Predicting metformin efficacy in improving insulin sensitivity among women with polycystic ovary syndrome and insulin resistance: a machine learning study.

OBJECTIVE: Metformin is clinically effective in treating polycystic ovary syndrome (PCOS) with insulin resistance (IR), while its efficacy varies among individuals. This study aims to develop a machine learning model to predict the efficacy of metformin in improving insulin sensitivity among women with PCOS and IR. METHODS: This is a retrospective analysis of a multicenter, randomized controlled trial involving 114 women diagnosed with PCOS and IR. All women received metformin treatment for 4 months. We incorporated 27 baseline clinical variables of the women into the construction of our machine learning model. We firstly compared four commonly used feature selection methods to screen valuable clinical variables. Then we used the valuable variables as inputs to evaluate the performance of five machine learning models, including k-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (Xgboost), in predicting the efficacy of metformin. RESULTS: Among the five machine learning models, SVM performed the best with an area under the receiver operating characteristic curve (AUC) of 0.781 (95% confidence interval [CI]: 0.772-0.791). The key predictive variables identified were homeostasis model assessment of insulin resistance (HOMA-IR), body mass index (BMI), and low-density lipoprotein cholesterol (LDL-C). CONCLUSION: The developed machine learning model could be applied to to predict the efficacy of metformin in improving insulin sensitivity among women with PCOS and IR. The result could help doctors evaluate the efficacy of metformin in advance, optimize treatment plans, and thereby enhance overall clinical outcomes.

A novel scoring model for predicting efficacy and guiding individualised treatment in immune thrombocytopaenia.

Despite diverse therapeutic options for immune thrombocytopaenia (ITP), drug efficacy and selection challenges persist. This study systematically identified potential indicators in ITP patients and followed up on subsequent treatment. We initially analysed 61 variables and identified 12, 14, and 10 candidates for discriminating responders from non-responders in glucocorticoid (N = 215), thrombopoietin receptor agonists (TPO-RAs) (N = 224), and rituximab (N = 67) treatments, respectively. Patients were randomly assigned to training or testing datasets and employing five machine learning (ML) models, with eXtreme Gradient Boosting (XGBoost) area under the curve (AUC = 0.89), Decision Tree (DT) (AUC = 0.80) and Artificial Neural Network (ANN) (AUC = 0.79) selected. Cross-validated with logistic regression and ML finalised five variables (baseline platelet, IP-10, TNF-α, Treg, B cell) for glucocorticoid, eight variables (baseline platelet, TGF-ß1, MCP-1, IL-21, Th1, Treg, MK number, TPO) for TPO-RAs, and three variables (IL-12, Breg, MAIPA-) for rituximab to establish the predictive model. Spearman correlation and receiver operating characteristic curve analysis in validation datasets demonstrated strong correlations between response fractions and scores in all treatments. Scoring thresholds SGlu ≥ 3 (AUC = 0.911, 95% CI, 0.865-0.956), STPO-RAs ≥ 5 (AUC = 0.964, 95% CI 0.934-0.994), and SRitu = 3 (AUC = 0.964, 95% CI 0.915-1.000) indicated ineffectiveness in glucocorticoid, TPO-RAs, and rituximab therapy, respectively. Regression analysis and ML established a tentative and preliminary predictive scoring model for advancing individualised treatment.

Learning the cellular activity representation based on gene regulatory networks for prediction of tumor response to drugs.

Predicting the response of tumor cells to anti-tumor drugs is critical to realizing cancer precision medicine. Currently, most existing methods ignore the regulatory relationships between genes and thus have unsatisfactory predictive performance. In this paper, we propose to predict anti-tumor drug efficacy via learning the activity representation of tumor cells based on a priori knowledge of gene regulation networks (GRNs). Specifically, the method simulates the cellular biosystem by synthesizing a cell-gene activity network and then infers a new low-dimensional activity representation for tumor cells from the raw high-dimensional expression profile. The simulated cell-gene network mainly comprises known gene regulatory networks collected from multiple resources and fuses tumor cells by linking them to hotspot genes that are over- or under-expressed in them. The resulting activity representation could not only reflect the shallow expression profile (hotspot genes) but also mines in-depth information of gene regulation activity in tumor cells before treatment. Finally, we build deep learning models on the activity representation for predicting drug efficacy in tumor cells. Experimental results on the benchmark GDSC dataset demonstrate the superior performance of the proposed method over SOTA methods with the highest AUC of 0.954 in the efficacy label prediction and the best R2 of 0.834 in the regression of half maximal inhibitory concentration (IC50) values, suggesting the potential value of the proposed method in practice.

Immunotherapy efficacy prediction through a feature re-calibrated 2.5D neural network.

BACKGROUND AND OBJECTIVE: Lung cancer continues to be a leading cause of cancer-related mortality worldwide, with immunotherapy emerging as a promising therapeutic strategy for advanced non-small cell lung cancer (NSCLC). Despite its potential, not all patients experience benefits from immunotherapy, and the current biomarkers used for treatment selection possess inherent limitations. As a result, the implementation of imaging-based biomarkers to predict the efficacy of lung cancer treatments offers a promising avenue for improving therapeutic outcomes. METHODS: This study presents an automatic system for immunotherapy efficacy prediction on the subjects with lung cancer, facilitating significant clinical implications. Our model employs an advanced 2.5D neural network that incorporates 2D intra-slice feature extraction and 3D inter-slice feature aggregation. We further present a lesion-focused prior to guide the re-calibration for intra-slice features, and a attention-based re-calibration for the inter-slice features. Finally, we design an accumulated back-propagation strategy to optimize network parameters in a memory-efficient fashion. RESULTS: We demonstrate that the proposed method achieves impressive performance on an in-house clinical dataset, surpassing existing state-of-the-art models. Furthermore, the proposed model exhibits increased efficiency in inference for each subject on average. To further validate the effectiveness of our model and its components, we conducted comprehensive and in-depth ablation experiments and discussions. CONCLUSION: The proposed model showcases the potential to enhance physicians' diagnostic performance due to its impressive performance in predicting immunotherapy efficacy, thereby offering significant clinical application value. Moreover, we conduct adequate comparison experiments of the proposed methods and existing advanced models. These findings contribute to our understanding of the proposed model's effectiveness and serve as motivation for future work in immunotherapy efficacy prediction.

Personalized anti-tumor drug efficacy prediction based on clinical data.

Anti-tumor drug efficacy prediction poses an unprecedented challenge to realizing personalized medicine. This paper proposes to predict personalized anti-tumor drug efficacy based on clinical data. Specifically, we encode the clinical text as numeric vectors featured with hidden topics for patients using Latent Dirichlet Allocation model. Then, to classify patients into two classes, responsive or non-responsive to a drug, drug efficacy predictors are established by machine learning based on the Latent Dirichlet Allocation topic representation. To evaluate the proposed method, we collected and collated clinical records of lung and bowel cancer patients treated with platinum. Experimental results on the data sets show the efficacy and effectiveness of the proposed method, suggesting the potential value of clinical data in cancer precision medicine. We hope that it will promote the research of drug efficacy prediction based on clinical data.

Dynamic surveillance of lymphocyte subsets in patients with non-small cell lung cancer during chemotherapy or combination immunotherapy for early prediction of efficacy.

Background: Non-small cell lung cancer (NSCLC) remains the leading cause of cancer-related deaths worldwide. Lymphocytes are the primary executors of the immune system and play essential roles in tumorigenesis and development. We investigated the dynamic changes in peripheral blood lymphocyte subsets to predict the efficacy of chemotherapy or combination immunotherapy in NSCLC. Methods: This retrospective study collected data from 81 patients with NSCLC who received treatments at the First Affiliated Hospital of Zhengzhou University from May 2021 to May 2023. Patients were divided into response and non-response groups, chemotherapy and combination immunotherapy groups, and first-line and multiline groups. We analyzed the absolute counts of each lymphocyte subset in the peripheral blood at baseline and after each treatment cycle. Within-group and between-group differences were analyzed using paired Wilcoxon signed-rank and Mann-Whitney U tests, respectively. The ability of lymphocyte subsets to predict treatment efficacy was analyzed using receiver operating characteristic curve and logistic regression. Results: The absolute counts of lymphocyte subsets in the response group significantly increased after the first cycle of chemotherapy or combination immunotherapy, whereas those in the non-response group showed persistent decreases. Ratios of lymphocyte subsets after the first treatment cycle to those at baseline were able to predict treatment efficacy early. Combination immunotherapy could increase lymphocyte counts compared to chemotherapy alone. In addition, patients with NSCLC receiving chemotherapy or combination immunotherapy for the first time mainly presented with elevated lymphocyte levels, whereas multiline patients showed continuous reductions. Conclusion: Dynamic surveillance of lymphocyte subsets could reflect a more actual immune status and predict efficacy early. Combination immunotherapy protected lymphocyte levels from rapid decrease and patients undergoing multiline treatments were more prone to lymphopenia than those receiving first-line treatment. This study provides a reference for the early prediction of the efficacy of clinical tumor treatment for timely combination of immunotherapy or the improvement of immune status.

Can Brain Volume-Driven Characteristic Features Predict the Response of Alzheimer's Patients to Repetitive Transcranial Magnetic Stimulation? A Pilot Study.

This study is a post-hoc examination of baseline MRI data from a clinical trial investigating the efficacy of repetitive transcranial magnetic stimulation (rTMS) as a treatment for patients with mild-moderate Alzheimer's disease (AD). Herein, we investigated whether the analysis of baseline MRI data could predict the response of patients to rTMS treatment. Whole-brain T1-weighted MRI scans of 75 participants collected at baseline were analyzed. The analyses were run on the gray matter (GM) and white matter (WM) of the left and right dorsolateral prefrontal cortex (DLPFC), as that was the rTMS application site. The primary outcome measure was the Alzheimer's disease assessment scale-cognitive subscale (ADAS-Cog). The response to treatment was determined based on ADAS-Cog scores and secondary outcome measures. The analysis of covariance showed that responders to active treatment had a significantly lower baseline GM volume in the right DLPFC and a higher GM asymmetry index in the DLPFC region compared to those in non-responders. Logistic regression with a repeated five-fold cross-validated analysis using the MRI-driven features of the initial 75 participants provided a mean accuracy of 0.69 and an area under the receiver operating characteristic curve of 0.74 for separating responders and non-responders. The results suggest that GM volume or asymmetry in the target area of active rTMS treatment (DLPFC region in this study) may be a weak predictor of rTMS treatment efficacy. These results need more data to draw more robust conclusions.

High somatic mutations in circulating tumor DNA predict response of metastatic pancreatic ductal adenocarcinoma to first-line nab-paclitaxel plus S-1: prospective study.

AIMS: We previously showed that the nab-paclitaxel plus S-1 (NPS) regimen had promising effects against metastatic pancreatic ducal adenocarcinoma (mPDAC), whose efficacy however could not be precisely predicted by routine biomarkers. This prospective study aimed to investigate the values of mutations in circulating tumor DNA (ctDNA) and their dynamic changes in predicting response of mPDAC to NPS chemotherapy. METHODS: Paired tumor tissue and blood samples were prospectively collected from patients with mPDAC receiving first-line NPS chemotherapy, and underwent next-generation sequencing with genomic profiling of 425 genes for ctDNA. High mutation allelic frequency (MAF) was defined as ≥ 30% and ≥ 5% in tumor tissue and blood, respectively. Kappa statistics were used to assess agreement between mutant genes in tumor and ctDNA. Associations of mutations in ctDNA and their dynamic changes with tumor response, overall survival (OS), and progression-free survival (PFS) were assessed using the Kaplan-Meier method, multivariable-adjusted Cox proportional hazards regression, and longitudinal data analysis. RESULTS: 147 blood samples and 43 paired tumor specimens from 43 patients with mPDAC were sequenced. The most common driver genes with high MAF were KRAS (tumor, 35%; ctDNA, 37%) and TP53 (tumor, 37%; ctDNA, 33%). Mutation rates of KRAS and TP53 in ctDNA were significantly higher in patients with liver metastasis, with baseline CA19-9 ≥ 2000 U/mL, and/or without an early CA19-9 response. κ values for the 5 most commonly mutated genes between tumor and ctDNA ranged from 0.48 to 0.76. MAFs of the genes mostly decreased sequentially during subsequent measurements, which significantly correlated with objective response, with an increase indicating cancer progression. High mutations of KRAS and ARID1A in both tumor and ctDNA, and of TP53, CDKN2A, and SMAD4 in ctDNA but not in tumor were significantly associated with shorter survival. When predicting 6-month OS, AUCs for the 5 most commonly mutated genes in ctDNA ranged from 0.59 to 0.84, larger than for genes in tumor (0.56 to 0.71) and for clinicopathologic characteristics (0.51 to 0.68). Repeated measurements of mutations in ctDNA significantly differentiated survival and tumor response. Among the 31 patients with ≥ 2 ctDNA tests, longitudinal analysis of changes in gene MAF showed that ctDNA progression was 60 and 58 days ahead of radiologic and CA19-9 progression for 48% and 42% of the patients, respectively. CONCLUSIONS: High mutations of multiple driving genes in ctDNA and their dynamic changes could effectively predict response of mPDAC to NPS chemotherapy, with promising reliable predictive performance superior to routine clinicopathologic parameters. Inspiringly, longitudinal ctDNA tracking could predict disease progression about 2 months ahead of radiologic or CA19-9 evaluations, with the potential to precisely devise individualized therapeutic strategies for mPDAC.

Modulator of TMB-associated immune infiltration (MOTIF) predicts immunotherapy response and guides combination therapy.

Patients with high tumor mutational burden (TMB) levels do not consistently respond to immune checkpoint inhibitors (ICIs), possibly because a high TMB level does not necessarily result in adequate infiltration of CD8+ T cells. Using bulk ribonucleic acid sequencing (RNA-seq) data from 9311 tumor samples across 30 cancer types, we developed a novel tool called the modulator of TMB-associated immune infiltration (MOTIF), which comprises genes that can determine the extent of CD8+ T cell infiltration prompted by a certain TMB level. We confirmed that MOTIF can accurately reflect the integrity and defects of the cancer-immunity cycle. By analyzing 84 human single-cell RNA-seq datasets from 32 types of solid tumors, we revealed that MOTIF can provide insights into the diverse roles of various cell types in the modulation of CD8+ T cell infiltration. Using pretreatment RNA-seq data from 13 ICI-treated cohorts, we validated the use of MOTIF in predicting CD8+ T cell infiltration and ICI efficacy. Among the components of MOTIF, we identified EMC3 as a negative regulator of CD8+ T cell infiltration, which was validated via in vivo studies. Additionally, MOTIF provided guidance for the potential combinations of programmed death 1 blockade with certain immunostimulatory drugs to facilitate CD8+ T cell infiltration and improve ICI efficacy.

[Predictive Value of Peripheral Blood Biomarkers in the Treatment of 
Lung Cancer Patients with Anti PD-1 Immunotherapy].

BACKGROUND: The application of programmed cell death 1 (PD-1)/programmed cell death ligand 1 (PD-L1) antibodies has greatly improved the clinical outcomes of lung cancer patients. Here, we retrospectively analyzed the efficacy of PD-1 antibody therapy in locally advanced non-surgical or metastatic lung cancer patients, and preliminarily explored the correlation between peripheral blood biomarkers and clinical responses. METHODS: We conducted a single center study that included 61 IIIA-IV lung cancer patients who received PD-1 antibody treatment from March 2020 to December 2021, and collected the medical record data on PD-1 antibody first-line or second-line treatment. The levels of multiple Th1 and Th2 cytokines in the patient's peripheral blood serum, as well as the phenotype of peripheral blood T cells, were detected and analyzed. RESULTS: All the patients completed at least 2 cycles of PD-1 monoclonal antibody treatment. Among them, 42 patients (68.9%) achieved partial response (PR); 7 patients (11.5%) had stable disease (SD); and 12 patients (19.7%) had progressive disease (PD). The levels of peripheral blood interferon gamma (IFN-γ) (P=0.023), tumor necrosis factor α (TNF-α) (P=0.007) and interleukin 5 (IL-5) (P=0.002) before treatment were higher in patients of the disease control rate (DCR) (PR+SD) group than in the PD group. In addition, the decrease in absolute peripheral blood lymphocyte count after PD-1 antibody treatment was associated with disease progression (P=0.023). Moreover, the levels of IL-5 (P=0.0027) and IL-10 (P=0.0208) in the blood serum after immunotherapy were significantly increased compared to baseline. CONCLUSIONS: Peripheral blood serum IFN-γ, TNF-α and IL-5 in lung cancer patients have certain roles in predicting the clinical efficacy of anti-PD-1 therapy. The decrease in absolute peripheral blood lymphocyte count in lung cancer patients is related to disease progression, but large-scale prospective studies are needed to further elucidate the value of these biomarkers.

Neutrophil extracellular traps in relationship to efficacy of systemic therapy for metastatic renal cell carcinoma.

BACKGROUND: The efficacy of systemic therapy regimens, such as immune checkpoint inhibitors and tyrosine kinase inhibitors (IO-TKI) and targeted therapy, for metastatic clear cell renal cell carcinoma (ccRCC) remains unpredictable due to the lack of effective biomarkers. Neutrophil extracellular trap (NET) plays an important role in promoting ccRCC. This study explores the NET predictive value of the efficacy in metastatic ccRCC. METHODS: In this retrospective study, patients with metastatic ccRCC who received targeted drugs and IO-TKI were included. Immunofluorescence staining was utilized to quantify the levels of tissue NETs through cell counts of H3Cit(+) and MPO(+) cells. RESULTS: A total of 183 patients with metastatic ccRCC were enrolled, including 150 patients who received TKIs and 33 patients who received IO-TKI. The levels of NETs in tumor tissue were significantly higher than in para-tumor tissue (p < 0.001). In terms of predicting drug efficacy, a correlation between NET levels and progression-free survival (PFS) was observed in the TKI with metachronous metastasis group (HR 1.73 [95% CI 1.02-2.91], log-rank p = 0.037), while no correlation was observed in the TKI with synchronous metastasis group and IO-TKI group. Regarding overall survival (OS), activated NET levels were associated with poor OS in both TKI (HR 1.60 [95% CI 1.05-2.43], log-rank p = 0.017) and IO-TKI group (HR 4.35 [95% CI 1.06-17.82], log-rank p =0.047). IMDC score (HR 1.462 [95% CI 1.030-2.075], p = 0.033) and tumor tissue NET levels (HR 1.733 [95% CI 1.165-2.579], p = 0.007) were independent prognostic risk factors for OS in patients with metastatic ccRCC.NET level was associated with poor OS in both TKI (HR 1.60 [95% CI 1.05-2.43], log-rank p = 0.017). CONCLUSIONS: The active NET levels in tumor tissue can predict drug efficacy in patients with metastatic ccRCC who received systemic therapy. Elevated levels of NETs in tumor tissue were also associated with poor efficacy in OS.

Predicting acupuncture efficacy for major depressive disorder using baseline clinical variables: A machine learning study.

Acupuncture is a viable treatment option for major depressive disorder (MDD). However, its effectiveness varies among patients. This study aimed to develop a model to predict the efficacy of acupuncture therapy for MDD using machine learning and baseline clinical variables. A total of 124 patients with MDD from five research centers were included in our machine learning study. All patients underwent acupuncture treatment for 6 weeks and the efficacy of the treatment was evaluated using the Hamilton Depression Scale-17 (HAMD-17). The max-relevance and min-redundancy (mRMR) algorithm and Pearson correlation analysis were used for selecting 11 significant features from 26 baseline clinical variables for model training. We compared the performance of five machine learning models, including logistic regression, support vector machine, K-nearest neighbor, random forest, and XgBoost, in predicting the effect of acupuncture in relieving major depression. Among the five models, XgBoost performed the best with an area under the receiver operating characteristic curve (AUC) of 0.835, an accuracy of 0.730, a sensitivity of 0.670, a specificity of 0.774, and an F1 score of 0.751. The key predictive variables identified were anxiety score in the self-rating depression scale (SDS), the traditional Chinese medicine syndrome of deficiency in both heart and spleen, and body mass index (BMI). The study demonstrates that the developed model can help physicians predict the patients who will benefit from acupuncture treatment, which is of positive significance for improving the clinical efficacy of acupuncture on MDD.

PMSG-Net: A priori-guided multilevel graph transformer fusion network for immunotherapy efficacy prediction.

In the case of specific immunotherapy regimens and access to pre-treatment CT scans, developing reliable, interpretable intelligent image biomarkers to predict efficacy is essential for physician decision-making and patient treatment selection. However, varying levels of prognosis show a similar appearance on CT scans. It becomes challenging to stratify patients by a single pre-treatment CT scan when presenting subtle differences in images for experienced experts and existing prognostic classification methods. In addition, the pattern of peri-tumoural radiological structures also determines the patient's response to ICIs. Therefore, it is essential to develop a method that focuses on the clinical priori features of the tumour edges but also makes full use of the rich information within the 3D tumour. This paper proposes a priori-guided multilevel graph transformer fusion network (PMSG-Net). Specifically, a graph convolutional network is first used to obtain a feature representation of the tumour edge, and complementary information from that detailed representation is used to enhance the global representation. In the tumour global representation branch (MSGNet), we designed the cascaded scale-enhanced swin transformer to obtain attributes of graph nodes, and efficiently learn and model spatial dependencies and semantic connections at different scales through multi-hop context-aware attention (MCA), yielding a richer global semantic representation. To our knowledge, this is the first attempt to use graph neural networks to predict the efficacy of immunotherapy, and the experimental results show that this method outperforms the current mainstream methods.

Peripheral blood mononuclear cell- transcriptome signatures of atopic dermatitis and prediction for the efficacy of dupilumab.

BACKGROUND: Few studies have explored transcriptome of the peripheral blood mononuclear cells (PBMCs) of atopic dermatitis (AD). Parameters for prediction of the efficacy of dupilumab in AD remain obscure. OBJECTIVE: To explore transcriptome signature of the PBMCs from Chinese AD patients and the usage in predication for the efficacy of dupilumab. METHODS: A total of 56 moderate-to-severe adult AD patients were enrolled and followed up for 16 week-dupilumab treatment. PBMCs samples were collected at baseline and 16 weeks after dupilumab treatment. Thirty-five patients were subjected to RNA-sequencing. Weighted gene co-expression network analysis (WGCNA) was used to find genes for prediction of dupilumab efficacy, which was validated in the rest 21 AD patients. Another 30 healthy individuals were enrolled and subjected to RNA-sequencing as healthy controls. RESULTS: Upregulation of the T helper (Th) 2/Th22 pathway, Th17 antimicrobial genes, and natural T-regulatory cell abundance in the PBMCs of AD cases was observed, whereas TGF-ß signaling and NK-cell signaling were decreased. Dupilumab treatment reversed the increase in the expression of Th2 cytokine receptors. WGCNA identified two immune-related modules that were correlated significantly with the efficacy of dupilumab. Hub gene MAP2K3 and UBE2L3 of these two modules demonstrated potential predictive ability for efficacy in the RNA-sequencing group by Spearman correlation, ROC analysis, and regression analysis, which was further validated in additional 21 AD cases. CONCLUSION: We firstly revealed the molecular phenotype of PBMCs in Chinese patients with AD, and uncovered two molecules that might be useful for prediction of the efficacy of dupilumab.

Advances in efficacy prediction and monitoring of neoadjuvant immunotherapy for non-small cell lung cancer.

The use of immune checkpoint inhibitors (ICIs) has become mainstream in the treatment of non-small cell lung cancer (NSCLC). The idea of harnessing the immune system to fight cancer is fast developing. Neoadjuvant treatment in NSCLC is undergoing unprecedented change. Chemo-immunotherapy combinations not only seem to achieve population-wide treating coverage irrespective of PD-L1 expression but also enable achieving a pathological complete response (pCR). Despite these recent advancements in neoadjuvant chemo-immunotherapy, not all patients respond favorably to treatment with ICIs plus chemo and may even suffer from severe immune-related adverse effects (irAEs). Similar to selection for target therapy, identifying patients most likely to benefit from chemo-immunotherapy may be valuable. Recently, several prognostic and predictive factors associated with the efficacy of neoadjuvant immunotherapy in NSCLC, such as tumor-intrinsic biomarkers, tumor microenvironment biomarkers, liquid biopsies, microbiota, metabolic profiles, and clinical characteristics, have been described. However, a specific and sensitive biomarker remains to be identified. Recently, the construction of prediction models for ICI therapy using novel tools, such as multi-omics factors, proteomic tests, host immune classifiers, and machine learning algorithms, has gained attention. In this review, we provide a comprehensive overview of the different positive prognostic and predictive factors in treating preoperative patients with ICIs, highlight the recent advances made in the efficacy prediction of neoadjuvant immunotherapy, and provide an outlook for joint predictors.

Hierarchical multi-omics data integration and modeling predict cell-specific chemical proteomics and drug responses.

Drug-induced phenotypes result from biomolecular interactions across various levels of a biological system. Characterization of pharmacological actions therefore requires integration of multi-omics data. Proteomics profiles, which may more directly reflect disease mechanisms and biomarkers than transcriptomics, have not been widely exploited due to data scarcity and frequent missing values. A computational method for inferring drug-induced proteome patterns would therefore enable progress in systems pharmacology. To predict the proteome profiles and corresponding phenotypes of an uncharacterized cell or tissue type that has been disturbed by an uncharacterized chemical, we developed an end-to-end deep learning framework: TransPro. TransPro hierarchically integrated multi-omics data, in line with the central dogma of molecular biology. Our in-depth assessments of TransPro's predictions of anti-cancer drug sensitivity and drug adverse reactions reveal that TransPro's accuracy is on par with that of experimental data. Hence, TransPro may facilitate the imputation of proteomics data and compound screening in systems pharmacology.

Immune-related adverse events correlate with the efficacy of PD-1 inhibitors combination therapy in advanced cholangiocarcinoma patients: A retrospective cohort study.

Background: Whether irAEs can predict the efficacy of PD-1 inhibitors in cholangiocarcinoma (CCA) has not been assessed. Therefore, this study aims to investigate the correlation between irAEs and the therapeutic effect of PD-1 inhibitors combination therapy in patients with advanced CCA. Methods: All patients with CCA who were consecutively admitted to the inpatient unit of our hospital and received PD-1 inhibitors combination therapy between September 2020 and April 2022 were screened. In total, 106 patients with CCA were screened out. We then followed up these patients until October 2022. Due to perioperative use (n=28), less than 2 cycles of PD-1 inhibitor therapy (n=9), incomplete data (n=8) and no pathological report (n=2), 59 patients were included in the final analysis. The patients were divided into the irAEs cohort and the non-irAEs cohort according to whether they experienced irAEs or not. The Log-Rank test was performed to compare the difference in survival time between these two cohorts. We then applied multivariate COX regression analysis to investigate whether irAEs were independent prognostic factors for survival in patients with advanced CCA. Results: Finally, 32 patients were included in the irAEs cohort and 27 patients in the non-irAEs cohort. A total of 32 patients (54.2%) had any-grade irAEs, of which 4 patients (6.8%) had grade 3-4 irAEs. The most common irAEs were thyroid toxicity (30.5%) and dermatologic toxicity (30.5%). There were no notable differences in demographics and clinical characteristics between the irAEs and non-irAEs cohorts, except for total bilirubin level (P=0.026) and relapse (P=0.016). The disease control rate (DCR) in the irAEs cohort was higher than in the non-irAEs cohort (90.6% vs 70.4%, P=0.047). Median overall survival (OS) and median progression-free survival (PFS) were better in the irAEs cohort than in the non-irAEs cohort (OS: 21.2 vs 10.0 months, P<0.001; PFS: 9.0 vs 4.4 months, P=0.003). Multivariate COX regression analysis showed that irAEs were independent prognostic factors for OS and PFS (OS: HR=0.133, 95% CI: 0.039-0.452, P=0.001; PFS: HR=0.435, 95% CI: 0.202-0.934, P=0.033). Conclusion: IrAEs correlated with improved DCR, OS, and PFS in advanced CCA patients receiving PD-1 inhibitors combination therapy.

Association analysis of gut microbiota and efficacy of SSRIs antidepressants in patients with major depressive disorder.

BACKGROUND: Relevant studies have shown that gut microbiome plays an important role in the occurrence, development and treatment of major depressive disorder (MDD). Many studies have also shown that, selective serotonin reuptake inhibitors (SSRIs) antidepressants can improve the symptoms of depression by changing the distribution of gut microbiome, Here we investigated whether a distinct gut microbiome was associated with Major depressive disorder (MDD), and how it was modulated by SSRIs antidepressants. METHOD: In this study, we analyzed the gut microbiome composition of 62 patients with first-episode MDD and 41 matched healthy controls, before SSRIs antidepressants treatment, using 16S rRNA gene sequencing. MDD patients characterized as treatment-resistant (TR) or responders (R) to antidepressants by score reduction rate were ≥50 % after SSRIs antidepressants treatment for eight weeks. RESULTS: LDA effect size (LEfSe) analysis found that there were 50 different bacterial groups among the three groups, of which 19 genera were mainly at the genus level. The relative abundance of 12 genera increased in the HCs group, 5 genera in the R group increased in relative abundance, and 2 genera in the TR group increased in relative abundance. The correlation analysis of 19 bacterial genera and the score reduction rate showed that Blautia, Bifidobacterium and Coprococcus with higher relative abundance in the treatment effective group were related to the efficacy of SSRIs antidepressants. CONCLUSIONS: Patients with MDD have a distinct gut microbiome that changes after SSRIs antidepressants treatment. Dysbiosis could be a new therapeutic target and prognostic tool for the treatment of patients with MDD.

Epithelial-mesenchymal transition-related gene prognostic index and phenotyping clusters for hepatocellular carcinoma patients.

Epithelial-mesenchymal transition (EMT) contributes to high tumor heterogeneity and the immunosuppressive environment of the HCC tumor microenvironment (TME). Here, we developed EMT-related genes phenotyping clusters and systematically evaluated their impact on HCC prognosis, the TME, and drug efficacy prediction. We identified HCC specific EMT-related genes using weighted gene co-expression network analysis (WGCNA). An EMT-related genes prognostic index (EMT-RGPI) capable of effectively predicting HCC prognosis was then constructed. Consensus clustering of 12 HCC specific EMT-related hub genes uncovered two molecular clusters C1 and C2. Cluster C2 preferentially associated with unfavorable prognosis, higher stemness index (mRNAsi) value, elevated immune checkpoint expression, and immune cell infiltration. The TGF-ß signaling, EMT, glycolysis, Wnt ß-catenin signaling, and angiogenesis were markedly enriched in cluster C2. Moreover, cluster C2 exhibited higher TP53 and RB1 mutation rates. The TME subtypes and tumor immune dysfunction and exclusion (TIDE) score showed that cluster C1 patients responded well to immune checkpoint inhibitors (ICIs). Half-maximal inhibitory concentration (IC50) revealed that cluster C2 patients were more sensitive to chemotherapeutic and antiangiogenic agents. These findings may guide risk stratification and precision therapy for HCC patients.