Development and Validation of an Interpretable Machine Learning Prediction Model for Total Pathological Complete Response after Neoadjuvant Chemotherapy in Locally Advanced Breast Cancer: Multicenter Retrospective Analysis.

Objective: This study aims to develop an interpretable machine learning (ML) model to accurately predict the probability of achieving total pathological complete response (tpCR) in patients with locally advanced breast cancer (LABC) following neoadjuvant chemotherapy (NAC). Methods: This multi-center retrospective study included pre-NAC clinical pathology data from 698 LABC patients. Post-operative pathological outcomes divided patients into tpCR and non-tpCR groups. Data from 586 patients at Shanghai Ruijin Hospital were randomly assigned to a training set (80%) and a test set (20%). In comparison, data from our hospital's remaining 112 patients were used for external validation. Variable selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis. Predictive models were constructed using six ML algorithms: decision trees, K-nearest neighbors (KNN), support vector machine, light gradient boosting machine, and extreme gradient boosting. Model efficacy was assessed through various metrics, including receiver operating characteristic (ROC) curves, precision-recall (PR) curves, confusion matrices, calibration plots, and decision curve analysis (DCA). The best-performing model was selected by comparing the performance of different algorithms. Moreover, variable relevance was ranked using the SHapley Additive exPlanations (SHAP) technique to improve the interpretability of the model and solve the "black box" problem. Results: A total of 191 patients (32.59%) achieved tpCR following NAC. Through LASSO regression analysis, five variables were identified as predictive factors for model construction, including tumor size, Ki-67, molecular subtype, targeted therapy, and chemotherapy regimen. The KNN model outperformed the other five classifier algorithms, achieving area under the curve (AUC) values of 0.847 (95% CI: 0.809-0.883) in the training set, 0.763 (95% CI: 0.670-0.856) in the test set, and 0.665 (95% CI: 0.555-0.776) in the external validation set. DCA demonstrated that the KNN model yielded the highest net advantage through a wide range of threshold probabilities in both the training and test sets. Furthermore, the analysis of the KNN model utilizing SHAP technology demonstrated that targeted therapy is the most crucial factor in predicting tpCR. Conclusion: An ML prediction model using clinical and pathological data collected before NAC was developed and verified. This model accurately predicted the probability of achieving a tpCR in patients with LABC after receiving NAC. SHAP technology enhanced the interpretability of the model and assisted in clinical decision-making and therapy optimization.

Genome-Wide Identification and Expression Profile Analysis of the Phenylalanine Ammonia-Lyase Gene Family in Hevea brasiliensis.

The majority of the world's natural rubber comes from the rubber tree (Hevea brasiliensis). As a key enzyme for synthesizing phenylpropanoid compounds, phenylalanine ammonia-lyase (PAL) has a critical role in plant satisfactory growth and environmental adaptation. To clarify the characteristics of rubber tree PAL family genes, a genome-wide characterization of rubber tree PALs was conducted in this study. Eight PAL genes (HbPAL1-HbPAL8), which spread over chromosomes 3, 7, 8, 10, 12, 13, 14, 16, and 18, were found to be present in the genome of H. brasiliensis. Phylogenetic analysis classified HbPALs into groups I and II, and the group I HbPALs (HbPAL1-HbPAL6) displayed similar conserved motif compositions and gene architectures. Tissue expression patterns of HbPALs quantified by quantitative real-time PCR (qPCR) proved that distinct HbPALs exhibited varying tissue expression patterns. The HbPAL promoters contained a plethora of cis-acting elements that responded to hormones and stress, and the qPCR analysis demonstrated that abiotic stressors like cold, drought, salt, and H2O2-induced oxidative stress, as well as hormones like salicylic acid, abscisic acid, ethylene, and methyl jasmonate, controlled the expression of HbPALs. The majority of HbPALs were also regulated by powdery mildew, anthracnose, and Corynespora leaf fall disease infection. In addition, HbPAL1, HbPAL4, and HbPAL7 were significantly up-regulated in the bark of tapping panel dryness rubber trees relative to that of healthy trees. Our results provide a thorough comprehension of the characteristics of HbPAL genes and set the groundwork for further investigation of the biological functions of HbPALs in rubber trees.

Integrated physiology, transcriptome and proteome analyses highlight the potential roles of multiple hormone-mediated signaling pathways involved in tapping panel dryness in rubber tree.

Currently, one of the most serious threats to rubber tree is the tapping panel dryness (TPD) that greatly restricts natural rubber production. Over-tapping or excessive ethephon stimulation is regarded as the main cause of TPD occurrence. Although extensive studies have been carried out, the molecular mechanism underlying TPD remains puzzled. An attempt was made to compare the levels of endogenous hormones and the profiles of transcriptome and proteome between healthy and TPD trees. Results showed that most of endogenous hormones such as jasmonic acid (JA), 1-aminocyclopropanecarboxylic acid (ACC), indole-3-acetic acid (IAA), trans-zeatin (tZ) and salicylic acid (SA) in the barks were significantly altered in TPD-affected rubber trees. Accordingly, multiple hormone-mediated signaling pathways were changed. In total, 731 differentially expressed genes (DEGs) and 671 differentially expressed proteins (DEPs) were identified, of which 80 DEGs were identified as putative transcription factors (TFs). Further analysis revealed that 12 DEGs and five DEPs regulated plant hormone synthesis, and that 16 DEGs and six DEPs were involved in plant hormone signal transduction pathway. Nine DEGs and four DEPs participated in rubber biosynthesis and most DEGs and all the four DEPs were repressed in TPD trees. All these results highlight the potential roles of endogenous hormones, signaling pathways mediated by these hormones and rubber biosynthesis pathway in the defense response of rubber trees to TPD. The present study extends our understanding of the nature and mechanism underlying TPD and provides some candidate genes and proteins related to TPD for further research in the future.