Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing computational methods for preclinical and clinical cancer drug response(CDR)prediction,chal-lenges remain regarding the generalization of new drugs that are unseen in the training set.Herein,we propose a multimodal fusion deep learning(DL)model called drug-target and single-cell language based CDR(DTLCDR)to predict preclinical and clinical CDRs.The model integrates chemical descriptors,mo-lecular graph representations,predicted protein target profiles of drugs,and cell line expression profiles with general knowledge from single cells.Among these features,a well-trained drug-target interaction(DTI)prediction model is used to generate target profiles of drugs,and a pretrained single-cell language model is integrated to provide general genomic knowledge.Comparison experiments on the cell line drug sensitivity dataset demonstrated that DTLCDR exhibited improved generalizability and robustness in predicting unseen drugs compared with previous state-of-the-art baseline methods.Further ablation studies verified the effectiveness of each component of our model,highlighting the significant contribution of target information to generalizability.Subsequently,the ability of DTLCDR to predict novel molecules was validated through in vitro cell experiments,demonstrating its potential for real-world applications.Moreover,DTLCDR was transferred to the clinical datasets,demonstrating satisfactory performance in the clinical data,regardless of whether the drugs were included in the cell line dataset.Overall,our results suggest that the DTLCDR is a promising tool for personalized drug discovery.

Focal therapy has emerged as an alternative to surgical treatment for selected renal tumors.The core principle of this approach lies in the local destruction of tumor tissue through physical or chemical means to achieve tumor control.Focal therapy is particularly applicable to patients with tumors ≤4 cm in diameter who are unfit for surgery or anesthesia due to advanced age,comorbidities,solitary kidney,or renal insufficiency,as well as those with recurrent tumors after prior partial nephrectomy.This review summarizes the mechanisms,advantages,limitations,and clinical efficacy of six focal therapy modalities for renal tumors,including radiofrequency ablation,cryoablation,microwave ablation,irreversible electroporation,high-intensity focused ultrasound,and stereotactic ablative radiotherapy.The aim is to provide reference for achieving individualized and precise clinical management.

Accurate prediction of drug responses in cancer cell lines (CCLs) and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine. Despite the rapid advancements in existing computational methods for preclinical and clinical cancer drug response (CDR) prediction, challenges remain regarding the generalization of new drugs that are unseen in the training set. Herein, we propose a multimodal fusion deep learning (DL) model called drug-target and single-cell language based CDR (DTLCDR) to predict preclinical and clinical CDRs. The model integrates chemical descriptors, molecular graph representations, predicted protein target profiles of drugs, and cell line expression profiles with general knowledge from single cells. Among these features, a well-trained drug-target interaction (DTI) prediction model is used to generate target profiles of drugs, and a pretrained single-cell language model is integrated to provide general genomic knowledge. Comparison experiments on the cell line drug sensitivity dataset demonstrated that DTLCDR exhibited improved generalizability and robustness in predicting unseen drugs compared with previous state-of-the-art baseline methods. Further ablation studies verified the effectiveness of each component of our model, highlighting the significant contribution of target information to generalizability. Subsequently, the ability of DTLCDR to predict novel molecules was validated through in vitro cell experiments, demonstrating its potential for real-world applications. Moreover, DTLCDR was transferred to the clinical datasets, demonstrating satisfactory performance in the clinical data, regardless of whether the drugs were included in the cell line dataset. Overall, our results suggest that the DTLCDR is a promising tool for personalized drug discovery.

Focal therapy has emerged as an alternative to surgical treatment for selected renal tumors.The core principle of this approach lies in the local destruction of tumor tissue through physical or chemical means to achieve tumor control.Focal therapy is particularly applicable to patients with tumors ≤4 cm in diameter who are unfit for surgery or anesthesia due to advanced age,comorbidities,solitary kidney,or renal insufficiency,as well as those with recurrent tumors after prior partial nephrectomy.This review summarizes the mechanisms,advantages,limitations,and clinical efficacy of six focal therapy modalities for renal tumors,including radiofrequency ablation,cryoablation,microwave ablation,irreversible electroporation,high-intensity focused ultrasound,and stereotactic ablative radiotherapy.The aim is to provide reference for achieving individualized and precise clinical management.

Background::Bladder cancer, characterized by a high potential of tumor recurrence, has high lifelong monitoring and treatment costs. To date, tumor cells with intrinsic softness have been identified to function as cancer stem cells in several cancer types. Nonetheless, the existence of soft tumor cells in bladder tumors remains elusive. Thus, our study aimed to develop a microbarrier microfluidic chip to efficiently isolate deformable tumor cells from distinct types of bladder cancer cells.Methods::The stiffness of bladder cancer cells was determined by atomic force microscopy (AFM). The modified microfluidic chip was utilized to separate soft cells, and the 3D Matrigel culture system was to maintain the softness of tumor cells. Expression patterns of integrin β8 (ITGB8), protein kinase B (AKT), and mammalian target of rapamycin (mTOR) were determined by Western blotting. Double immunostaining was conducted to examine the interaction between F-actin and tripartite motif containing 59 (TRIM59). The stem-cell-like characteristics of soft cells were explored by colony formation assay and in vivo studies upon xenografted tumor models. Results::Using our newly designed microfluidic approach, we identified a small fraction of soft tumor cells in bladder cancer cells. More importantly, the existence of soft tumor cells was confirmed in clinical human bladder cancer specimens, in which the number of soft tumor cells was associated with tumor relapse. Furthermore, we demonstrated that the biomechanical stimuli arising from 3D Matrigel activated the F-actin/ITGB8/TRIM59/AKT/mTOR/glycolysis pathways to enhance the softness and tumorigenic capacity of tumor cells. Simultaneously, we detected a remarkable up-regulation in ITGB8, TRIM59, and phospho-AKT in clinical bladder recurrent tumors compared with their non-recurrent counterparts.Conclusions::The ITGB8/TRIM59/AKT/mTOR/glycolysis axis plays a crucial role in modulating tumor softness and stemness. Meanwhile, the soft tumor cells become more sensitive to chemotherapy after stiffening, that offers new insights for hampering tumor progression and recurrence.