Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “response prediction”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources
PubMed2025

Multimodal deep learning for immunotherapy response prediction and biomarker discovery in non-small cell lung cancer.

OBJECTIVE: Immunotherapy has emerged as a promising treatment for advanced non-small cell lung cancer (NSCLC), but accurately predicting which patients will benefit from it remains a major clinical challenge. To address this, we aim to develop a novel multimodal method, DeepAFM, that integrates histopathology, genomic features, and clinical information to predict patient responses to anti-PD-(L)1 immunotherapy. MATERIALS AND METHODS: A total of 93 patients with advanced NSCLC were included in this study. Histopathological whole-slide images were processed using a self-supervised VQVAE2 for representation learning. PCA and K-means clustering were then applied for dimensionality reduction and feature grouping. Key regions of interest were visualized through permutation importance evaluation and color-coding techniques. The extracted histopathological features, along with genomic alterations and clinical variables, were integrated into the DeepAFM multimodal prediction model. RESULTS: The DeepAFM achieved a high predictive performance with an area under the curve (AUC) of 0.77 (95% confidence interval: 0.69-1.00). Attention-based heatmaps revealed that the model could identify critical pathological patterns, genomic mutations, and clinical indicators associated with patient responses to immunotherapy. DISCUSSION: The integration of multimodal data enabled the model to capture complex interactions among pathology, genomics, and clinical characteristics, enhancing the interpretability and predictive power of immunotherapy response prediction. The visualization techniques facilitated the identification of biologically meaningful features and potential biomarkers. CONCLUSION: This study demonstrates the effectiveness of the DeepAFM in predicting responses to immunotherapy in advanced NSCLC. The approach not only improves prediction accuracy but also provides valuable insights for personalized treatment strategies and biomarker discovery.

Humans↗
PubMed2026

A Knowledge-Enhanced Multimodal Framework with Genomic Reconstruction for DLBCL Drug Response Prediction.

Diffuse large B-cell lymphoma (DLBCL) exhibits substantial biological heterogeneity, leading to pronounced variability in patient response to therapy. Accurate drug response prediction is therefore critical for precision treatment but remains challenging in clinical settings where genomic sequencing, a highly informative modality, is frequently incomplete. Existing methods, often developed from cell-line pharmacogenomic datasets or single-modality data, typically assume fully observed molecular profiles and thus show limited robustness under missing genomic data. To address this limitation, a knowledge-enhanced multimodal framework with genomic reconstruction (KeM-DRP) is proposed for individualized drug response prediction in DLBCL. The framework models the central role of genomics by integrating biological prior knowledge through a gene-pathway-biological process hierarchy, enabling robust representation learning from sparse observations. To compensate for missing genomic measurements, a cross-modal genomic compensation module reconstructs genomically informed latent features from routinely available clinical modalities. Furthermore, a genomics-guided adaptive fusion strategy dynamically integrates heterogeneous modalities conditioned on observed or reconstructed genomic representation. Experiments on a real-world DLBCL cohort demonstrate that KeM-DRP consistently outperforms competitive baselines. The reconstructed genomic representation represents most predictive utility, highlighting the robustness and practical value of the framework under incomplete genomic data.

Journal Article↗
PubMed2025

Anticancer drug response prediction integrating multi-omics pathway-based difference features and multiple deep learning techniques.

Individualized prediction of cancer drug sensitivity is of vital importance in precision medicine. While numerous predictive methodologies for cancer drug response have been proposed, the precise prediction of an individual patient's response to drug and a thorough understanding of differences in drug responses among individuals continue to pose significant challenges. This study introduced a deep learning model PASO, which integrated transformer encoder, multi-scale convolutional networks and attention mechanisms to predict the sensitivity of cell lines to anticancer drugs, based on the omics data of cell lines and the SMILES representations of drug molecules. First, we use statistical methods to compute the differences in gene expression, gene mutation, and gene copy number variations between within and outside biological pathways, and utilized these pathway difference values as cell line features, combined with the drugs' SMILES chemical structure information as inputs to the model. Then the model integrates various deep learning technologies multi-scale convolutional networks and transformer encoder to extract the properties of drug molecules from different perspectives, while an attention network is devoted to learning complex interactions between the omics features of cell lines and the aforementioned properties of drug molecules. Finally, a multilayer perceptron (MLP) outputs the final predictions of drug response. Our model exhibits higher accuracy in predicting the sensitivity to anticancer drugs comparing with other methods proposed recently. It is found that PARP inhibitors, and Topoisomerase I inhibitors were particularly sensitive to SCLC when analyzing the drug response predictions for lung cancer cell lines. Additionally, the model is capable of highlighting biological pathways related to cancer and accurately capturing critical parts of the drug's chemical structure. We also validated the model's clinical utility using clinical data from The Cancer Genome Atlas. In summary, the PASO model suggests potential as a robust support in individualized cancer treatment. Our methods are implemented in Python and are freely available from GitHub (https://github.com/queryang/PASO).

Deep Learning↗
PubMed2026

Patient-derived organoids predict responses to chemotherapy and PARP inhibitors in advanced ovarian cancer.

BACKGROUND: While tumor organoids hold promise for personalized medicine, clinical validation of epithelial ovarian cancer (EOC) organoids as predictors of therapeutic efficacy-particularly for PARP inhibitors (PARPi)-remains unestablished. METHODS: Patient-derived organoids (PDOs) were established from treatment-naive EOC specimens and characterized by H&E staining, immunohistochemistry, and whole-exome sequencing. Drug sensitivity testing (DST) was performed using carboplatin, paclitaxel, and PARPi (olaparib and niraparib). Clinical homologous recombination deficiency (HRD) status was assessed by tumor sequencing. Organoid responses were prospectively compared to patient outcomes after first-line chemotherapy (carboplatin/paclitaxel) and PARPi maintenance. RESULTS: PDOs were successfully established from 21 of 30 patients (70%) across multiple EOC subtypes and preserved the histopathological features and genomic landscapes of their corresponding primary tumors. Organoid-based DST accurately predicted responses to first-line carboplatin/paclitaxel, with a sensitivity of 100% (95% CI 62.88-100%), specificity of 66.67% (95% CI 12.53-98.23%), accuracy of 91.67% (95% CI 61.52-99.79%), AUC of 0.95 (95% CI 0.85-1.00), and Cohen's kappa of 0.75 (95% CI 0.30-1.00). In evaluating PARPi response, organoids revealed discrepancies between genomic HRD status and actual drug responses. One HRD-positive PDO was PARPi-resistant, consistent with patient non-response, while two HRR-proficient PDOs showed PARPi sensitivity and corresponding clinical benefit. CONCLUSIONS: EOC-derived PDOs provide a robust platform for predicting chemotherapy response and offer added value in assessing PARPi efficacy beyond genomic profiling. Combination of organoid-based testing with genomic analysis may improve precision treatment strategies in EOC.

Humans↗
PubMed1975

Predicting response to endocrine therapy in human breast cancer: a hypothesis.

We hypothesize that the presence of progesterone receptors in human breast tumors may be a sensitive marker for predicting response to endocrine therapy. Progesterone receptors were found in 56 percent of tumors with estrogen receptors, but were absent in tumors without estrogen receptors. Preliminary clinical correlations show that only those breast tumors with progesterone receptors regressed after endocrine therapy.

Breast Neoplasms↗
PubMed1978

A survey study of the use of electropupillogram in predicting response to psychostimulants.

To confirm the conclusions from a previous study supporting the usefullness of electropupillogram (E.P.G.) in predicting clinical response, data from three separate studies with hyperkinetic and learning disabled (L.D.) children treated with stimulants were surveyed. Change in extent of pupillary contraction (E.C.) after a test dose of stimulant as measured by E.P.G. did not correlate significantly with actual clinical rating change (with one exception out of 14 correlations calculated). These negative results are reported with a reservation regarding their validity because of technical difficulties in data collection.

Adolescent↗
PubMed2026

Targeting cancer stem cells predicts response and reverses chemoresistance in ascites-derived ovarian cancer organoids.

BACKGROUND: Ovarian cancer (OC) is frequently diagnosed at an advanced stage, where tumor heterogeneity and rapid development of chemoresistance contribute to a poor prognosis. The lack of reliable predictive biomarkers further hinders the development of effective treatment strategies. Patient-derived organoids (PDOs) have recently emerged as promising preclinical models with the potential to predict therapeutic responses. METHODS: OC PDOs were generated from ascites samples representing diverse histological subtypes. Histological and genomic fidelity to parental tumors was confirmed through histopathological analysis and whole-exome sequencing. Drug sensitivity to cisplatin and poly (ADP-ribose) polymerase (PARP) inhibitors was evaluated and correlated with 1-year clinical outcomes. We also investigated the therapeutic efficacy of oncolytic herpes simplex virus 2 (OH2) both as a single agent and in combination with cisplatin. The expression of cancer stem cell (CSC) markers CD44 and ALDH1A1 under treatment conditions was analyzed using immunohistochemistry and flow cytometry. RESULTS: PDOs were successfully established with an 86.2% success rate. These PDOs faithfully recapitulated the histopathological and genomic features of their corresponding tumors, maintaining intratumoral heterogeneity, and were amenable to xenotransplantation. Drug sensitivity assays demonstrated that PDOs accurately predicted patient-specific responses to cisplatin and PARP inhibitors. OH2 exhibited direct cytotoxicity in both cisplatin-sensitive and cisplatin-resistant PDOs, reducing cell viability by 20-60%. Notably, the combination treatment with OH2 and cisplatin enhanced antitumor efficacy, resulting in a significant reduction of the CD44+CSC subpopulation. CONCLUSIONS: Ascites-derived OC PDOs represent a robust platform for individualized drug testing. The combination of OH2 and cisplatin offers a novel and effective strategy for circumventing chemoresistance in OC.

Female↗
PubMed2025

ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction.

Personalized cancer drug treatment is emerging as a frontier issue in modern medical research. Considering the genomic differences among cancer patients, determining the most effective drug treatment plan is a complex and crucial task. In response to these challenges, this study introduces the Adaptive Sparse Graph Contrastive Learning Network (ASGCL), an innovative approach to unraveling latent interactions in the complex context of cancer cell lines and drugs. The core of ASGCL is the GraphMorpher module, an innovative component that enhances the input graph structure via strategic node attribute masking and topological pruning. By contrasting the augmented graph with the original input, the model delineates distinct positive and negative sample sets at both node and graph levels. This dual-level contrastive approach significantly amplifies the model's discriminatory prowess in identifying nuanced drug responses. Leveraging a synergistic combination of supervised and contrastive loss, ASGCL accomplishes end-to-end learning of feature representations, substantially outperforming existing methodologies. Comprehensive ablation studies underscore the efficacy of each component, corroborating the model's robustness. Experimental evaluations further illuminate ASGCL's proficiency in predicting drug responses, offering a potent tool for guiding clinical decision-making in cancer therapy.

Humans↗
PubMed2026

Integrating clinical and genomic features to predict response to neoadjuvant therapy in microsatellite-stable rectal cancer.

BACKGROUND: Neoadjuvant therapy (NAT) has shifted rectal cancer management toward organ preservation. However, achieving a complete response (CR) for "watch-and-wait" strategies is hindered by high response heterogeneity. Although immunotherapy-combined NAT has expanded the candidate pools, the predictive significance of molecular alterations remains unclear. OBJECTIVES: This study aimed to evaluate clinical and genomic profiles of rectal cancer patients undergoing NAT to identify response predictors and to develop a nomogram for estimating CR probability. DESIGN: Retrospective, single-center cohort study. METHODS: This study included 437 patients with rectal adenocarcinoma at Fudan University Shanghai Cancer Center between December 2019 and March 2023. Patients underwent paired tumor and germline genomic sequencing (887-gene panel) before NAT. Logistic and Cox regression analyses were performed to identify clinical and genetic risk factors associated with tumor response and long-term survival. RESULTS: Of the 437 patients, 96.6% had microsatellite-stable (MSS) tumors. In the MSS locally advanced rectal cancer cohort (N = 307), the CR rate was 35.5%. Multivariate analysis identified immunotherapy-combined NAT (iTNT) (OR 4.41, 95% CI: 2.42-8.27), SYNE1 mutation (OR 2.12, 95% CI: 1.06-4.26), negative mesorectal fascia (MRF) status (OR 0.34, 95% CI: 0.17-0.66), and lower tumor location (OR 0.48, 95% CI: 0.27-0.84) as independent predictors of CR. KRAS mutation was the sole independent predictor of reduced disease-free survival (DFS; HR 1.93, 95% CI: (1.11-3.36), p = 0.020). KRAS G12D subtype was associated with the worst 2-year distant metastasis-free survival (71.3%) and exhibited a distinct predilection for lung metastasis. The clinical-genomic nomogram yielded strong discrimination (AUC = 0.705) and calibration, with favorable DCA net benefit. CONCLUSION: Clinical and genomic features jointly determine outcomes in MSS rectal cancer. SYNE1 mutation serves as a novel biomarker for CR, while KRAS mutations, especially the G12D subtype, identify patients at high risk for systemic relapse. The clinical-genomic nomogram facilitates individualized selection for organ-preservation strategies.

biomarker↗
PubMed2025

Biomarker-Based Nomogram to Predict Neoadjuvant Chemotherapy Response in Muscle-Invasive Bladder Cancer.

Background/Objectives: The aim of this study was to identify response prediction and prognostic biomarkers in muscle-invasive bladder cancer (MIBC) patients undergoing neoadjuvant chemotherapy (NAC). Methods: A retrospective multicentre study including 191 patients with MIBC who received NAC previous to radical cystectomy (RC) between 1996 and 2013. Gene expression patterns were analysed in 34 samples from transurethral resection of the bladder (TURB) using Illumina microarrays. The expression levels of 45 selected differentially expressed genes between responders and non-responders to NAC were validated by quantitative PCR in an independent cohort of 157 patients. Regression analysis was used to identify predictors of downstaging and relapse. A nomogram for predicting downstaging and relapse-including clinicopathological and gene expression variables-was developed. Results: The expression levels of 1352 transcripts differed between responders and non-responders to NAC. A nomogram based on the most predictive clinical variables (age, Tis (in situ), gender, history of NMIBC, and lymphadenopathy) and genes selected following the Akaike information criterion (AIC) (CBTB16, CHMP6, DDX54, CASP8, LOR, and PLEC) was then created. In addition, a three-gene expression prognostic model to predict tumour relapse was generated. This model was able to discriminate between two groups of patients with a significantly different probability of tumour relapse (HR: 2.11; CI: 1.16-3.83, p = 0.01). Conclusions: Our nomogram based on gene expression and clinical data is a useful tool to predict downstaging and tumour relapse after NAC in MIBC patients. Further validation is warranted.

bladder cancer↗
PubMed1979

Predicting the response of growth hormone-deficient children to long term treatment with human growth hormone.

A previous study showed that when GH-deficient children below the third percentile in height are treated with 0.168 U human GH (hGH)/kg BW3/4 for 10 days, their height increases by 0.3--1.9 cm during the next 8 weeks. The present study determined whether this acute response would predict the child's long term response to 1 yr of treatment with the same dose of hGH given three times a week. Eighteen GH-deficient children and adolescents, aged 8--16 yr, were measured every 2 weeks over 108 weeks. After a control period of 12 weeks (period 1), the patient received hGH for 10 days. During the remainder of the 12 weeks of period 2 and during the next 12 weeks (period 3), hGH was not given. Patients recieved hGH three times a week during periods 4 and 5 (24 weeks each). Periods 6 and 7 (12 weeks each) were posttreatment control periods. During periods 1, 3, 6, and 7, rate of growth was less than 0.2 cm/month. During period 2, the rate ranged between 0.1--0.8 cm/month. During periods 4 and 5, the growth rate ranged from 0.2--1.0 cm/month. Rate of growth during periods 4 and 5 (y) was related to rate during period 2 (x) by the equation y = 0.027 + 1.17 x. The correlation coefficient between y and x was 0.91 (P less than 0.001). The increment in height which will occur during 48 weeks of treatment can be predicted from the response to 10 days of treatment by this equation. The SE of the prediction averages +/- 1.2 cm/yr.

Adolescent↗
PubMed2025

Transfer learning with multiomics integration and deep neural networks reveals drug resistance mechanisms in cancer.

Drug resistance remains one of the primary challenges in effective cancer therapy. In this study, we employed a deep neural network (DNN)-based transfer learning (TL) approach to predict drug response and uncover drug resistance mechanisms. We integrated gene expression, somatic mutation, and copy number aberration (CNA) data with drug response profiles using multi-omics integration (MI). We used the Genomics of Drug Sensitivity in Cancer (GDSC) data for training and incorporated drugs with same pathways into the training models. We then evaluated drug response predictions on independent in-vivo PDX Encyclopedia (PDX) and ex-vivo the Cancer Genome Atlas (TCGA) datasets. In addition, we conducted pathway enrichment analyses to elucidate the mechanisms underlying drug resistance for paclitaxel, 5-fluorouracil (5-FU), gemcitabine, and cetuximab. We also applied Fisher's exact test (FET) to assess potential associations between drug resistance and the presence of mutations or CNAs. Our pan-drug models outperformed other methods based on the area under the precision-recall curve (AUCPR). Our pathway enrichment analyses revealed LDHB-mediated pyruvate metabolism and FYN-mediated focal adhesion might have pivotal roles in paclitaxel resistance, while PINK1-mediated mitophagy might be critical in 5-FU resistance. In addition to transcriptional activation, FET suggested that CNAs in LDHB and PINK1 may also be associated with resistance to paclitaxel and 5-FU, respectively. Furthermore, enrichment results for paclitaxel and cetuximab indicated shared resistance mechanisms between the two drugs. Importantly, our findings are consistent with prior experimental studies, providing literature-based validation of our results. Overall, our DNN-based TL approach achieved strong predictive performance across PDX & TCGA datasets and enrichment analyses provided valuable biological insights into drug resistance mechanisms.

Humans↗
PubMed2025

Individualized patient tumor organoids faithfully preserve human brain tumor ecosystems and predict patient response to therapy.

Tumor organoids are important tools for cancer research, but current models have drawbacks that limit their applications for predicting response to therapy. Here, we developed a fast, efficient, and complex culture system (IPTO, individualized patient tumor organoid) that accurately recapitulates the cellular and molecular pathology of human brain tumors. Patient-derived tumor explants were cultured in induced pluripotent stem cell (iPSC)-derived cerebral organoids, thus enabling culture of a wide range of human tumors in the central nervous system (CNS), including adult, pediatric, and metastatic brain cancers. Histopathological, genomic, epigenomic, and single-cell RNA sequencing (scRNA-seq) analyses demonstrated that the IPTO model recapitulates cellular heterogeneity and molecular features of original tumors. Crucially, we showed that the IPTO model predicts patient-specific drug responses, including resistance mechanisms, in a prospective patient cohort. Collectively, the IPTO model represents a major breakthrough in preclinical modeling of human cancers, which provides a path toward personalized cancer therapy.

Humans↗