Predicting response to immunotherapy in oral squamous cell carcinoma via a CT-based radiomics model.

BACKGROUND: To investigate whether radiomics models derived from pretreatment CT could help to predict response to immunotherapy in oral squamous cell carcinoma (OSCC). METHODS: Retrospectively, a total of 40 patients with measurable OSCC were included. The patients were divided into responder group and non-responder group according to the comparison of pre-treatment and post-treatment CT findings. Radiomics features were extracted from pre-treatment CT images, and optimal features were selected by univariate analysis and the least absolute shrinkage and selection operator (LASSO) regression analysis. Neural network, support vector machine, random forest and logistic regression models were used to predict response to immunotherapy in OSCC, and leave-one-out cross validation was employed to assess the performance of the classifiers. The area under the curve (AUC), accuracy, sensitivity and specificity were calculated to quantify the predictive efficacy. RESULTS: A total of 7 features were selected to build models upon machine learning methods. By comparing different machine learning based models, the neural network model achieved the best predictive ability, with an AUC of 0.864, an accuracy of 82.5%, a sensitivity of 82.5%, and a specificity of 82.5%. CONCLUSIONS: The pretreatment CT-based radiomics model showed good performance in predicting response to immunotherapy in OSCC. Pretreatment CT-based radiomics model might provide an alternative approach for the selection of patients who benefit from immunotherapy.

Phosphoproteomics predict response to midostaurin plus chemotherapy in independent cohorts of FLT3-mutated acute myeloid leukaemia.

BACKGROUND: Acute myeloid leukaemia (AML) is a bone marrow malignancy with poor prognosis. One of several treatments for AML is midostaurin combined with intensive chemotherapy (MIC), currently approved for FLT3 mutation-positive (FLT3-MP) AML. However, many patients carrying FLT3 mutations are refractory or experience an early relapse following MIC treatment, and might benefit more from receiving a different treatment. Development of a stratification method that outperforms FLT3 mutational status in predicting MIC response would thus benefit a large number of patients. METHODS: We employed mass spectrometry phosphoproteomics to analyse 71 diagnosis samples of 47 patients with FLT3-MP AML who subsequently received MIC. We then used machine learning to identify biomarkers of response to MIC, and validated the resulting predictive model in two independent validation cohorts (n = 20). FINDINGS: We identified three distinct phosphoproteomic AML subtypes amongst long-term survivors. The subtypes showed similar duration of MIC response, but different modulation of AML-implicated pathways, and exhibited distinct, highly-predictive biomarkers of MIC response. Using these biomarkers, we built a phosphoproteomics-based predictive model of MIC response, which we called MPhos. When applied to two retrospective real-world patient test cohorts (n = 20), MPhos predicted MIC response with 83% sensitivity and 100% specificity (log-rank p < 7∗10-5, HR = 0.005 [95% CI: 0-0.31]). INTERPRETATION: In validation, MPhos outperformed the currently-used FLT3-based stratification method. Our findings have the potential to transform clinical decision-making, and highlight the important role that phosphoproteomics is destined to play in precision oncology. FUNDING: This work was funded by Innovate UK grants (application numbers: 22217 and 10054602) and by Kinomica Ltd.

Preoperative treatment response prediction for pancreatic cancer by multiple microRNAs in plasma exosomes: Optimization using machine learning and network analysis.

BACKGROUND/OBJECTIVES: MicroRNAs (miRNAs) are involved in chemosensitivity through their biological activities in various malignancies, including pancreatic cancer (PC). However, single-miRNA models offer limited predictability of treatment response. We investigated whether a multiple-miRNA prediction model optimized via machine learning could improve treatment response prediction. METHODS: A total of 20 and 66 patients who underwent curative resection for PC after gemcitabine-based preoperative treatment were included in the discovery and validation cohorts, respectively. Patients were classified according to their response to preoperative treatment. In the discovery cohort, miRNA microarray and machine learning were used to identify candidate miRNAs (in peripheral plasma exosomes obtained before treatment) associated with treatment response. In the validation cohort, miRNA expression was analyzed using quantitative reverse transcription polymerase chain reaction to validate its ability to predict treatment response. RESULTS: In the discovery cohort, six and three miRNAs were associated with good and poor responders, respectively. The combination of these miRNAs significantly improved predictive accuracy compared with using each single miRNA, with area under the curve (AUC) values increasing from 0.485 to 0.672 to 0.909 for good responders and from 0.475 to 0.606 to 0.788 for poor responders. In the validation cohort, improved predictive performance of the miRNA combination over single-miRNA prediction models was confirmed, with AUC values increasing from 0.461 to 0.669 to 0.777 for good responders and from 0.501 to 0.556 to 0.685 for poor responders. CONCLUSIONS: Peripheral blood miRNA profiles using an optimized combination of miRNAs may provide a more advanced prediction model for preoperative treatment response in PC.

MCMVDRP: a multi-channel multi-view deep learning framework for cancer drug response prediction.

Drug therapy remains the primary approach to treating tumours. Variability among cancer patients, including variations in genomic profiles, often results in divergent therapeutic responses to analogous anti-cancer drug treatments within the same cohort of cancer patients. Hence, predicting the drug response by analysing the genomic profile characteristics of individual patients holds significant research importance. With the notable progress in machine learning and deep learning, many effective methods have emerged for predicting drug responses utilizing features from both drugs and cell lines. However, these methods are inadequate in capturing a sufficient number of features inherent to drugs. Consequently, we propose a representational approach for drugs that incorporates three distinct types of features: the molecular graph, the SMILE strings, and the molecular fingerprints. In this study, a novel deep learning model, named MCMVDRP, is introduced for the prediction of cancer drug responses. In our proposed model, an amalgamation of these extracted features is performed, followed by the utilization of fully connected layers to predict the drug response based on the IC50 values. Experimental results demonstrate that the presented model outperforms current state-of-the-art models in performance.

DRN-CDR: A cancer drug response prediction model using multi-omics and drug features.

Cancer drug response (CDR) prediction is an important area of research that aims to personalize cancer therapy, optimizing treatment plans for maximum effectiveness while minimizing potential negative effects. Despite the advancements in Deep learning techniques, the effective integration of multi-omics data for drug response prediction remains challenging. In this paper, a regression method using Deep ResNet for CDR (DRN-CDR) prediction is proposed. We aim to explore the potential of considering sole cancer genes in drug response prediction. Here the multi-omics data such as gene expressions, mutation data, and methylation data along with the molecular structural information of drugs were integrated to predict the IC50 values of drugs. Drug features are extracted by employing a Uniform Graph Convolution Network, while Cell line features are extracted using a combination of Convolutional Neural Network and Fully Connected Networks. These features are then concatenated and fed into a deep ResNet for the prediction of IC50 values between Drug - Cell line pairs. The proposed method yielded higher Pearson's correlation coefficient (rp) of 0.7938 with lowest Root Mean Squared Error (RMSE) value of 0.92 when compared with similar methods of tCNNS, MOLI, DeepCDR, TGSA, NIHGCN, DeepTTA, GraTransDRP and TSGCNN. Further, when the model is extended to a classification problem to categorize drugs as sensitive or resistant, we achieved AUC and AUPR measures of 0.7623 and 0.7691, respectively. The drugs such as Tivozanib, SNX-2112, CGP-60474, PHA-665752, Foretinib etc., exhibited low median IC50 values and were found to be effective anti-cancer drugs. The case studies with different TCGA cancer types also revealed the effectiveness of SNX-2112, CGP-60474, Foretinib, Cisplatin, Vinblastine etc. This consistent pattern strongly suggests the effectiveness of the model in predicting CDR.

Predictive performance of [18F]F-fibroblast activation protein inhibitor (FAPI)-42 positron emission tomography/computed tomography (PET/CT) in evaluating response of recurrent or metastatic gastrointestinal stromal tumors: complementary or alternative to [18F]fluorodeoxyglucose (FDG) PET/CT?

Background: Accurately and promptly predicting the response of gastrointestinal stromal tumors (GISTs) to targeted therapy is essential for optimizing treatment strategies. However, some fractions of recurrent or metastatic GISTs present as non-FDG-avid lesions, limiting the value of [18F]fluorodeoxyglucose positron emission tomography/computed tomography ([18F]FDG PET/CT) in treatment evaluation. This study evaluated the efficacy of [18F]F-fibroblast activation protein inhibitor (FAPI)-42 [18F]FAPI-42) PET/CT for assessing the treatment response in recurrent or metastatic GISTs, in comparison to [18F]FDG PET/CT and explores a model integrating PET/CT imaging and clinical parameters to optimize the clinical use of these diagnostic tools. Methods: Our retrospective analysis included 27 patients with recurrent or metastatic GISTs who underwent [18F]FAPI-42 PET/CT and [18F]FDG PET/CT at baseline before switching targeted therapy. Treatment response status was divided into a progression group (PG) and a non-progression group (NPG) based on the Response Criteria in Solid Tumors (RECIST) 1.1, according to the contrast-enhanced computed tomography (CT) scan at six months. [18F]FAPI-42 and [18F]FDG PET/CT parameters including the mean standardized uptake value (SUVmean), the standard uptake value corrected for lean body mass (SULpeak), the maximum standardized uptake value (SUVmax), tumor-to-blood pool SUV ratio (TBR), tumor-to-liver SUV ratio (TLR), metabolic tumor volume (MTV)/FAPI-positive tumor volume (GTV-FAPI), total lesion glycolysis (TLG)/FAPI-positive total lesion accumulation (TLF) were correlated with the response status to identify indicative of treatment response. The predictive performance of them was quantified by generating receiver operating characteristic curves (ROC), calibration curves, and cross-validation. Results: A total of 110 lesions were identified in 27 patients. Compared with PG, NPG was associated with lower levels of TBR and SUVmean in FDG PET/CT (TBR-FDG, SUVmean-FDG; P=0.033 and P=0.038, respectively), with higher SULpeak and TLF in FAPI PET/CT (SULpeak-FAPI, TLF-FAPI; P=0.10 and P=0.049, respectively). The predictive power of a composite-parameter model, including TBR-FDG, SULpeak-FAPI, gene mutation, and type of targeted therapy [area under the curve (AUC) =0.865], was superior to the few-parameter models incorporating TBR-FDG (AUC =0.637, P<0.001), SULpeak-FAPI (AUC =0.665, P<0.001) or both (AUC =0.721, P<0.001). Conclusions: Both [18F]FAPI-42 PET/CT and [18F]FDG PET/CT have value in predicting the treatment response of recurrent or metastatic GISTs. And [18F]FAPI-42 PET/CT offers synergistic value when used in combination with [18F]FDG PET/CT. Notably, the nomogram generated from the model incorporating [18F]FAPI-42 PET/CT, [18F]FDG PET/CT parameters, gene mutation, and type of targeted therapy could yield more precise predictions of the response of recurrent metastatic GISTs.

A model combining BI-RADS® descriptors from pre-treatment B-mode breast ultrasound with clinicopathological tumor features shows promise in the prediction of residual disease after neoadjuvant chemotherapy.

PURPOSE: To create a simple model using standard BI-RADS® descriptors from pre-treatment B-mode ultrasound (US) combined with clinicopathological tumor features, and to assess the potential of the model to predict the presence of residual tumor after neoadjuvant chemotherapy (NAC) in breast cancer (BC) patients. METHOD: 245 female BC patients receiving NAC between January 2017 and December 2019 were included in this retrospective study. Two breast imaging fellows independently evaluated representative B-mode tumor images from baseline US. Additional clinicopathological tumor features were retrieved. The dataset was split into 170 training and 83 validation cases. Logistic regression was used in the training set to identify independent predictors of residual disease post NAC and to create a model, whose performance was evaluated by ROC curve analysis in the validation set. The reference standard was postoperative histology to determine the absence (pathological complete response, pCR) or presence (non-pCR) of residual invasive tumor in the breast or axillary lymph nodes. RESULTS: 100 patients (40.8%) achieved pCR. Logistic regression demonstrated that tumor size, microlobulated margin, spiculated margin, the presence of calcifications, the presence of edema, HER2-positive molecular subtype, and triple-negative molecular subtype were independent predictors of residual disease. A model using these parameters demonstrated an area under the ROC curve of 0.873 in the training and 0.720 in the validation set for the prediction of residual tumor post NAC. CONCLUSIONS: A simple model combining standard BI-RADS® descriptors from pre-treatment B-mode breast US with clinicopathological tumor features predicts the presence of residual disease after NAC.

Evaluating Ovarian Cancer Chemotherapy Response Using Gene Expression Data and Machine Learning.

Background: Ovarian cancer (OC) is the most lethal gynecological cancer in the United States. Among the different types of OC, serous ovarian cancer (SOC) stands out as the most prevalent. Transcriptomics techniques generate extensive gene expression data, yet only a few of these genes are relevant to clinical diagnosis. Methods: Methods for feature selection (FS) address the challenges of high dimensionality in extensive datasets. This study proposes a computational framework that applies FS techniques to identify genes highly associated with platinum-based chemotherapy response on SOC patients. Using SOC datasets from the Gene Expression Omnibus (GEO) database, LASSO and varSelRF FS methods were employed. Machine learning classification algorithms such as random forest (RF) and support vector machine (SVM) were also used to evaluate the performance of the models. Results: The proposed framework has identified biomarkers panels with 9 and 10 genes that are highly correlated with platinum-paclitaxel and platinum-only response in SOC patients, respectively. The predictive models have been trained using the identified gene signatures and accuracy of above 90% was achieved. Conclusions: In this study, we propose that applying multiple feature selection methods not only effectively reduces the number of identified biomarkers, enhancing their biological relevance, but also corroborates the efficacy of drug response prediction models in cancer treatment.

A susceptibility gene signature for ERBB2-driven mammary tumour development and metastasis in collaborative cross mice.

BACKGROUND: Deeper insights into ERBB2-driven cancers are essential to develop new treatment approaches for ERBB2+ breast cancers (BCs). We employed the Collaborative Cross (CC) mouse model to unearth genetic factors underpinning Erbb2-driven mammary tumour development and metastasis. METHODS: 732 F1 hybrid female mice between FVB/N MMTV-Erbb2 and 30 CC strains were monitored for mammary tumour phenotypes. GWAS pinpointed SNPs that influence various tumour phenotypes. Multivariate analyses and models were used to construct the polygenic score and to develop a mouse tumour susceptibility gene signature (mTSGS), where the corresponding human ortholog was identified and designated as hTSGS. The importance and clinical value of hTSGS in human BC was evaluated using public datasets, encompassing TCGA, METABRIC, GSE96058, and I-SPY2 cohorts. The predictive power of mTSGS for response to chemotherapy was validated in vivo using genetically diverse MMTV-Erbb2 mice. FINDINGS: Distinct variances in tumour onset, multiplicity, and metastatic patterns were observed in F1-hybrid female mice between FVB/N MMTV-Erbb2 and 30 CC strains. Besides lung metastasis, liver and kidney metastases emerged in specific CC strains. GWAS identified specific SNPs significantly associated with tumour onset, multiplicity, lung metastasis, and liver metastasis. Multivariate analyses flagged SNPs in 20 genes (Stx6, Ramp1, Traf3ip1, Nckap5, Pfkfb2, Trmt1l, Rprd1b, Rer1, Sepsecs, Rhobtb1, Tsen15, Abcc3, Arid5b, Tnr, Dock2, Tti1, Fam81a, Oxr1, Plxna2, and Tbc1d31) independently tied to various tumour characteristics, designated as a mTSGS. hTSGS scores (hTSGSS) based on their transcriptional level showed prognostic values, superseding clinical factors and PAM50 subtype across multiple human BC cohorts, and predicted pathological complete response independent of and superior to MammaPrint score in I-SPY2 study. The power of mTSGS score for predicting chemotherapy response was further validated in an in vivo mouse MMTV-Erbb2 model, showing that, like findings in human patients, mouse tumours with low mTSGS scores were most likely to respond to treatment. INTERPRETATION: Our investigation has unveiled many new genes predisposing individuals to ERBB2-driven cancer. Translational findings indicate that hTSGS holds promise as a biomarker for refining treatment strategies for patients with BC. FUNDING: The U.S. Department of Defense (DoD) Breast Cancer Research Program (BCRP) (BC190820), United States; MCIN/AEI/10.13039/501100011039 (PID2020-118527RB-I00, PDC2021-121735-I00), the "European Union Next Generation EU/PRTR," the Regional Government of Castile and León (CSI144P20), European Union.

The life-saving benefit of dexamethasone in severe COVID-19 is linked to a reversal of monocyte dysregulation.

Dexamethasone is a life-saving treatment for severe COVID-19, yet its mechanism of action is unknown, and many patients deteriorate or die despite timely treatment initiation. Here, we identify dexamethasone treatment-induced cellular and molecular changes associated with improved survival in COVID-19 patients. We observed a reversal of transcriptional hallmark signatures in monocytes associated with severe COVID-19 and the induction of a monocyte substate characterized by the expression of glucocorticoid-response genes. These molecular responses to dexamethasone were detected in circulating and pulmonary monocytes, and they were directly linked to survival. Monocyte single-cell RNA sequencing (scRNA-seq)-derived signatures were enriched in whole blood transcriptomes of patients with fatal outcome in two independent cohorts, highlighting the potential for identifying non-responders refractory to dexamethasone. Our findings link the effects of dexamethasone to specific immunomodulation and reversal of monocyte dysregulation, and they highlight the potential of single-cell omics for monitoring in vivo target engagement of immunomodulatory drugs and for patient stratification for precision medicine approaches.

Integration of autoencoder and graph convolutional network for predicting breast cancer drug response.

Background and objectives: Breast cancer is the most prevalent type of cancer among women. The effectiveness of anticancer pharmacological therapy may get adversely affected by tumor heterogeneity that includes genetic and transcriptomic features. This leads to clinical variability in patient response to therapeutic drugs. Anticancer drug design and cancer understanding require precise identification of cancer drug responses. The performance of drug response prediction models can be improved by integrating multi-omics data and drug structure data. Methods: In this paper, we propose an Autoencoder (AE) and Graph Convolutional Network (AGCN) for drug response prediction, which integrates multi-omics data and drug structure data. Specifically, we first converted the high dimensional representation of each omic data to a lower dimensional representation using an AE for each omic data set. Subsequently, these individual features are combined with drug structure data obtained using a Graph Convolutional Network and given to a Convolutional Neural Network to calculate IC[Formula: see text] values for every combination of cell lines and drugs. Then a threshold IC[Formula: see text] value is obtained for each drug by performing K-means clustering of their known IC[Formula: see text] values. Finally, with the help of this threshold value, cell lines are classified as either sensitive or resistant to each drug. Results: Experimental results indicate that AGCN has an accuracy of 0.82 and performs better than many existing methods. In addition to that, we have done external validation of AGCN using data taken from The Cancer Genome Atlas (TCGA) clinical database, and we got an accuracy of 0.91. Conclusion: According to the results obtained, concatenating multi-omics data with drug structure data using AGCN for drug response prediction tasks greatly improves the accuracy of the prediction task.

Functional and clinical roles of stromal PDGF receptors in tumor biology.

PDGF receptors play pivotal roles in both developmental and physiological processes through the regulation of mesenchymal cells involved in paracrine instructive interactions with epithelial or endothelial cells. Tumor biology studies, alongside analyses of patient tissue samples, provide strong indications that the PDGF signaling pathways are also critical in various types of human cancer. This review summarizes experimental findings and correlative studies, which have explored the biological mechanisms and clinical relevance of PDGFRs in mesenchymal cells of the tumor microenvironment. Collectively, these studies support the overall concept that the PDGF system is a critical regulator of tumor growth, metastasis, and drug efficacy, suggesting yet unexploited targeting opportunities. The inter-patient variability in stromal PDGFR expression, as being linked to prognosis and treatment responses, not only indicates the need for stratified approaches in upcoming therapeutic investigations but also implies the potential for the development of PDGFRs as biomarkers of clinical utility, interestingly also in settings outside PDGFR-directed treatments.

Radiomic-based prediction of lesion-specific systemic treatment response in metastatic disease.

Despite sharing the same histologic classification, individual tumors in multi metastatic patients may present with different characteristics and varying sensitivities to anticancer therapies. In this study, we investigate the utility of radiomic biomarkers for prediction of lesion-specific treatment resistance in multi metastatic leiomyosarcoma patients. Using a dataset of n=202 lung metastases (LM) from n=80 patients with 1648 pre-treatment computed tomography (CT) radiomics features and LM progression determined from follow-up CT, we developed a radiomic model to predict the progression of each lesion. Repeat experiments assessed the relative predictive performance across LM volume groups. Lesion-specific radiomic models indicate up to a 4.5-fold increase in predictive capacity compared with a no-skill classifier, with an area under the precision-recall curve of 0.70 for the most precise model (FDR = 0.05). Precision varied by administered drug and LM volume. The effect of LM volume was controlled by removing radiomic features at a volume-correlation coefficient threshold of 0.20. Predicting lesion-specific responses using radiomic features represents a novel strategy by which to assess treatment response that acknowledges biological diversity within metastatic subclones, which could facilitate management strategies involving selective ablation of resistant clones in the setting of systemic therapy.

Baseline [18F]FDG PET/CT and MRI first-order breast tumor features do not improve pathological complete response prediction to neoadjuvant chemotherapy.

PURPOSE: To verify the ability of pretreatment [18F]FDG PET/CT and T1-weighed dynamic contrast-enhanced MRI to predict pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) in breast cancer (BC) patients. METHODS: This retrospective study includes patients with BC of no special type submitted to baseline [18F]FDG PET/CT, NAC and surgery. [18F]FDG PET-based features reflecting intensity and heterogeneity of tracer uptake were extracted from the primary BC and suspicious axillary lymph nodes (ALN), for comparative analysis related to NAC response (pCR vs. non-pCR). Multivariate logistic regression was performed for response prediction combining the breast tumor-extracted PET-based features and clinicopathological features. A subanalysis was performed in a patients' subsample by adding breast tumor-extracted first-order MRI-based features to the multivariate logistic regression. RESULTS: A total of 170 tumors from 168 patients were included. pCR was observed in 60/170 tumors (20/107 luminal B-like, 25/45 triple-negative and 15/18 HER2-enriched surrogate molecular subtypes). Higher intensity and higher heterogeneity of [18F]FDG uptake in the primary BC were associated with NAC response in HER2-negative tumors (immunohistochemistry score 0, 1 + or 2 + non-amplified by in situ hybridization). Also, higher intensity of tracer uptake was observed in ALN in the pCR group among HER2-negative tumors. No [18F]FDG PET-based features were associated with pCR in the other subgroup analyses. A subsample of 103 tumors was also submitted to extraction of MRI-based features. When combined with clinicopathological features, neither [18F]FDG PET nor MRI-based features had additional value for pCR prediction. The only significant predictors were estrogen receptor status, HER2 expression and grade. CONCLUSION: Pretreatment [18F]FDG PET-based features from primary BC and ALN are not associated with response to NAC, except in HER2-negative tumors. As compared with pathological features, no breast tumor-extracted PET or MRI-based feature improved response prediction.

Histopathology and proteomics are synergistic for High-Grade Serous Ovarian Cancer platinum response prediction.

Patients with High-Grade Serous Ovarian Cancer (HGSOC) exhibit varied responses to treatment, with 20-30% showing de novo resistance to platinum-based chemotherapy. While hematoxylin-eosin (H&E) pathological slides are used for routine diagnosis of cancer type, they may also contain diagnostically useful information about treatment response. Our study demonstrates that combining H&E-stained Whole Slide Images (WSIs) with proteomic signatures using a multimodal deep learning framework significantly improves the prediction of platinum response in both discovery and validation cohorts. This method outperforms the Homologous Recombination Deficiency (HRD) score in predicting platinum response and overall patient survival. The study sets new performance benchmarks and explores the intersection of histology and proteomics, highlighting phenotypes related to treatment response pathways, including homologous recombination, DNA damage response, nucleotide synthesis, apoptosis, and ER stress. This integrative approach has the potential to improve personalized treatment and provide insights into the therapeutic vulnerabilities of HGSOC.

iGenSig-Rx: an integral genomic signature based white-box tool for modeling cancer therapeutic responses using multi-omics data.

Multi-omics sequencing is poised to revolutionize clinical care in the coming decade. However, there is a lack of effective and interpretable genome-wide modeling methods for the rational selection of patients for personalized interventions. To address this, we present iGenSig-Rx, an integral genomic signature-based approach, as a transparent tool for modeling therapeutic response using clinical trial datasets. This method adeptly addresses challenges related to cross-dataset modeling by capitalizing on high-dimensional redundant genomic features, analogous to reinforcing building pillars with redundant steel rods. Moreover, it integrates adaptive penalization of feature redundancy on a per-sample basis to prevent score flattening and mitigate overfitting. We then developed a purpose-built R package to implement this method for modeling clinical trial datasets. When applied to genomic datasets for HER2 targeted therapies, iGenSig-Rx model demonstrates consistent and reliable predictive power across four independent clinical trials. More importantly, the iGenSig-Rx model offers the level of transparency much needed for clinical application, allowing for clear explanations as to how the predictions are produced, how the features contribute to the prediction, and what are the key underlying pathways. We anticipate that iGenSig-Rx, as an interpretable class of multi-omics modeling methods, will find broad applications in big-data based precision oncology. The R package is available: https://github.com/wangxlab/iGenSig-Rx .

Personalized medicine in acromegaly: The ACROFAST study.

Medical treatment of acromegaly is currently performed through a trial-error approach using first generation somatostatin receptor ligands (fgSRLs) as first-line drugs, with an effectiveness of about 50%, and subsequent drugs are indicated through clinical judgment. Some biomarkers can predict fgSRLs response. Here we report the results of the ACROFAST study, a clinical trial in which a protocol based on predictive biomarkers of fgSRLs was evaluated. METHODS AND SUBJECTS: prospective trial (21 university hospitals) comparing the effectiveness and time-to control of two treatment protocols during 12 months: A) A personalized protocol in which first option were fgSRLs as monotherapy or in combination with pegvisomant or, pegvisomant as monotherapy depending on the short Acute Octreotide Test (sAOT) results, tumor T2 Magnetic Resonance (MRI) signal or immunostaining for E-cadherin and, B) A control group with treatment always started by fgSRLs and the other drugs included after demonstrating inadequate control. RESULTS: Eighty-five patients participated; 45 in the personalized and 40 in the control group. More patients in the personalized protocol achieved hormonal control compared to those in the control group (78% vs 53%, p < 0.05). Survival analysis revealed a hazard ratio for achieving hormonal control adjusted by age and sex of 2.53 (CI 1.30-4.80). Patients from personalized arm were controlled in a shorter period of time (p = 0.01). CONCLUSION: Personalized medicine is feasible using a relatively simple protocol and allows a higher number of patients achieving control in a shorter period of time.

Advancing drug-response prediction using multi-modal and -omics machine learning integration (MOMLIN): a case study on breast cancer clinical data.

The inherent heterogeneity of cancer contributes to highly variable responses to any anticancer treatments. This underscores the need to first identify precise biomarkers through complex multi-omics datasets that are now available. Although much research has focused on this aspect, identifying biomarkers associated with distinct drug responders still remains a major challenge. Here, we develop MOMLIN, a multi-modal and -omics machine learning integration framework, to enhance drug-response prediction. MOMLIN jointly utilizes sparse correlation algorithms and class-specific feature selection algorithms, which identifies multi-modal and -omics-associated interpretable components. MOMLIN was applied to 147 patients' breast cancer datasets (clinical, mutation, gene expression, tumor microenvironment cells and molecular pathways) to analyze drug-response class predictions for non-responders and variable responders. Notably, MOMLIN achieves an average AUC of 0.989, which is at least 10% greater when compared with current state-of-the-art (data integration analysis for biomarker discovery using latent components, multi-omics factor analysis, sparse canonical correlation analysis). Moreover, MOMLIN not only detects known individual biomarkers such as genes at mutation/expression level, most importantly, it correlates multi-modal and -omics network biomarkers for each response class. For example, an interaction between ER-negative-HMCN1-COL5A1 mutations-FBXO2-CSF3R expression-CD8 emerge as a multimodal biomarker for responders, potentially affecting antimicrobial peptides and FLT3 signaling pathways. In contrast, for resistance cases, a distinct combination of lymph node-TP53 mutation-PON3-ENSG00000261116 lncRNA expression-HLA-E-T-cell exclusions emerged as multimodal biomarkers, possibly impacting neurotransmitter release cycle pathway. MOMLIN, therefore, is expected advance precision medicine, such as to detect context-specific multi-omics network biomarkers and better predict drug-response classifications.

Integrating Tumor and Nodal Radiomics to Predict the Response to Neoadjuvant Chemotherapy and Recurrence Risk for Locally Advanced Gastric Cancer.

AIMS: To develop and evaluate machine learning models using tumor and nodal radiomics features for predicting the response to neoadjuvant chemotherapy (NAC) and recurrence risk in locally advanced gastric cancer (LAGC). BACKGROUND: Early and accurate response prediction is vital to stratify LAGC patients and select proper candidates for NAC. OBJECTIVE: A total of 218 patients with LAGC undergoing NAC followed by gastrectomy were enrolled in our study and were randomly divided into a training cohort (n = 153) and a validation cohort (n = 65). METHODS: We extracted 1316 radiomics features from the volume of interest of the primary lesion and maximal lymph node on venous phase CT images. We built 3 radiomics signatures for distinguishing good responders and poor responders based on tumor radiomics (TR), nodal radiomics (NR), and a combination of the two (TNR), respectively. A nomogram was then developed by integrating the radiomics signature and clinical factors. Kaplan- Meier survival curves were used to evaluate the prognostic value of the nomogram. RESULTS: The TNR signature achieved improved predictive value, with AUCs of 0.755 and 0.744 in the training and validation cohorts. Our proposed nomogram model (TNRN) showed a good performance for GR prediction in the prediction efficacy, calibration ability, and clinical benefit, with AUCs of 0.779 and 0.732 in the training and validation cohorts, superior to the clinical model. Moreover, the TNRN could accurately classify the patients into high-risk and low-risk groups in both training and validation cohorts with regard to postoperative recurrence and metastasis. CONCLUSION: The TNRN performed well in identifying good responders and provided valuable information for predicting progression-free survival time (PFS) in patients with LAGC who underwent NAC.

[18F]FMISO-PET imaging reveals the role of hypoxia severity in checkpoint blockade response.

CONTEXT: Hypoxia within the tumor microenvironment is a critical factor influencing the efficacy of immunotherapy, including immune checkpoint inhibition. Insufficient oxygen supply, characteristic of hypoxia, has been recognized as a central determinant in the progression of various cancers. The reemergence of evofosfamide, a hypoxia-activated prodrug, as a potential treatment strategy has sparked interest in addressing the role of hypoxia in immunotherapy response. This investigation sought to understand the kinetics and heterogeneity of tumor hypoxia and their implications in affecting responses to immunotherapeutic interventions with and without evofosfamide. PURPOSE: This study aimed to investigate the influence of hypoxia on immune checkpoint inhibition, evofosfamide monotherapy, and their combination on colorectal cancer (CRC). Employing positron emission tomography (PET) imaging, we developed novel analytical methods to quantify and characterize tumor hypoxia severity and distribution. PROCEDURES: Murine CRC models were longitudinally imaged with [18F]-fluoromisonidazole (FMISO)-PET to quantify tumor hypoxia during checkpoint blockade (anti-CTLA-4 + and anti-PD1 +/- evofosfamide). Metrics including maximum tumor [18F]FMISO uptake (FMISOmax) and mean tumor [18F]FMISO uptake (FMISOmean) were quantified and compared with normal muscle tissue (average muscle FMISO uptake (mAvg) and muscle standard deviation (mSD)). Histogram distributions were used to evaluate heterogeneity of tumor hypoxia. FINDINGS: Severe hypoxia significantly impeded immunotherapy effectiveness consistent with an immunosuppressive microenvironment. Hypoxia-specific PET imaging revealed a striking degree of spatial heterogeneity in tumor hypoxia, with some regions exhibiting significantly more severe hypoxia than others. The study identified FMISOmax as a robust predictor of immunotherapy response, emphasizing the impact of localized severe hypoxia on tumor volume control during therapy. Interestingly, evofosfamide did not directly reduce hypoxia but markedly improved the response to immunotherapy, uncovering an alternative mechanism for its efficacy. CONCLUSIONS: These results enhance our comprehension of the interplay between hypoxia and immune checkpoint inhibition within the tumor microenvironment, offering crucial insights for the development of personalized cancer treatment strategies. Non-invasive hypoxia quantification through molecular imaging evaluating hypoxia severity may be an effective tool in guiding treatment planning, predicting therapy response, and ultimately improving patient outcomes across diverse cancer types and tumor microenvironments. It sets the stage for the translation of these findings into clinical practice, facilitating the optimization of immunotherapy regimens by addressing tumor hypoxia and thereby enhancing the efficacy of cancer treatments.