Natural product-based drug combinations (NPDCs) present distinctive advantages in treating complex diseases. While high-throughput screening (HTS) and conventional computational methods have partially accelerated synergistic drug combination discovery, their applications remain constrained by experimental data fragmentation, high costs, and extensive combinatorial space. Recent developments in artificial intelligence (AI), encompassing traditional machine learning and deep learning algorithms, have been extensively applied in NPDC identification. Through the integration of multi-source heterogeneous data and autonomous feature extraction, prediction accuracy has markedly improved, offering a robust technical approach for novel NPDC discovery. This review comprehensively examines recent advances in AI-driven NPDC prediction, presents relevant data resources and algorithmic frameworks, and evaluates current limitations and future prospects. AI methodologies are anticipated to substantially expedite NPDC discovery and inform experimental validation.
Artificial Intelligence ; Biological Products/chemistry* ; Humans ; Drug Combinations ; Drug Discovery/methods* ; Machine Learning ; Algorithms

Objective:To investigate the expression and clinical significance of the complement C3 and the S100 calcium binding protein A10 (S100A10) in children with traumatic brain injury (TBI).Methods:This case-control study included 129 TBI children admitted to the Affiliated Xuzhou Children′s Hospital of Xuzhou Medical University from January 2023 to November 2024.The patients were divided into a mild group (85 cases) and a moderate-to-severe group (44 cases).Thirty children with inguinal hernia but no underlying diseases admitted to the hospital during the same period were enrolled as the control group A. Twenty children whose lumbar puncture examination showed normal cerebrospinal fluid results and imaging tests showed no central nervous system disorder were included in the control group B. The children with moderate-to-severe TBI were followed up for 1 month after injury and further divided into good and poor prognosis groups.One-way (repeated-measures) analysis of variance (ANOVA) and t-tests were used to compare differences in complement C3 and S100A10 levels in serum and cerebrospinal fluid among groups.The correlation analysis was performed using the Spearman rank correlation method.Receiver operating characteristic (ROC) curves were drawn to evaluate the value of complements C3 and S100A10 proteins for predicting TBI severity. Results:The serum complement C3 levels in control group A, mild TBI, and moderate-to-severe TBI groups were (1.15±0.26) g/L, (1.02±0.09) g/L, (0.87±0.15) g/L, respectively.The difference in serum complement C3 levels was statistically significant among these three groups ( F=53.661, P<0.001).The serum S100A10 levels in control group A, mild TBI, and moderate-to-severe TBI groups were (0.09±0.03) μg/L, (0.17±0.04) μg/L, (0.32±0.11) μg/L, respectively.The difference in serum S100A10 levels was statistically significant among these three groups ( F=71.093, P<0.001).The levels of complement C3 and S100A10 in the cerebrospinal fluid (30 min post-operation) of children with severe TBI were significantly higher than those in the control group B, with statistically significant differences (all P<0.01).Correlation analysis revealed that Glasgow Coma Scale scores showed a positive correlation with serum complement C3 levels and a negative correlation with S100A10 levels ( r=0.592, -0.705; all P<0.001).The serum complement C3 and S100A10 levels were (0.90±0.13) g/L and (0.30±0.10) μg/L in the good prognosis group, and (0.74±0.16) g/L and (0.42±0.11) μg/L in the poor prognosis group, respectively.Both serum complement C3 and S100A10 levels were statistically significantly different between good and poor prognosis groups ( t=3.025, -3.014; all P<0.01).The complement C3 level in the cerebrospinal fluid of severe TBI children was (0.093±0.007) g/L 30 min after operation, and it gradually increased to reach the first peak at day 3 and the second peak at day 5 postoperatively[(0.112±0.005) g/L and (0.120±0.010) g/L, respectively].The difference in the complement C3 level in the cerebrospinal fluid of severe TBI children was significant between 30 min and 3-5 d after operation ( F=42.756, P<0.01).The S100A10 level in the cerebrospinal fluid of severe TBI children was (2.56±0.31) μg/L 30 min after operation, and then it showed a sustained increase, reaching (4.09±0.13) μg/L at day 7 postoperatively.The difference in the S100A10 level in the cerebrospinal fluid of severe TBI children was significant between 30 min and 7 d after operation ( F=110.676, P<0.01).ROC curve analysis showed that the areas under the curve for predicting moderate-to-severe TBI based on serum complement C3 and S100A10 levels were 0.802 and 0.889, respectively (all P<0.01). Conclusions:Serum complement C3 levels are significantly decreased whereas serum S100A10 levels are markedly elevated in pediatric TBI patients.The measurement of serum complement C3 and S100A10 levels can aid in the clinical assessment of the severity and prognosis of TBI children.Both complement C3 and S100A10 levels in cerebrospinal fluid show a significant elevation within 7 days after operation in severe pediatric TBI, which is potentially linked to sustained astrocyte activation.

Objective:To investigate the expression and clinical significance of the complement C3 and the S100 calcium binding protein A10 (S100A10) in children with traumatic brain injury (TBI).Methods:This case-control study included 129 TBI children admitted to the Affiliated Xuzhou Children′s Hospital of Xuzhou Medical University from January 2023 to November 2024.The patients were divided into a mild group (85 cases) and a moderate-to-severe group (44 cases).Thirty children with inguinal hernia but no underlying diseases admitted to the hospital during the same period were enrolled as the control group A. Twenty children whose lumbar puncture examination showed normal cerebrospinal fluid results and imaging tests showed no central nervous system disorder were included in the control group B. The children with moderate-to-severe TBI were followed up for 1 month after injury and further divided into good and poor prognosis groups.One-way (repeated-measures) analysis of variance (ANOVA) and t-tests were used to compare differences in complement C3 and S100A10 levels in serum and cerebrospinal fluid among groups.The correlation analysis was performed using the Spearman rank correlation method.Receiver operating characteristic (ROC) curves were drawn to evaluate the value of complements C3 and S100A10 proteins for predicting TBI severity. Results:The serum complement C3 levels in control group A, mild TBI, and moderate-to-severe TBI groups were (1.15±0.26) g/L, (1.02±0.09) g/L, (0.87±0.15) g/L, respectively.The difference in serum complement C3 levels was statistically significant among these three groups ( F=53.661, P<0.001).The serum S100A10 levels in control group A, mild TBI, and moderate-to-severe TBI groups were (0.09±0.03) μg/L, (0.17±0.04) μg/L, (0.32±0.11) μg/L, respectively.The difference in serum S100A10 levels was statistically significant among these three groups ( F=71.093, P<0.001).The levels of complement C3 and S100A10 in the cerebrospinal fluid (30 min post-operation) of children with severe TBI were significantly higher than those in the control group B, with statistically significant differences (all P<0.01).Correlation analysis revealed that Glasgow Coma Scale scores showed a positive correlation with serum complement C3 levels and a negative correlation with S100A10 levels ( r=0.592, -0.705; all P<0.001).The serum complement C3 and S100A10 levels were (0.90±0.13) g/L and (0.30±0.10) μg/L in the good prognosis group, and (0.74±0.16) g/L and (0.42±0.11) μg/L in the poor prognosis group, respectively.Both serum complement C3 and S100A10 levels were statistically significantly different between good and poor prognosis groups ( t=3.025, -3.014; all P<0.01).The complement C3 level in the cerebrospinal fluid of severe TBI children was (0.093±0.007) g/L 30 min after operation, and it gradually increased to reach the first peak at day 3 and the second peak at day 5 postoperatively[(0.112±0.005) g/L and (0.120±0.010) g/L, respectively].The difference in the complement C3 level in the cerebrospinal fluid of severe TBI children was significant between 30 min and 3-5 d after operation ( F=42.756, P<0.01).The S100A10 level in the cerebrospinal fluid of severe TBI children was (2.56±0.31) μg/L 30 min after operation, and then it showed a sustained increase, reaching (4.09±0.13) μg/L at day 7 postoperatively.The difference in the S100A10 level in the cerebrospinal fluid of severe TBI children was significant between 30 min and 7 d after operation ( F=110.676, P<0.01).ROC curve analysis showed that the areas under the curve for predicting moderate-to-severe TBI based on serum complement C3 and S100A10 levels were 0.802 and 0.889, respectively (all P<0.01). Conclusions:Serum complement C3 levels are significantly decreased whereas serum S100A10 levels are markedly elevated in pediatric TBI patients.The measurement of serum complement C3 and S100A10 levels can aid in the clinical assessment of the severity and prognosis of TBI children.Both complement C3 and S100A10 levels in cerebrospinal fluid show a significant elevation within 7 days after operation in severe pediatric TBI, which is potentially linked to sustained astrocyte activation.

Objective:To investigate the efficacy of a combined model constructed by the radiomics features based on non-contrast CT (NCCT) combined with clinical risk factors in predicting the occurrence of symptomatic intracranial hemorrhagic transformation (sICH) after intravenous thrombolysis with recombinant tissue plasminogen activator (rt-PA) in patients with anterior circulation acute ischemic stroke (AIS).Methods:In this cross-sectional study, clinical and imaging data of 316 patients with anterior circulation AIS who received intravenous thrombolysis with rt-PA at Nantong First People′s Hospital from October 2018 to September 2022 were retrospectively analyzed. The cases were divided into a training set of 210 cases and a validation set of 106 cases by stratified random sampling at a ratio of 7∶3. Univariate and multivariate logistic regression analyses were performed to select the independent clinical risk factors for predicting sICH. The infarct area was delineated on the NCCT images and radiomics features were extracted. The extracted radiomics features were dimensionally reduced and selected using the inter-and intra-group correlation coefficients, maximum correlation and minimum redundancy, and the least absolute shrinkage and selection operator, and then the radiomics score was calculated. Finally, multivariate logistic analysis was performed and the clinical risk factors and radiomics scores were used to establish the clinical model, the radiomics model and the radiomics-clinical combined model. The predictive efficacy of each model was evaluated by the receiver operating characteristic curve and the area under the curve, and decision curve analysis (DCA) was used to calculate and quantify the net benefits of each predictive model.Results:In total eight radiomics features were selected to construct the radiomics model. Multivariate logistic analysis showed that hypertension ( OR=2.703, 95% CI 1.153-6.334, P=0.022), atrial fibrillation ( OR=3.023, 95% CI 1.290-7.085, P=0.011), and the National Institutes of Health Stroke Scale score at admission ( OR=1.078, 95% CI 1.017-1.143, P=0.012) were independent risk factors for sICH after rt-PA intravenous thrombolysis in patients with anterior circulation AIS. In the validation set, the area under the curve of the combined model for predicting sICH was 0.763 (95% CI 0.618-0.909), which was higher than that of the clinical model 0.710 (95% CI 0.552-0.868) and the radiomics model 0.708 (95% CI 0.568-0.848). DCA showed that the combined model could allow patients to obtain higher net benefits. Conclusion:The combined model constructed based on the radiomics of NCCT and clinical risk factors has a high diagnostic efficacy in predicting sICH after rt-PA intravenous thrombolysis in patients with anterior circulation AIS.

Purpose: Explore the causal relationship between the gut microbiota and erectile dysfunction (ED) at phylum, class, order, family, and genus levels, and identify specific pathogenic bacteria that may be associated with the onset and progression of ED. Materials and Methods: The genetic variation data of 196 human gut microbiota incorporated in our study came from the human gut microbiome Genome Wide Association Studies (GWAS) dataset released by the MiBioGen Consortium. The GWAS statistics for ED were extracted from one study by Bovijn et al., which included 223,805 participants of European ancestry, of whom 6,175 were diagnosed with ED. Subsequently, Mendelian randomization (MR) analysis was carried out to explore whether a causal relationship exists between the gut microbiota and ED. Additionally, bidirectional MR analysis was performed to examine the directionality of the causal relationship. Results: Through MR analysis, we found that family Lachnospiraceae (odds ratio [OR]: 1.27, 95% confidence interval [CI]: 1.05–1.52, p=0.01) and its subclass genus LachnospiraceaeNC2004 group (OR: 1.17, 95% CI: 1.01–1.37, p=0.04) are associated with a higher risk of ED. In addition, genus Oscillibacter (OR: 1.17, 95% CI: 1.02–1.35, p=0.03), genus Senegalimassilia (OR: 1.32, 95% CI: 1.06–1.64, p=0.01) and genus Tyzzerella3 (OR: 1.14, 95% CI: 1.02–1.27, p=0.02) also increase the risk of ED. In contrast, the inverse variance weighted estimate of genus RuminococcaceaeUCG013 (OR: 0.77, 95% CI: 0.61–0.96, p=0.02) suggests that it has a protective effect against the occurrence of ED. Conclusions This study preliminarily identified 6 bacterial taxa that may have a causal relationship with ED, including family Lachnospiraceae, genus Lachnospiraceae NC2004 group, Oscillibacter, Senegalimassilia, Tyzzerella 3 and Ruminococcaceae UCG013. These identified important bacterial taxa may serve as candidates for microbiome intervention in future ED clinical trials.

Purpose: Explore the causal relationship between the gut microbiota and erectile dysfunction (ED) at phylum, class, order, family, and genus levels, and identify specific pathogenic bacteria that may be associated with the onset and progression of ED. Materials and Methods: The genetic variation data of 196 human gut microbiota incorporated in our study came from the human gut microbiome Genome Wide Association Studies (GWAS) dataset released by the MiBioGen Consortium. The GWAS statistics for ED were extracted from one study by Bovijn et al., which included 223,805 participants of European ancestry, of whom 6,175 were diagnosed with ED. Subsequently, Mendelian randomization (MR) analysis was carried out to explore whether a causal relationship exists between the gut microbiota and ED. Additionally, bidirectional MR analysis was performed to examine the directionality of the causal relationship. Results: Through MR analysis, we found that family Lachnospiraceae (odds ratio [OR]: 1.27, 95% confidence interval [CI]: 1.05–1.52, p=0.01) and its subclass genus LachnospiraceaeNC2004 group (OR: 1.17, 95% CI: 1.01–1.37, p=0.04) are associated with a higher risk of ED. In addition, genus Oscillibacter (OR: 1.17, 95% CI: 1.02–1.35, p=0.03), genus Senegalimassilia (OR: 1.32, 95% CI: 1.06–1.64, p=0.01) and genus Tyzzerella3 (OR: 1.14, 95% CI: 1.02–1.27, p=0.02) also increase the risk of ED. In contrast, the inverse variance weighted estimate of genus RuminococcaceaeUCG013 (OR: 0.77, 95% CI: 0.61–0.96, p=0.02) suggests that it has a protective effect against the occurrence of ED. Conclusions This study preliminarily identified 6 bacterial taxa that may have a causal relationship with ED, including family Lachnospiraceae, genus Lachnospiraceae NC2004 group, Oscillibacter, Senegalimassilia, Tyzzerella 3 and Ruminococcaceae UCG013. These identified important bacterial taxa may serve as candidates for microbiome intervention in future ED clinical trials.

Purpose: Explore the causal relationship between the gut microbiota and erectile dysfunction (ED) at phylum, class, order, family, and genus levels, and identify specific pathogenic bacteria that may be associated with the onset and progression of ED. Materials and Methods: The genetic variation data of 196 human gut microbiota incorporated in our study came from the human gut microbiome Genome Wide Association Studies (GWAS) dataset released by the MiBioGen Consortium. The GWAS statistics for ED were extracted from one study by Bovijn et al., which included 223,805 participants of European ancestry, of whom 6,175 were diagnosed with ED. Subsequently, Mendelian randomization (MR) analysis was carried out to explore whether a causal relationship exists between the gut microbiota and ED. Additionally, bidirectional MR analysis was performed to examine the directionality of the causal relationship. Results: Through MR analysis, we found that family Lachnospiraceae (odds ratio [OR]: 1.27, 95% confidence interval [CI]: 1.05–1.52, p=0.01) and its subclass genus LachnospiraceaeNC2004 group (OR: 1.17, 95% CI: 1.01–1.37, p=0.04) are associated with a higher risk of ED. In addition, genus Oscillibacter (OR: 1.17, 95% CI: 1.02–1.35, p=0.03), genus Senegalimassilia (OR: 1.32, 95% CI: 1.06–1.64, p=0.01) and genus Tyzzerella3 (OR: 1.14, 95% CI: 1.02–1.27, p=0.02) also increase the risk of ED. In contrast, the inverse variance weighted estimate of genus RuminococcaceaeUCG013 (OR: 0.77, 95% CI: 0.61–0.96, p=0.02) suggests that it has a protective effect against the occurrence of ED. Conclusions This study preliminarily identified 6 bacterial taxa that may have a causal relationship with ED, including family Lachnospiraceae, genus Lachnospiraceae NC2004 group, Oscillibacter, Senegalimassilia, Tyzzerella 3 and Ruminococcaceae UCG013. These identified important bacterial taxa may serve as candidates for microbiome intervention in future ED clinical trials.

Objective To investigate the application value of the quantitative parameters of collateral circulation based on computed tomography perfusion(CTP)in evaluating the clinical prognosis of patients with acute ischemic stroke(AIS).Methods A total of 126 patients with AIS caused by middle cerebral artery occlusion were enrolled,collateral circulation were reconstructed and scored via multiphase computed tomography angiography(mCTA)based on CTP.The hypoperfusion intensity ratio(HIR)and collateral vessel density(CVD)were calculated.All patients were divided into good prognosis group(72 cases)and poor prognosis group(54 cases)based on 90 d modified Rankin scale(mRS)scores.Differences in cardiovascular risk factors,National Institutes of Health Stroke Scale(NIHSS)scores,Albert stroke program early CT(ASPECT)scores,Tmax＞10 s volume,Tmax＞6 s volume,core infarct area volume,and final infarct volume between the two groups were compared.Binary logistic regression was employed to identify independent predictors of the clinical prognosis,and the DeLong test was used to compare the efficacy of different predictors in predicting clinical prognosis.Results The good prognosis group had significantly higher ASPECT scores,mCTA scores,and CVD,but significantly lower HIR,Tmax＞10 s volume,and baseline NIHSS scores compared to the poor prognosis group(P＜0.05).Binary logistic regression analysis showed that ASPECT scores[odds ratio(OR)=0.780],mCTA scores(OR=0.669),CVD(OR=0.595),and HIR(OR=28.968)were independent predictors of clinical prognosis(P＜0.05).DeLong test found no significant difference in area under the curve(AUC)values between mCTA scores,CVD and HIR in predicting the clinical prognosis of AIS patients(P＞0.05).Conclusion Quantitative parameters such as CVD and HIR related to collateral circulation have a strong diagnostic efficacy in predicting the 90 d clinical prognosis in patients with AIS.

Purpose: Explore the causal relationship between the gut microbiota and erectile dysfunction (ED) at phylum, class, order, family, and genus levels, and identify specific pathogenic bacteria that may be associated with the onset and progression of ED. Materials and Methods: The genetic variation data of 196 human gut microbiota incorporated in our study came from the human gut microbiome Genome Wide Association Studies (GWAS) dataset released by the MiBioGen Consortium. The GWAS statistics for ED were extracted from one study by Bovijn et al., which included 223,805 participants of European ancestry, of whom 6,175 were diagnosed with ED. Subsequently, Mendelian randomization (MR) analysis was carried out to explore whether a causal relationship exists between the gut microbiota and ED. Additionally, bidirectional MR analysis was performed to examine the directionality of the causal relationship. Results: Through MR analysis, we found that family Lachnospiraceae (odds ratio [OR]: 1.27, 95% confidence interval [CI]: 1.05–1.52, p=0.01) and its subclass genus LachnospiraceaeNC2004 group (OR: 1.17, 95% CI: 1.01–1.37, p=0.04) are associated with a higher risk of ED. In addition, genus Oscillibacter (OR: 1.17, 95% CI: 1.02–1.35, p=0.03), genus Senegalimassilia (OR: 1.32, 95% CI: 1.06–1.64, p=0.01) and genus Tyzzerella3 (OR: 1.14, 95% CI: 1.02–1.27, p=0.02) also increase the risk of ED. In contrast, the inverse variance weighted estimate of genus RuminococcaceaeUCG013 (OR: 0.77, 95% CI: 0.61–0.96, p=0.02) suggests that it has a protective effect against the occurrence of ED. Conclusions This study preliminarily identified 6 bacterial taxa that may have a causal relationship with ED, including family Lachnospiraceae, genus Lachnospiraceae NC2004 group, Oscillibacter, Senegalimassilia, Tyzzerella 3 and Ruminococcaceae UCG013. These identified important bacterial taxa may serve as candidates for microbiome intervention in future ED clinical trials.

Purpose: Explore the causal relationship between the gut microbiota and erectile dysfunction (ED) at phylum, class, order, family, and genus levels, and identify specific pathogenic bacteria that may be associated with the onset and progression of ED. Materials and Methods: The genetic variation data of 196 human gut microbiota incorporated in our study came from the human gut microbiome Genome Wide Association Studies (GWAS) dataset released by the MiBioGen Consortium. The GWAS statistics for ED were extracted from one study by Bovijn et al., which included 223,805 participants of European ancestry, of whom 6,175 were diagnosed with ED. Subsequently, Mendelian randomization (MR) analysis was carried out to explore whether a causal relationship exists between the gut microbiota and ED. Additionally, bidirectional MR analysis was performed to examine the directionality of the causal relationship. Results: Through MR analysis, we found that family Lachnospiraceae (odds ratio [OR]: 1.27, 95% confidence interval [CI]: 1.05–1.52, p=0.01) and its subclass genus LachnospiraceaeNC2004 group (OR: 1.17, 95% CI: 1.01–1.37, p=0.04) are associated with a higher risk of ED. In addition, genus Oscillibacter (OR: 1.17, 95% CI: 1.02–1.35, p=0.03), genus Senegalimassilia (OR: 1.32, 95% CI: 1.06–1.64, p=0.01) and genus Tyzzerella3 (OR: 1.14, 95% CI: 1.02–1.27, p=0.02) also increase the risk of ED. In contrast, the inverse variance weighted estimate of genus RuminococcaceaeUCG013 (OR: 0.77, 95% CI: 0.61–0.96, p=0.02) suggests that it has a protective effect against the occurrence of ED. Conclusions This study preliminarily identified 6 bacterial taxa that may have a causal relationship with ED, including family Lachnospiraceae, genus Lachnospiraceae NC2004 group, Oscillibacter, Senegalimassilia, Tyzzerella 3 and Ruminococcaceae UCG013. These identified important bacterial taxa may serve as candidates for microbiome intervention in future ED clinical trials.