and psychogenic nonepileptic events (PNEEs) is a worldwide problem for neurologists. The present study aims to identify important characteristics from body fluid tests and develop diagnostic models based on them. METHODS: This is a register-based observational study in patients with a diagnosis of epilepsy or PNEEs at West China Hospital of Sichuan University. Data from body fluid tests between 2009 and 2019 were used as a training set. We constructed models with a random forest approach in eight training subsets divided by sex and categories of tests, including electrolyte, blood cell, metabolism, and urine tests. Then, we collected data prospectively from patients between 2020 and 2022 to validate our models and calculated the relative importance of characteristics in robust models. Selected characteristics were finally analyzed with multiple logistic regression to establish nomograms. RESULTS: A total of 388 patients, including 218 with epilepsy and 170 with PNEEs, were studied. The AUROCs of random forest models of electrolyte and urine tests in the validation phase achieved 80.0% and 79.0%, respectively. Carbon dioxide combining power, anion gap, potassium, calcium, and chlorine in electrolyte tests and specific gravity, pH, and conductivity in urine tests were selected for the logistic regression analysis. C (ROC) of the electrolyte and urine diagnostic nomograms achieved 0.79 and 0.85, respectively. SIGNIFICANCE: The application of routine indicators of serum and urine may help in the more accurate identification of epileptic and PNEEs.

Unraveling Structural Alerts in Marketed Drugs for Improving Adverse Outcome Pathway Framework of Drug-Induced QT Prolongation.

In pharmaceutical treatment, many non-cardiac drugs carry the risk of prolonging the QT interval, which can lead to fatal cardiac complications such as torsades de points (TdP). Although the unexpected blockade of ion channels has been widely considered to be one of the main reasons for affecting the repolarization phase of the cardiac action potential and leading to QT interval prolongation, the lack of knowledge regarding chemical structures in drugs that may induce the prolongation of the QT interval remains a barrier to further understanding the underlying mechanism and developing an effective prediction strategy. In this study, we thoroughly investigated the differences in chemical structures between QT-prolonging drugs and drugs with no drug-induced QT prolongation (DIQT) concerns, based on the Drug-Induced QT Prolongation Atlas (DIQTA) dataset. Three categories of structural alerts (SAs), namely amines, ethers, and aromatic compounds, appeared in large quantities in QT-prolonging drugs, but rarely in drugs with no DIQT concerns, indicating a close association between SAs and the risk of DIQT. Moreover, using the molecular descriptors associated with these three categories of SAs as features, the structure-activity relationship (SAR) model for predicting the high risk of inducing QT interval prolongation of marketed drugs achieved recall rates of 72.5% and 80.0% for the DIQTA dataset and the FDA Adverse Event Reporting System (FAERS) dataset, respectively. Our findings may promote a better understanding of the mechanism of DIQT and facilitate research on cardiac adverse drug reactions in drug development.

A pilot study on identifying gene signatures as markers for predicting patient response to antiseizure medications.

The majority of the biomarkers were associated with the diagnosis of epilepsy and few of them can be applied to predict the response to antiseizure medications (ASMs). In this study, we identified 26 significantly up-regulated genes and 32 down-regulated genes by comparing the gene expression profiles of patients with epilepsy that responded to valproate with those without applying any ASM. The results of gene set enrichment analysis indicated that the ferroptosis pathway was significantly impacted (p = 0.0087) in patients who responded to valproate. Interestingly, the gene NCOA4 in this pathway exhibited significantly different expression levels between the two groups, indicating that NCOA4 could serve as a potential biomarker to better understand the mechanism of valproate resistance. In addition, six up-regulated genes SF3A2, HMGN2, PABPN1, SSBP3, EFTUD2, and CREB3L2 as well as six down-regulated genes ZFP36L1, ACRC, SUB1, CALM2, TLK1, and STX2 also showed significantly different expression patterns between the two groups. Moreover, based on the gene expression profiles of the patients with the treatment of valproate, carbamazepine, and phenytoin, we proposed a strategy for predicting the response to the ASMs by using the Connectivity Map scoring method. Our findings could be helpful for better understanding the mechanisms of drug resistance of ASMs and improving the clinical treatment of epilepsy.

Structure-Activity Relationship (SAR) Model for Predicting Teratogenic Risk of Antiseizure Medications in Pregnancy by Using Support Vector Machine.

Teratogenicity is one of the main concerns in clinical medications of pregnant women. Prescription of antiseizure medications (ASMs) in women with epilepsy during pregnancy may cause teratogenic effects on the fetus. Although large scale epilepsy pregnancy registries played an important role in evaluating the teratogenic risk of ASMs, for most ASMs, especially the newly approved ones, the potential teratogenic risk cannot be effectively assessed due to the lack of evidence. In this study, the analyses are performed on any medication, with a focus on ASMs. We curated a list containing the drugs with potential teratogenicity based on the US Food and Drug Administration (FDA)-approved drug labeling, and established a support vector machine (SVM) model for detecting drugs with high teratogenic risk. The model was validated by using the post-marketing surveillance data from US FDA Spontaneous Adverse Events Reporting System (FAERS) and applied to the prediction of potential teratogenic risk of ASMs. Our results showed that our proposed model outperformed the state-of-art approaches, including logistic regression (LR), random forest (RF) and extreme gradient boosting (XGBoost), when detecting the high teratogenic risk of drugs (MCC and recall rate were 0.312 and 0.851, respectively). Among 196 drugs with teratogenic potential reported by FAERS, 136 (69.4%) drugs were correctly predicted. For the eight commonly used ASMs, 4 of them were predicted as high teratogenic risk drugs, including topiramate, phenobarbital, valproate and phenytoin (predicted probabilities of teratogenic risk were 0.69, 0.60 0.59, and 0.56, respectively), which were consistent with the statement in FDA-approved drug labeling and the high reported prevalence of teratogenicity in epilepsy pregnancy registries. In addition, the structural alerts in ASMs that related to the genotoxic carcinogenicity and mutagenicity, idiosyncratic adverse reaction, potential electrophilic agents and endocrine disruption were identified and discussed. Our findings can be a good complementary for the teratogenic risk assessment in drug development and facilitate the determination of pharmacological therapies during pregnancy.

Raman Spectroscopy: A Potential Diagnostic Tool for Oral Diseases.

Oral diseases impose a major health burden worldwide and have a profound effect on general health. Dental caries, periodontal diseases, and oral cancers are the most common oral health conditions. Their occurrence and development are related to oral microbes, and effective measures for their prevention and the promotion of oral health are urgently needed. Raman spectroscopy detects molecular vibration information by collecting inelastic scattering light, allowing a "fingerprint" of a sample to be acquired. It provides the advantages of rapid, sensitive, accurate, and minimally invasive detection as well as minimal interference from water in the "fingerprint region." Owing to these characteristics, Raman spectroscopy has been used in medical detection in various fields to assist diagnosis and evaluate prognosis, such as detecting and differentiating between bacteria or between neoplastic and normal brain tissues. Many oral diseases are related to oral microbial dysbiosis, and their lesions differ from normal tissues in essential components. The colonization of keystone pathogens, such as Porphyromonas gingivalis, resulting in microbial dysbiosis in subgingival plaque, is the main cause of periodontitis. Moreover, the components in gingival crevicular fluid, such as infiltrating inflammatory cells and tissue degradation products, are markedly different between individuals with and without periodontitis. Regarding dental caries, the compositions of decayed teeth are transformed, accompanied by an increase in acid-producing bacteria. In oral cancers, the compositions and structures of lesions and normal tissues are different. Thus, the changes in bacteria and the components of saliva and tissue can be used in examinations as special markers for these oral diseases, and Raman spectroscopy has been acknowledged as a promising measure for detecting these markers. This review summarizes and discusses key research and remaining problems in this area. Based on this, suggestions for further study are proposed.

Drug-induced QT Prolongation Atlas (DIQTA) for enhancing cardiotoxicity management.

Drug-induced prolongation of the QT interval is common in a variety of pharmaceutical treatments and can lead to serious clinical outcomes. Although substantial efforts have been made to prevent drug-induced QT interval prolongation, the lack of a centralized data source remains the main obstacle to further study of the underlying mechanism and the development of effective prediction strategies. To fill this gap, we propose a schema for stratifying the risk of marketed QT prolonging drugs based on US Food and Drug Administration (FDA)-approved drug labeling and developed a Drug-Induced QT Prolongation Atlas (DIQTA). Potential application of DIQTA was shown by precision dosing in off-label use and therapeutic strategy optimization, as well as the facilitation of artificial intelligence (AI)-based modeling in predictive toxicity.

Comprehensive Risk Assessment of Applying Biogas Slurry in Peanut Cultivation.

Biogas slurry, a byproduct of biogas plants, is considered a high-quality bio-organic fertilizer. Despite providing nutrients to crops, biogas slurry may contain a high concentration of heavy metals, leading to food safety problems and endangering human health if such metals are absorbed by plants. Therefore, biogas slurry should undergo systematic risk assessment prior to direct use on farmland to ensure its safety for soils and crops. In this study, the risk of applying biogas slurry in peanut cultivation was comprehensively evaluated. Based on nitrogen contents, different concentrations of biogas slurry were applied in peanut cultivation. The results achieved herein showed that the application of biogas slurry as a nutrient supplier in peanut cultivation would significantly affect the physical and chemical properties of soil and characteristics of the plant and the quality of peanuts. Although the heavy metal content of biogas slurry was within the permitted range, it had potential risks to human health and the environment. Principal component analysis (PCA) showed that biogas slurry was the primary source of heavy metals in soil. After the application of biogas slurry, the contents of As and Hg in the soil increased significantly, which were 11.12 and 26.67 times higher than those in the control soil. The contents of Cu, Zn, Pb, Cd, and As in peanut kernel samples under different levels of biogas slurry application were all lower than the maximum permissible limit set by the Standardization Administration of China. In contrast, the content of Hg in peanut kernels was higher than the maximum permissible limit value of 0.02 mg/kg. Peanut had a higher enrichment capacity of Cd and Zn and a higher migration capacity of Pb. The health risk assessment showed that the long-term consumption of peanuts grown with a high dosage of biogas slurry would be harmful to the health of children aged 2-6 years with a large consumption level.

Comparative Analysis for the Performance of Long-Read-Based Structural Variation Detection Pipelines in Tandem Repeat Regions.

There has been growing recognition of the vital links between structural variations (SVs) and diverse diseases. Research suggests that, with much longer DNA fragments and abundant contextual information, long-read technologies have advantages in SV detection even in complex repetitive regions. So far, several pipelines for calling SVs from long-read sequencing data have been proposed and used in human genome research. However, the performance of these pipelines is still lack of deep exploration and adequate comparison. In this study, we comprehensively evaluated the performance of three commonly used long-read SV detection pipelines, namely PBSV, Sniffles and PBHoney, especially the performance on detecting the SVs in tandem repeat regions (TRRs). Evaluated by using a robust benchmark for germline SV detection as the gold standard, we thoroughly estimated the precision, recall and F1 score of insertions and deletions detected by the pipelines. Our results revealed that all these pipelines clearly exhibited better performance outside TRRs than that in TRRs. The F1 scores of Sniffles in and outside TRRs were 0.60 and 0.76, respectively. The performance of PBSV was similar to that of Sniffles, and was generally higher than that of PBHoney. In conclusion, our findings can be benefit for choosing the appropriate pipelines in real practice and are good complementary to the application of long-read sequencing technologies in the research of rare diseases.

Prediction of Synergistic Drug Combinations for Prostate Cancer by Transcriptomic and Network Characteristics.

Prostate cancer (PRAD) is a major cause of cancer-related deaths. Current monotherapies show limited efficacy due to often rapidly emerging resistance. Combination therapies could provide an alternative solution to address this problem with enhanced therapeutic effect, reduced cytotoxicity, and delayed the appearance of drug resistance. However, it is prohibitively cost and labor-intensive for the experimental approaches to pick out synergistic combinations from the millions of possibilities. Thus, it is highly desired to explore other efficient strategies to assist experimental researches. Inspired by the challenge, we construct the transcriptomics-based and network-based prediction models to quickly screen the potential drug combination for Prostate cancer, and further assess their performance by in vitro assays. The transcriptomics-based method screens nine possible combinations. However, the network-based method gives discrepancies for at least three drug pairs. Further experimental results indicate the dose-dependent effects of the three docetaxel-containing combinations, and confirm the synergistic effects of the other six combinations predicted by the transcriptomics-based model. For the network-based predictions, in vitro tests give opposite results to the two combinations (i.e. mitoxantrone-cyproheptadine and cabazitaxel-cyproheptadine). Namely, the transcriptomics-based method outperforms the network-based one for the specific disease like Prostate cancer, which provide guideline for selection of the computational methods in the drug combination screening. More importantly, six combinations (the three mitoxantrone-containing and the three cabazitaxel-containing combinations) are found to be promising candidates to synergistically conquer Prostate cancer.

Quantitative Structure-Activity Relationship (QSAR) Model for the Severity Prediction of Drug-Induced Rhabdomyolysis by Using Random Forest.

Drug-induced rhabdomyolysis (DIR) is a rare and potentially life-threatening muscle injury that is characterized by low incidence and high risk. To our best knowledge, the performance of the current predictive models for the early detection of DIR is suboptimal because of the scarcity and dispersion of DIR cases. Therefore, on the basis of the curated drug information from the Drug-Induced Rhabdomyolysis Atlas (DIRA) database, we proposed a random forest (RF) model to predict the DIR severity of the marketed drugs. Compared with the state-of-art methods, our proposed model outperformed extreme gradient boosting, support vector machine, and logistic regression in distinguishing the Most-DIR concern drugs from the No-DIR concern drugs (Matthews correlation coefficient (MCC) and recall rate of our model were 0.46 and 0.81, respectively). Our model was subsequently applied to predicting the potentially serious DIR for 1402 drugs, which were reported to cause DIR by the postmarketing DIR surveillance data in the FDA Spontaneous Adverse Events Reporting System (FAERS). As a result, 62.7% (94) of drugs ranked in the top 150 drugs with the Most-DIR concerns in FAERS can be identified by our model. The top four drugs (odds ratio >30) including acepromazine, rapacuronium, oxyphenbutazone, and naringenin were correctly predicted by our model. In conclusion, the RF model can well predict the Most-DIR concern drug only based on the chemical structure information and can be a facilitated tool for early DIR detection.

Improving Model Performance on the Stratification of Breast Cancer Patients by Integrating Multiscale Genomic Features.

In clinical cancer research, it is a hot topic on how to accurately stratify patients based on genomic data. With the development of next-generation sequencing technology, more and more types of genomic features, such as mRNA expression level, can be used to distinguish cancer patients. Previous studies commonly stratified patients by using a single type of genomic features, which can only reflect one aspect of the cancer. In fact, multiscale genomic features will provide more information and may be helpful for clinical prediction. In addition, most of the conventional machine learning algorithms use a handcrafted gene set as features to construct models, which is generally selected by a statistical method with an arbitrary cut-off, e.g., p value < 0.05. The genes in the gene set are not necessarily related to the cancer and will make the model unreliable. Therefore, in our study, we thoroughly investigated the performance of different machine learning methods on stratifying breast cancer patients with a single type of genomic features. Then, we proposed a strategy, which can take into account the degree of correlation between genes and cancer patients, to identify the features from mRNAs and microRNAs, and evaluated the performance of the models with the new combined features of the multiscale genomic features. The results showed that, compared with the models constructed with a single type of features, the models with the multiscale genomic features generated by our proposed method achieved better performance on stratifying the ER status of breast cancer patients. Moreover, we found that the identified multiscale genomic features were closely related to the cancer by gene set enrichment analysis, indicating that our proposed strategy can well reflect the biological relevance of the genes to breast cancer. In conclusion, modelling with multiscale genomic features closely related to the cancer not only can guarantee the prediction performance of the models but also can effectively provide candidate genes for interpreting the mechanisms of cancer.

Uncovering the prognostic gene signatures for the improvement of risk stratification in cancers by using deep learning algorithm coupled with wavelet transform.

BACKGROUND: The aim of gene expression-based clinical modelling in tumorigenesis is not only to accurately predict the clinical endpoints, but also to reveal the genome characteristics for downstream analysis for the purpose of understanding the mechanisms of cancers. Most of the conventional machine learning methods involved a gene filtering step, in which tens of thousands of genes were firstly filtered based on the gene expression levels by a statistical method with an arbitrary cutoff. Although gene filtering procedure helps to reduce the feature dimension and avoid overfitting, there is a risk that some pathogenic genes important to the disease will be ignored. RESULTS: In this study, we proposed a novel deep learning approach by combining a convolutional neural network with stationary wavelet transform (SWT-CNN) for stratifying cancer patients and predicting their clinical outcomes without gene filtering based on tumor genomic profiles. The proposed SWT-CNN overperformed the state-of-art algorithms, including support vector machine (SVM) and logistic regression (LR), and produced comparable prediction performance to random forest (RF). Furthermore, for all the cancer types, we firstly proposed a method to weight the genes with the scores, which took advantage of the representative features in the hidden layer of convolutional neural network, and then selected the prognostic genes for the Cox proportional-hazards regression. The results showed that risk stratifications can be effectively improved by using the identified prognostic genes as feature, indicating that the representative features generated by SWT-CNN can well correlate the genes with prognostic risk in cancers and be helpful for selecting the prognostic gene signatures. CONCLUSIONS: Our results indicated that gene expression-based SWT-CNN model can be an excellent tool for stratifying the prognostic risk for cancer patients. In addition, the representative features of SWT-CNN were validated to be useful for evaluating the importance of the genes in the risk stratification and can be further used to identify the prognostic gene signatures.

Transcriptome Analysis Identifies Piwi-Interacting RNAs as Prognostic Markers for Recurrence of Prostate Cancer.

Prostate cancer remains the second leading cause of male cancer death, and there is an unmet need for biomarkers to identify patients with such aggressive disease. Piwi-inteacting RNAs (piRNAs) have been classified as transcriptional and posttranscriptional regulators in somatic cells. In this study, we discovered three piRNAs as novel prognostic markers and their association with prostate cancer biochemical recurrence was confirmed in validation data set. To obtain a better understanding of piRNA expression patterns in prostate cancer and to find gene coexpression with piRNAs, we performed weighted gene coexpression network analysis. Target genes of three piRNAs have also been predicted based on base complementarity and expression correlativity. Functional analysis revealed the relationships between target genes and prostate cancer. Our work also identified differential expression of piRNAs between Gleason stage 3 + 4 and 4 + 3 prostate cancer. Overall, this study may explain the roles and demonstrate the potential clinical utility of piRNAs in prostate cancer in a way.

Comparative Analysis for the Performance of Variant Calling Pipelines on Detecting the de novo Mutations in Humans.

Despite of the low occurrence rate in the entire genomes, de novo mutation is proved to be deleterious and will lead to severe genetic diseases via impacting on the gene function. Considering the fact that the traditional family based linkage approaches and the genome-wide association studies are unsuitable for identifying the de novo mutations, in recent years, several pipelines have been proposed to detect them based on the whole-genome or whole-exome sequencing data and were used for calling them in the rare diseases. However, how the performance of these variant calling pipelines on detecting the de novo mutations is still unexplored. For the purpose of facilitating the appropriate choice of the pipelines and reducing the false positive rate, in this study, we thoroughly evaluated the performance of the commonly used trio calling methods on the detection of the de novo single-nucleotide variants (DNSNVs) by conducting a comparative analysis for the calling results. Our results exhibited that different pipelines have a specific tendency to detect the DNSNVs in the genomic regions with different GC contents. Additionally, to refine the calling results for a single pipeline, our proposed filter achieved satisfied results, indicating that the read coverage at the mutation positions can be used as an effective index to identify the high-confidence DNSNVs. Our findings should be good support for the committees to choose an appropriate way to explore the de novo mutations for the rare diseases.

Drug-Induced Rhabdomyolysis Atlas (DIRA) for idiosyncratic adverse drug reaction management.

Drug-induced rhabdomyolysis (DIR) is an idiosyncratic and fatal adverse drug reaction (ADR) characterized in severe muscle injuries accompanied by multiple-organ failure. Limited knowledge regarding the pathophysiology of rhabdomyolysis is the main obstacle to developing early biomarkers and prevention strategies. Given the lack of a centralized data resource to curate, organize, and standardize widespread DIR information, here we present a Drug-Induced Rhabdomyolysis Atlas (DIRA) that provides DIR-related information, including: a classification scheme for DIR based on drug labeling information; postmarketing surveillance data of DIR; and DIR drug property information. To elucidate the utility of DIRA, we used precision dosing, concomitant use of DIR drugs, and predictive modeling development to exemplify strategies for idiosyncratic ADR (IADR) management.

Narrowing the Gap Between In Vitro and In Vivo Genetic Profiles by Deconvoluting Toxicogenomic Data In Silico.

Toxicogenomics (TGx) is a powerful method to evaluate toxicity and is widely used in both in vivo and in vitro assays. For in vivo TGx, reduction, refinement, and replacement represent the unremitting pursuit of live-animal tests, but in vitro assays, as alternatives, usually demonstrate poor correlation with real in vivo assays. In living subjects, in addition to drug effects, inner-environmental reactions also affect genetic variation, and these two factors are further jointly reflected in gene abundance. Thus, finding a strategy to factorize inner-environmental factor from in vivo assays based on gene expression levels and to further utilize in vitro data to better simulate in vivo data is needed. We proposed a strategy based on post-modified non-negative matrix factorization, which can estimate the gene expression profiles and contents of major factors in samples. The applicability of the strategy was first verified, and the strategy was then utilized to simulate in vivo data by correcting in vitro data. The similarities between real in vivo data and simulated data (single-dose 0.72, repeat-doses 0.75) were higher than those observed when directly comparing real in vivo data with in vitro data (single-dose 0.56, repeat-doses 0.70). Moreover, by keeping environment-related factor, a simulation can always be generated by using in vitro data to provide potential substitutions for in vivo TGx and to reduce the launch of live-animal tests.

Using accelerated molecular dynamics simulation to shed light on the mechanism of activation/deactivation upon mutations for CCR5.

In this work, accelerated molecular dynamics (aMD) simulations were used to study different effects of G286F and R126 mutations on the activity of CCR5. Potential of Mean Force (PMF) results indicate that there are stable inactive-like states and active-like ones existing in the conformation space of the wild type (WT), confirming that CCR5 could possess to some extent constitutive activity. But the R126N mutation could constrain CCR5 in the inactive state through influencing the TXP motif and limiting the movements of TM5 and TM6. In contrast, the G286F mutation promotes the activity of the receptor by increasing the distance of TM2-TM6 and the flexibility of the intracellular part of TM5 and changing the H-bonding in the TXP motif. The observations from the cross correlation analysis further show that the R126N mutation dramatically reduces the motion correlations between TMs, which should partly contribute to the deactivation of CCR5. Compared with the WT system, TM6 and TM7 in the G286F mutant are loosely correlated with other regions, which should be conducive to drive the movement of TM6 and TM7 toward the active conformation. In addition, the result from the protein structure network (PSN) analysis reveals that the shortest pathways connecting the extracellular and the intracellular domains are highly conserved in the three systems despite the different mutations, in which the hydrogen bond plays a pivotal role. However, the G286F mutation shortens the lifetime of the pathway with respect to the R126N mutation, which may be associated with the different activities of the two mutants. The pathway connecting the ligand-binding site and the G-protein region reveals that the allosteric communication between TM6 and TM7 is enhanced by the R126N mutation while the G286F mutation induces the activation of the G-protein pocket by arousing more residues in the NPxxY region to participate in the pathway.