Response Prediction Model Research Articles

Revolutionizing Cancer Research and Drug Discovery: The Role of Artificial Intelligence and Machine Learning

Abstract: Artificial Intelligence (AI) and Machine Learning (ML) have revolutionized various industries, including cancer research and drug discovery. This article provides a summary of the history of AI and ML, highlighting their resurgence in the 1990s with advancements in computational power and new algorithms. In the context of drug discovery, AI and ML techniques have been applied to accelerate the development of new drugs, from target identification and lead generation to drug repurposing. AI applications in drug design and virtual screening have improved the efficiency of identifying potential drug candidates. Deep learning, a division of ML, has been particularly effective in predicting protein structures and optimizing lead compounds. In anti-cancer drug target prediction, AI and ML algorithms analyze large-scale genomic, proteomic, and clinical data to identify potential targets for cancer therapy. AI has also transformed cancer imaging and diagnosis by enhancing the accuracy and efficiency of cancer detection, classification, and prognosis. Medical imaging analysis, pathology, and radiology have benefited from AI algorithms’ ability to interpret and analyze various imaging modalities. Moreover, AI applications in cancer treatment have facilitated the development of predictive models for treatment response, enabling personalized and targeted therapies based on individual patient characteristics. The purpose of the study was to give facts regarding the integration of artificial intelligence and machine learning in drug discovery and cancer therapy and its significant prospects for improving efficiency, decreasing costs, and improving patient outcomes.

Modelling bioremediation of contaminated effluents by Ulva ohnoi. – A predictive perspective

Ulva spp. are tolerant to salinity variations and exhibit easy acclimation, playing an essential role in the depollution of aquatic ecosystems precisely due to their high efficiency in absorbing and accumulating nutrients. For this reason, Ulva spp. becomes an attractive solution for recovering areas that suffer the impacts of problems such as the eutrophication of anthropogenic origin. In addition to being a promising alternative for the blue bioeconomy, it can contribute to the sustainability of economic activities in coastal areas. Therefore, the present study aimed to develop and elucidate the behavior of Ulva ohnoi using predictive surface response models. The algae were grown under different concentrations of nutrient and salinity levels, as predicted by the experimental design, and it was evaluated according to the potential of the biomass to absorb the nutrients, as well as its photosynthetic performance and biochemical parameters. Our study confirmed the high efficiency and preference of Ulva ohnoi in the absorption of nitrogen dissolved in the medium in the form of NH4+ and that salinity is an essential factor in the dynamics and speed of ammonium absorption. The absorption of orthophosphate by U. ohnoi is reverted to the culture medium when subjected to long-term cultivation. This process was more intense because of low salinity, even at conditions of availability of the compound. The 3D-models of response surfaces elucidate the behavior of Ulva ohnoi, attributing a correlation between nutrient availability and salinity and the biological behavior of the species. In view of what is exposed by these models, as well as the effects of saline distribution along the Lagoon, the following regions of the lagoon are suggested: Center-North, Center and South – as potential areas for the implementation of bioremediation projects with Ulva ohnoi.

Development and validation of a prediction model for unexpected poor ovarian response during IVF/ICSI.

Identifying poor ovarian response (POR) among patients with good ovarian reserve poses a significant challenge within reproductive medicine. Currently, there is a lack of published data on the potential risk factors that could predict the occurrence of unexpected POR. The objective of this study was to develop a predictive model to assess the individual probability of unexpected POR during in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) treatments. The development of the nomogram involved a cohort of 10,404 patients with normal ovarian reserve [age, ≤40 years; antral follicle count (AFC), ≥5; and anti-Müllerian hormone (AMH), ≥1.2 ng/ml] from January 2019 to December 2022. Univariate regression analyses and least absolute shrinkage and selection operator regression analysis were employed to ascertain the characteristics associated with POR. Subsequently, the selected variables were utilized to construct the nomogram. The predictors included in our model were body mass index, basal follicle-stimulating hormone, AMH, AFC, homeostasis model assessment of insulin resistance (HOMA-IR), protocol, and initial dose of gonadotropin. The area under the receiver operating characteristic curve (AUC) was 0.753 [95% confidence interval (CI) = 0.7257-0.7735]. The AUC, along with the Hosmer-Lemeshow test (p = 0.167), demonstrated a satisfactory level of congruence and discrimination ability of the developed model. The nomogram can anticipate the probability of unexpected POR in IVF/ICSI treatment, thereby assisting professionals in making appropriate clinical judgments and in helping patients to effectively manage expectations.

Uncovering the subtype-specific disease module and the development of drug response prediction models for glioma

The poor prognosis of glioma patients brought attention to the need for effective therapeutic approaches for precision therapy. Here, we deployed algorithms relying on network medicine and artificial intelligence to design the framework for subtype-specific target identification and drug response prediction in glioma. We identified the driver mutations that were differentially expressed in each subtype of lower-grade glioma and glioblastoma multiforme and were linked to cancer-specific processes. Driver mutations that were differentially expressed were also subjected to subtype-specific disease module identification. The drugs from the drug bank database were retrieved to target these disease modules. However, the efficacy of anticancer drugs depends on the molecular profile of the cancer and varies among cancer patients due to intratumor heterogeneity. Hence, we developed a deep-learning-based drug response prediction framework using the experimental drug screening data. Models for 30 drugs that can target the disease module were developed, where drug response measured by IC50 was considered a response and gene expression and mutation data were considered predictor variables. The model construction consists of three steps: feature selection, data integration, and classification. We observed the consistent performance of the models in training, test, and validation datasets. Drug responses were predicted for particular cell lines derived from distinct subtypes of gliomas. We found that subtypes of gliomas respond differently to the drug, highlighting the importance of subtype-specific drug response prediction. Therefore, the development of personalized therapy by integrating network medicine and a deep learning-based approach can lead to cancer-specific treatment and improved patient care.

Multi-omics approaches for drug-response characterization in primary biliary cholangitis and autoimmune hepatitis variant syndrome

BackgroundPrimary biliary cholangitis (PBC) and autoimmune hepatitis (AIH) variant syndrome (VS) exhibit a complex overlap of AIH features with PBC, leading to poorer prognoses than those with PBC or AIH alone. The biomarkers associated with drug response and potential molecular mechanisms in this syndrome have not been fully elucidated.MethodsWhole-transcriptome sequencing was employed to discern differentially expressed (DE) RNAs within good responders (GR) and poor responders (PR) among patients with PBC/AIH VS. Subsequent gene ontology (GO) analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were conducted for the identified DE RNAs. Plasma metabolomics was employed to delineate the metabolic profiles distinguishing PR and GR groups. The quantification of immune cell profiles and associated cytokines was achieved through flow cytometry and immunoassay technology. Uni- and multivariable logistic regression analyses were conducted to construct a predictive model for insufficient biochemical response. The performance of the model was assessed by computing the area under the receiver operating characteristic (AUC) curve, sensitivity, and specificity.FindingsThe analysis identified 224 differentially expressed (DE) mRNAs, 189 DE long non-coding RNAs, 39 DE circular RNAs, and 63 DE microRNAs. Functional pathway analysis revealed enrichment in lipid metabolic pathways and immune response. Metabolomics disclosed dysregulated lipid metabolism and identified PC (18:2/18:2) and PC (16:0/20:3) as predictors. CD4+ T helper (Th) cells, including Th2 cells and regulatory T cells (Tregs), were upregulated in the GR group. Pro-inflammatory cytokines (IFN-γ, TNF-α, IL-9, and IL-17) were downregulated in the GR group, while anti-inflammatory cytokines (IL-10, IL-4, IL-5, and IL-22) were elevated. Regulatory networks were constructed, identifying CACNA1H and ACAA1 as target genes. A predictive model based on these indicators demonstrated an AUC of 0.986 in the primary cohort and an AUC of 0.940 in the validation cohort for predicting complete biochemical response.ConclusionA combined model integrating genomic, metabolic, and cytokinomic features demonstrated high accuracy in predicting insufficient biochemical response in patients with PBC/AIH VS. Early recognition of individuals at elevated risk for insufficient response allows for the prompt initiation of additional treatments.

Bioinformatic analysis and experimental validation of cuproptosis-related LncRNA as a novel biomarker for prognosis and immunotherapy of oral squamous cell carcinoma

BackgroundThe novel form of regulatory cell death, cuproptosis, is characterized by proteotoxicity, which ultimately leads to cell death. Its targeting has emerged as a promising therapeutic approach for oral squamous cell carcinoma (OSCC). Long noncoding RNAs (lncRNAs) participate in epigenetic regulation and have been linked to the progression, prognosis, and treatment of OSCC. Thus, this study aimed to identify new cuproptosis-related lncRNAs (CRLs), establish predictive models for clinical prognosis, immune response, and drug sensitivity, and provide novel insights into immune escape and tumor drug resistance.MethodsThe present study screened eight CRLs (THAP9-AS1, STARD4-AS1, WDFY3-AS2, LINC00847, CDKN2A-DT, AL132800.1, GCC2-AS1, AC005746.1) using Lasso Cox regression analysis to develop an eight-CRL prognostic model. Patients were categorized into high- and low-risk groups using risk scores. To evaluate the predictive ability of the model, Kaplan-Meier analysis, ROC curves, and nomograms were employed. Furthermore, the study investigated the differences in immune function and anticancer drug sensitivity between the high- and low-risk groups. To validate the expression of CRLs in the model, OSCC cell lines were subjected to quantitative real-time fluorescence PCR (qRT-PCR).ResultsThe results of the study showed that the high-risk group had a shorter overall survival (OS) time in OSCC patients. Cox regression analysis demonstrated that the high-risk score was an independent risk factor for a poor prognosis. The validity of the model was confirmed using ROC curve analysis, and a nomogram was developed to predict the prognosis of OSCC patients. Furthermore, patients in the high-risk group with high TMB had a poorer prognosis. Patients in the low-risk group responded better to immunotherapy than those in the high-risk group. Additionally, the risk scores were significantly associated with drug sensitivity in OSCC patients. Finally, the findings of qRT-PCR supported the reliability of the proposed risk model.ConclusionThe study identified and established the 8-CRL model, which represents a novel pathway of lncRNA regulation of cuproptosis in OSCC. This model provides guidance for the prognosis and treatment of OSCC and offers a new insight into immune escape and tumor drug resistance.

Treatment response and its predictors of immunosuppressive therapy in patients with severe or very severe aplastic anemia

Severe aplastic anemia (SAA) is a hematological condition with high morbidity and mortality. Treatment with immunosuppressive agents is alternative treatment if bone marrow transplant is not available. Several studies reported predictors of successful treatment in patients with SAA. However, the results are not consistent and not specific to anti-thymocyte globulin and cyclosporine. This study aimed to evaluate the predictor of response to treatment in this specific regimen. This study was a retrospective cohort study. The inclusion criteria were adult patients with SAA or very SAA who received this regimen. Clinical factors predictive of response to treatment were computed. There were 92 patients met the study criteria. Of those, 56 patients (60.87%) were in a group of response to treatment. There were nine factors in the predictive model for good response to treatment. Only body mass index was independently associated with response to treatment with an adjusted odds ratio of 1.31 (95% confidence interval of 1.04, 1.67). Age or hematological laboratory factors such as lymphocyte or neutrophil count were not significant. Low body mass index may be less likely to response to immunosuppressive treatment in patients with severe or very severe aplastic anemia.

Residual facial erythema in atopic dermatitis patients treated with dupilumab stratified by machine learning.

Persistent facial erythema represents a significant complication in atopic dermatitis (AD) patients undergoing treatment with dupilumab. Stratifying patients based on the erythema course is crucial for elucidating heterogeneous phenotypes and facilitating advanced drug efficacy predictions. This study aimed to identify factors associated with facial erythema severity in dupilumab-treated AD patients and to establish a prediction model for drug response based on the identified factors. Data from a retrospective study conducted between July 2018 and July 2021 were collected and analysed. Patients were categorized into three groups via hierarchical clustering based on the course of facial erythema: early remission, low remission and persistent residual. LightGBM, a supervised gradient boosting decision tree algorithm, was employed to discern group differences and construct a prediction model. The model incorporated patient demographic and clinical profiles, including pre- and post-treatment examinations. The model's performance was evaluated using accuracy and the area under the receiver operating characteristic curve (AUC). The binary classification model demonstrated an accuracy of 89.10% and an AUC of 0.862 when distinguishing between early remission and persistent residual patients. The eight prominent factors associated with facial erythema severity included age, sex, lactate dehydrogenase (LDH), immunoglobulin E (IgE), eosinophil count, white blood cell count, Alnus allergy and cedar allergy. This study has two main significances: first, three clusters were identified through unsupervised learning; second, a classification model was constructed that proved more accurate than random prediction. The stratification and identification of crucial factors associated with residual facial erythema in dupilumab-treated AD patients lay the foundation for AI-powered prognostic models. This groundwork provides a substantial basis for enhancing future medical AI support in AD treatment selection, potentially improving personalized treatment approaches and outcomes.

1. ORGANOID DEVELOPMENT IN COLORECTAL CANCER: NEW MODELS FOR PERSONALIZED MEDICINE

Abstract Introduction Despite the great advances in recent decades in identifying mechanisms related to tumor progression and resistance to treatment, there are still no safe and effective therapies to treat colorectal cancer (the most common neoplasm in Spain). Organoid models represent a highly promising tool for studying this pathology since they recapitulate, with great precision, the structure and functionality of the original organ. Methods At our center, we have generated an extensive collection of human intestinal organoids, including rectum and colon, from biopsies of healthy tissue and tumor tissue from 72 colorectal cancer patients. For the generation of these models, two different approaches were employed: 1. Organoid generation from intestinal crypts embedded in extracellular matrix droplets; 2. Air-liquid interface (ALI) culture that allows recreating the native microenvironment of the tumor while excluding endogenous infiltrating immune cell populations. Results These organoid collections have been highly characterized, confirming that they retain the molecular, structural, and functional characteristics of their tissues of origin. We present the different findings and their correlation. Conclusion The technology developed by our research group serves as a tool of great translational value for studying response/resistance mechanisms to current colorectal cancer treatments. Additionally, it serves as a predictive model for drug response, playing a crucial role in defining the efficacy of personalized antineoplastic treatments for each patient and advancing the development of personalized therapies against colorectal cancer.

New Advances in the Pharmacology and Toxicology of Lithium: A Neurobiologically Oriented Overview.

Over the last six decades, lithium has been considered the gold standard treatment for the long-term management of bipolar disorder due to its efficacy in preventing both manic and depressive episodes as well as suicidal behaviors. Nevertheless, despite numerous observed effects on various cellular pathways and biologic systems, the precise mechanism through which lithium stabilizes mood remains elusive. Furthermore, there is recent support for the therapeutic potential of lithium in other brain diseases. This review offers a comprehensive examination of contemporary understanding and predominant theories concerning the diverse mechanisms underlying lithium's effects. These findings are based on investigations utilizing cellular and animal models of neurodegenerative and psychiatric disorders. Recent studies have provided additional support for the significance of glycogen synthase kinase-3 (GSK3) inhibition as a crucial mechanism. Furthermore, research has shed more light on the interconnections between GSK3-mediated neuroprotective, antioxidant, and neuroplasticity processes. Moreover, recent advancements in animal and human models have provided valuable insights into how lithium-induced modifications at the homeostatic synaptic plasticity level may play a pivotal role in its clinical effectiveness. We focused on findings from translational studies suggesting that lithium may interface with microRNA expression. Finally, we are exploring the repurposing potential of lithium beyond bipolar disorder. These recent findings on the therapeutic mechanisms of lithium have provided important clues toward developing predictive models of response to lithium treatment and identifying new biologic targets. SIGNIFICANCE STATEMENT: Lithium is the drug of choice for the treatment of bipolar disorder, but its mechanism of action in stabilizing mood remains elusive. This review presents the latest evidence on lithium's various mechanisms of action. Recent evidence has strengthened glycogen synthase kinase-3 (GSK3) inhibition, changes at the level of homeostatic synaptic plasticity, and regulation of microRNA expression as key mechanisms, providing an intriguing perspective that may help bridge the mechanistic gap between molecular functions and its clinical efficacy as a mood stabilizer.

Leveraging baseline transcriptional features and information from single-cell data to power the prediction of influenza vaccine response.

Vaccination is still the primary means for preventing influenza virus infection, but the protective effects vary greatly among individuals. Identifying individuals at risk of low response to influenza vaccination is important. This study aimed to explore improved strategies for constructing predictive models of influenza vaccine response using gene expression data. We first used gene expression and immune response data from the Immune Signatures Data Resource (IS2) to define influenza vaccine response-related transcriptional expression and alteration features at different time points across vaccination via differential expression analysis. Then, we mapped these features to single-cell resolution using additional published single-cell data to investigate the possible mechanism. Finally, we explored the potential of these identified transcriptional features in predicting influenza vaccine response. We used several modeling strategies and also attempted to leverage the information from single-cell RNA sequencing (scRNA-seq) data to optimize the predictive models. The results showed that models based on genes showing differential expression (DEGs) or fold change (DFGs) at day 7 post-vaccination performed the best in internal validation, while models based on DFGs had a better performance in external validation than those based on DEGs. In addition, incorporating baseline predictors could improve the performance of models based on days 1-3, while the model based on the expression profile of plasma cells deconvoluted from the model that used DEGs at day 7 as predictors showed an improved performance in external validation. Our study emphasizes the value of using combination modeling strategy and leveraging information from single-cell levels in constructing influenza vaccine response predictive models.

AI-based morphologic model for prediction of individual patient response to immune checkpoint inhibitors for bladder cancer.

686 Background: Immune checkpoint inhibitors (ICI) have been used to treat advanced muscle invasive and/or metastatic bladder cancer. However, ICIs are only effective in 30-40% of cases. In light of potentially significant IRAE’s, tools to predict individual patient level benefits are desirable. AI technology offers the opportunity to apply computational methods to predict outcomes from readily available digitized pathology slides. We investigated the utility of an AI platform integrating computational biomarkers based on morphological characterization of digitized H&E slide whole images (WSI) to predict response to ICI. Methods: We analyzed H&E-stained whole slide images (WSI) of bladder tumor tissue collected from transurethral resection of bladder tumor (TURBT) from 116 patients with advanced or metastatic bladder cancer at a single institution between 2015-2020. Adjacent multiplex IHC stained specimens were analyzed myeloid and lymphoid marker panels. 20 patients from the overall cohort treated with ICI were designated ‘responders’ (complete response, partial response, stable disease) and 20 patients were identified as non-responders (progressive disease) based on ICI best clinical/radiographic response. WSIs were divided into small non-overlapping image patches. These image tiles were processed into multiple AI encoder models to extract morphological features. The tile morphological features, represented by high dimensional vectors, were combined by an aggregation model to represent the whole slide morphology and then used to classify the patients into responders vs non-responders to immunotherapy. Area-under-the-receiver operating characteristic (AUC) was used to measure the performance of response prediction. Results: Our method shows AUC of 0.708 at classification of the patients (n=40) into responder and non-responder groups. With a cutoff that identifies the top 50% patients (n=20) of high probability of responding to immunotherapy predicted by our models, 75% of them are responders. In the bottom 50% patients (n=20) of the low scores, 75% of them are non-responders. . Multiplex IHC (myeloid and lymphoid panel) was performed using adjacent sections and were characterized yielding deeper mechanistic insight into the inflammatory populations driving predictive morphologic patterns. Conclusions: By applying innovative AI morphological analysis on patient WSIs, we generated a computational biomarker that shows promising ability to predict patient response to immunotherapy in bladder cancer. This approach merits future prospective validation and additional patient level analysis in broader cohorts. [Table: see text]

M1 macrophage-related gene model for NSCLC immunotherapy response prediction.

Patients diagnosed with non-small cell lung cancer (NSCLC) have a limited lifespan and exhibit poor immunotherapy outcomes. M1 macrophages have been found to be essential for antitumor immunity. This study aims to develop an immunotherapy response evaluation model for NSCLC patients based on transcription. RNA sequencing profiles of 254 advanced-stage NSCLC patients treated with immunotherapy are downloaded from the POPLAR and OAK projects. Immune cell infiltration in NSCLC patients is examined, and thereafter, different coexpressed genes are identified. Next, the impact of M1 macrophage-related genes on the prognosis of NSCLC patients is investigated. Six M1 macrophage coexpressed genes, namely, NKX2-1, CD8A , SFTA3, IL2RB, IDO1, and CXCL9, exhibit a strong association with the prognosis of NSCLC and serve as effective predictors for immunotherapy response. A response model is constructed using a Cox regression model and Lasso Cox regression analysis. The M1 genes are validated in our TD-FOREKNOW NSCLC clinical trial by RT-qPCR. The response model shows excellent immunotherapy response prediction and prognosis evaluation value in advanced-stage NSCLC. This model can effectively predict advanced NSCLC prognosis and aid in identifying patients who could benefit from customized immunotherapy as well as sensitive drugs.

Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study.

Introduction: Early predictive pathological complete response (pCR) is beneficial for optimizing neoadjuvant chemotherapy (NAC) strategies for breast cancer. The hematoxylin and eosin (HE)-stained slices of biopsy tissues contain a large amount of information on tumor epithelial cells and stromal. The fusion of pathological image features and clinicopathological features is expected to build a model to predict pCR of NAC in breast cancer. Methods: We retrospectively collected a total of 440 breast cancer patients from three hospitals who underwent NAC. HE-stained slices of biopsy tissues were scanned to form whole-slide images (WSIs), and pathological images of representative regions of interest (ROI) of each WSI were selected at different magnifications. Based on several different deep learning models, we propose a novel feature extraction method on pathological images with different magnifications. Further, fused with clinicopathological features, a multimodal breast cancer NAC pCR prediction model based on a support vector machine (SVM) classifier was developed and validated with two additional validation cohorts (VCs). Results: Through experimental validation of several different deep learning models, we found that the breast cancer pCR prediction model based on the SVM classifier, which uses the VGG16 model for feature extraction of pathological images at ×20 magnification, has the best prediction efficacy. The area under the curve (AUC) of deep learning pathological model (DPM) were 0.79, 0.73, and 0.71 for TC, VC1, and VC2, respectively, all of which exceeded 0.70. The AUCs of clinical model (CM), a clinical prediction model established by using clinicopathological features, were 0.79 for TC, 0.73 for VC1, and 0.71 for VC2, respectively. The multimodal deep learning clinicopathological model (DPCM) established by fusing pathological images and clinicopathological features improved the AUC of TC from 0.79 to 0.84. The AUC of VC2 improved from 0.71 to 0.78. Conclusion: Our study reveals that pathological images of HE-stained slices of pre-NAC biopsy tissues can be used to build a pCR prediction model. Combining pathological images and clinicopathological features can further enhance the predictive efficacy of the model.

A prediction model for response to immune checkpoint inhibition in advanced melanoma.

Predicting who will benefit from treatment with immune checkpoint inhibition (ICI) in patients with advanced melanoma is challenging. We developed a multivariable prediction model for response to ICI, using routinely available clinical data including primary melanoma characteristics. We used a population-based cohort of 3525 patients with advanced cutaneous melanoma treated with anti-PD-1-based therapy. Our prediction model for predicting response within 6 months after ICI initiation was internally validated with bootstrap resampling. Performance evaluation included calibration, discrimination and internal-external cross-validation. Included patients received anti-PD-1 monotherapy (n = 2366) or ipilimumab plus nivolumab (n = 1159) in any treatment line. The model included serum lactate dehydrogenase, World Health Organization performance score, type and line of ICI, disease stage and time to first distant recurrence-all at start of ICI-, and location and type of primary melanoma, the presence of satellites and/or in-transit metastases at primary diagnosis and sex. The over-optimism adjusted area under the receiver operating characteristic was 0.66 (95% CI: 0.64-0.66). The range of predicted response probabilities was 7%-81%. Based on these probabilities, patients were categorized into quartiles. Compared to the lowest response quartile, patients in the highest quartile had a significantly longer median progression-free survival (20.0 vs 2.8 months; P < .001) and median overall survival (62.0 vs 8.0 months; P < .001). Our prediction model, based on routinely available clinical variables and primary melanoma characteristics, predicts response to ICI in patients with advanced melanoma and discriminates well between treated patients with a very good and very poor prognosis.

Expected Usefulness of Fourth Dose of COVID-19 Vaccine for Patients with Underlying Solid Tumor who Previously Received the Primary Heterologous COVID-19 Vaccine

AbstractCoronavirus disease 2019 (COVID-19) immunization frequently requires two standard doses. Due to the likelihood that the population may lose immunity after receiving a standard mass vaccination and the potential for the introduction of a new strain, several scientists are currently advocating the use of a booster dosage of the vaccine.The authors of this retrospective study used a clinical model for immune response prediction to forecast how solid cancer patients will respond to the fourth dosage of the COVID-19 immunization. In the case of homologous primary backgrounds, the prospective rates of extension of protective efficacy for using viral vector and messenger ribonucleic acid (mRNA) COVID-19 vaccines for vaccinees with underlying solid tumor are equal to 11.5 and 16.5%, respectively. In the event of heterologous primary backgrounds, the prospective rates of extension of protective efficacy for using viral vector and mRNA COVID-19 vaccines are equal to 2.2 and 7.2%, respectively, for patients with underlying solid cancer. In conclusion, the fourth dose of the COVID-19 vaccine regimen had an effect on the immunogenicity of vaccine recipients with underlying malignancy.

A CAR-T response prediction model for r/r B-NHL patients based on a T cell subset nomogram

BackgroundChimeric antigen receptor (CAR) T cells for refractory or relapsed (r/r) B cell no-Hodgkin lymphoma (NHL) patients have shown promising clinical effectiveness. However, the factors impacting the clinical response of CAR-T therapy have not been fully elucidated. We here investigate the independent influencing factors of the efficacy of CD19 CAR-T cell infusion in the treatment of r/r B-NHL and to establish an early prediction model.MethodsA total of 43 r/r B-NHL patients were enrolled in this retrospective study. The patients’ general data were recorded, and the primary endpoint is the patients’ treatment response. The independent factors of complete remission (CR) and partial remission (PR) were investigated by univariate and binary logistic regression analysis, and the prediction model of the probability of CR was constructed according to the determined independent factors. Receiver operating characteristic (ROC) and calibration plot were used to assess the discrimination and calibration of the established model. Furthermore, we collected 15 participators to validate the model.ResultsUnivariate analysis and binary logistic regression analysis of 43 patients showed that the ratio of central memory T cell (Tcm) and naïve T cell (Tn) in cytotoxic T cells (Tc) was an independent risk factor for response to CD19 CAR-T cell therapy in r/r B-NHL. On this basis, the area under the curve (AUC) of Tcm in the Tc and Tn in the Tc nomogram model was 0.914 (95%CI 0.832–0.996), the sensitivity was 83%, and the specificity was 74.2%, which had excellent predictive value. We did not found the difference of the progression-free survival (PFS).ConclusionsThe ratio of Tcm and Tn in Tc was found to be able to predict the treatment response of CD19 CAR-T cells in r/r B-NHL. We have established a nomogram model for the assessment of the CD19 CAR-T therapy response presented high specificity and sensitivity.

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction is of paramount importance for both preclinical drug screening studies and clinical treatment design. To build drug response prediction models, treatment response data need to be generated through screening experiments and used as input to train the prediction models. In this study, we investigate various active learning strategies of selecting experiments to generate response data for the purposes of (1) improving the performance of drug response prediction models built on the data and (2) identifying effective treatments. Here, we focus on constructing drug-specific response prediction models for cancer cell lines. Various approaches have been designed and applied to select cell lines for screening, including a random, greedy, uncertainty, diversity, combination of greedy and uncertainty, sampling-based hybrid, and iteration-based hybrid approach. All of these approaches are evaluated and compared using two criteria: (1) the number of identified hits that are selected experiments validated to be responsive, and (2) the performance of the response prediction model trained on the data of selected experiments. The analysis was conducted for 57 drugs and the results show a significant improvement on identifying hits using active learning approaches compared with the random and greedy sampling method. Active learning approaches also show an improvement on response prediction performance for some of the drugs and analysis runs compared with the greedy sampling method.

Integrated drug response prediction models pinpoint repurposed drugs with effectiveness against rhabdomyosarcoma.

Targeted therapies for inhibiting the growth of cancer cells or inducing apoptosis are urgently needed for effective rhabdomyosarcoma (RMS) treatment. However, identifying cancer-targeting compounds with few side effects, among the many potential compounds, is expensive and time-consuming. A computational approach to reduce the number of potential candidate drugs can facilitate the discovery of attractive lead compounds. To address this and obtain reliable predictions of novel cell-line-specific drugs, we apply prediction models that have the potential to improve drug discovery approaches for RMS treatment. The results of two prediction models were ensemble and validated via in vitro experiments. The computational models were trained using data extracted from the Genomics of Drug Sensitivity in Cancer database and tested on two RMS cell lines to select potential RMS drug candidates. Among 235 candidate drugs, 22 were selected following the result of the computational approach, and three candidate drugs were identified (NSC207895, vorinostat, and belinostat) that showed selective effectiveness in RMS cell lines in vitro via the induction of apoptosis. Our in vitro experiments have demonstrated that our proposed methods can effectively identify and repurpose drugs for treating RMS.

Construction of disulfidptosis-based immune response prediction model with artificial intelligence and validation of the pivotal grouping oncogene c-MET in regulating T cell exhaustion.

Given the lack of research on disulfidptosis, our study aimed to dissect its role in pan-cancer and explore the crosstalk between disulfidptosis and cancer immunity. Based on TCGA, ICGC, CGGA, GSE30219, GSE31210, GSE37745, GSE50081, GSE22138, GSE41613, univariate Cox regression, LASSO regression, and multivariate Cox regression were used to construct the rough gene signature based on disulfidptosis for each type of cancer. SsGSEA and Cibersort, followed by correlation analysis, were harnessed to explore the linkage between disulfidptosis and cancer immunity. Weighted correlation network analysis (WGCNA) and Machine learning were utilized to make a refined prognosis model for pan-cancer. In particular, a customized, enhanced prognosis model was made for glioma. The siRNA transfection, FACS, ELISA, etc., were employed to validate the function of c-MET. The expression comparison of the disulfidptosis-related genes (DRGs) between tumor and nontumor tissues implied a significant difference in most cancers. The correlation between disulfidptosis and immune cell infiltration, including T cell exhaustion (Tex), was evident, especially in glioma. The 7-gene signature was constructed as the rough model for the glioma prognosis. A pan-cancer suitable DSP clustering was made and validated to predict the prognosis. Furthermore, two DSP groups were defined by machine learning to predict the survival and immune therapy response in glioma, which was validated in CGGA. PD-L1 and other immune pathways were highly enriched in the core blue gene module from WGCNA. Among them, c-MET was validated as a tumor driver gene and JAK3-STAT3-PD-L1/PD1 regulator in glioma and T cells. Specifically, the down-regulation of c-MET decreased the proportion of PD1+ CD8+ T cells. To summarize, we dissected the roles of DRGs in the prognosis and their relationship with immunity in pan-cancer. A general prognosis model based on machine learning was constructed for pan-cancer and validated by external datasets with a consistent result. In particular, a survival-predicting model was made specifically for patients with glioma to predict its survival and immune response to ICIs. C-MET was screened and validated for its tumor driver gene and immune regulation function (inducing t-cell exhaustion) in glioma.