scholarly journals A Pan-Cancer Approach to Predict Responsiveness to Immune Checkpoint Inhibitors by Machine Learning

Cancers ◽  
2019 ◽  
Vol 11 (10) ◽  
pp. 1562 ◽  
Author(s):  
Maurizio Polano ◽  
Marco Chierici ◽  
Michele Dal Bo ◽  
Davide Gentilini ◽  
Federica Di Cintio ◽  
...  
Keyword(s):  
Machine Learning ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Checkpoint Inhibitors ◽  
Support Vector ◽  
Learning Approach ◽  
Expression Data ◽  
Machine Learning Approach ◽  
Cancer Types ◽  
Pan Cancer

Immunotherapy by using immune checkpoint inhibitors (ICI) has dramatically improved the treatment options in various cancers, increasing survival rates for treated patients. Nevertheless, there are heterogeneous response rates to ICI among different cancer types, and even in the context of patients affected by a specific cancer. Thus, it becomes crucial to identify factors that predict the response to immunotherapeutic approaches. A comprehensive investigation of the mutational and immunological aspects of the tumor can be useful to obtain a robust prediction. By performing a pan-cancer analysis on gene expression data from the Cancer Genome Atlas (TCGA, 8055 cases and 29 cancer types), we set up and validated a machine learning approach to predict the potential for positive response to ICI. Support vector machines (SVM) and extreme gradient boosting (XGboost) models were developed with a 10×5-fold cross-validation schema on 80% of TCGA cases to predict ICI responsiveness defined by a score combining tumor mutational burden and TGF- β signaling. On the remaining 20% validation subset, our SVM model scored 0.88 accuracy and 0.27 Matthews Correlation Coefficient. The proposed machine learning approach could be useful to predict the putative response to ICI treatment by expression data of primary tumors.

Immune Checkpoint Inhibitors: Basics and Challenges

2019 ◽  
Vol 26 (17) ◽  
pp. 3009-3025 ◽  
Author(s):  
Bin Li ◽  
Ho Lam Chan ◽  
Pingping Chen
Keyword(s):  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Checkpoint Inhibitors ◽  
Complete Response ◽  
Modern World ◽  
Basic Principles ◽  
Mutation Status ◽  
Anti Cancer ◽  
Cancer Types ◽  
Shed Light

Cancer is one of the most deadly diseases in the modern world. The last decade has witnessed dramatic advances in cancer treatment through immunotherapy. One extremely promising means to achieve anti-cancer immunity is to block the immune checkpoint pathways – mechanisms adopted by cancer cells to disguise themselves as regular components of the human body. Many review articles have described a variety of agents that are currently under extensive clinical evaluation. However, while checkpoint blockade is universally effective against a broad spectrum of cancer types and is mostly unrestricted by the mutation status of certain genes, only a minority of patients achieve a complete response. In this review, we summarize the basic principles of immune checkpoint inhibitors in both antibody and smallmolecule forms and also discuss potential mechanisms of resistance, which may shed light on further investigation to achieve higher clinical efficacy for these inhibitors.

scholarly journals Immune-Related Adverse Events (irAE) in Cancer Immune Checkpoint Inhibitors (ICI) and Survival Outcomes Correlation: To Rechallenge or Not?

Cancers ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 989
Author(s):  
Heidar J. Albandar ◽  
Jacob Fuqua ◽  
Jasim M. Albandar ◽  
Salahuddin Safi ◽  
Samuel A. Merrill ◽  
...  
Keyword(s):  
Adverse Events ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Checkpoint Inhibitors ◽  
Survival Outcomes ◽  
Limited Data ◽  
Risk Of Death ◽  
Survival Difference ◽  
Histopathologic Diagnosis ◽  
Cancer Types

Introduction: There is growing recognition of immune related adverse events (irAEs) from immune checkpoint therapies being correlated with treatment outcomes in certain malignancies. There are currently limited data or consensus to guide management of irAEs with regards to treatment rechallenge. Methods: We conducted a retrospective analysis with an IRB-approved protocol of adult patients seen at the WVU Cancer Institute between 2011–2019 with a histopathologic diagnosis of active cancers and were treated with immune checkpoint inhibitors (ICI) therapy. Results: Demographics were similar between the ICI interrupted irAE groups within cancer types. Overall, out of 548 patients who received ICI reviewed, there were 133 cases of ≥1 irAE found of any grade. Being treated with anti-CTLA-4 inhibitor ICI was associated with lower risk of death compared to anti-PD-1 ICI. The overall survival difference observed for irAE positive patients, between rechallenged (37.8 months, reinitiated with/without interruption; 38.6 months, reinitiated after interruption) and interrupted/non-reinitiated (i.e., discontinued) groups (24.9 months) was not statistically significant, with a numerical trend favoring the former. Conclusions: Our exploratory study did not identify significantly different survival outcomes among the Appalachian West Virginia adult cancer patients treated with ICI who developed irAE and had treatment reinitiated after interruption, when compared with those not reinitiated.

Genetic ancestry and clinical outcomes to immune checkpoint inhibitors among seven common cancers.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 10536-10536
Author(s):  
Amin Nassar ◽  
Elio Adib ◽  
Sarah Abou Alaiwi ◽  
Elie Akl ◽  
Talal El Zarif ◽  
...  
Keyword(s):  
Cell Carcinoma ◽  
Clinical Outcomes ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Checkpoint Inhibitors ◽  
East Asian ◽  
Genetic Ancestry ◽  
Sequencing Data ◽  
Histologic Subtype ◽  
Cancer Types

10536 Background: Prior studies and clinical trials report associations between self-reported race and clinical outcomes to Immune Checkpoint Inhibitors (ICIs). However, comprehensive studies of ancestry-associated differences in clinical outcomes have not been performed. We derived genetic ancestry scores and assessed clinical outcomes in 1341 patients with cancer treated with ICIs. Methods: Patients at the Dana-Farber Cancer Institute treated with ICIs only and with relevant cancer types and targeted exome sequencing data (Oncopanel) were included. Relevant cancer types included colorectal adenocarcinoma (CRC), esophagogastric adenocarcinoma (EGC), head and neck squamous cell carcinoma (HNSCC), melanoma, non-small cell lung cancer (NSCLC), renal cell carcinoma (RCC), and urothelial carcinoma (UC). We developed a bioinformatics pipeline to infer fine-scale genetic ancestry for each patient (n=1341) directly from tumor sequencing data by leveraging off and on-target sequenced reads and external ancestry reference panels. Three ancestry scores were determined (African, East Asian, European). Overall survival (OS) and time-to-treatment failure (TTF) were compared by Cox logistic regression between ancestral populations. Hazard ratio (HR) was derived using multivariable analysis, adjusted for single versus combination therapy, prior lines of therapy, and tumor mutational burden (TMB, as percentiles). Results: Median follow-up was 37.8 months (m; interquartile range: 35.7-39.5m). Common cancer types included CRC (n=52), EGC (n=114), HNSCC (n=88), melanoma (n=274), NSCLC (n=571), RCC (n=99), and UC (n=143). A higher East Asian ancestry (EAS) was significantly associated with worse OS ( p=0.03) and TTF ( p=0.002) in patients with RCC, independent of the histologic subtype (Table). There was no significant association between any of the three ancestral populations and clinical outcomes in the other 6 cancer types. Conclusions: We described clinical outcomes to ICIs across three global populations in 7 cancers. As the medical field re-evaluates the use of self-reported race in clinical decision-making, we utilize a novel ancestry pipeline that can be readily applied to tumor-only sequencing panels and better characterize non-white populations. We find no ancestry differences in clinical outcomes except in patients with RCC treated with ICIs which will require future validation. We plan to analyze genomic correlates of response by ancestry in each of the cancer types to better understand these diverge clinical behaviors.[Table: see text]

scholarly journals Distribution Grids Fault Location employing ST based Optimized Machine Learning Approach

Energies ◽  
2018 ◽  
Vol 11 (9) ◽  
pp. 2328 ◽  
Author(s):  
Md Shafiullah ◽  
M. Abido ◽  
Taher Abdel-Fattah
Keyword(s):  
Machine Learning ◽  
Fault Location ◽  
Percentage Error ◽  
Support Vector ◽  
Learning Approach ◽  
Efficiency Coefficient ◽  
Learning Tools ◽  
Performance Indices ◽  
Machine Learning Approach ◽  
Distribution Grids

Precise information of fault location plays a vital role in expediting the restoration process, after being subjected to any kind of fault in power distribution grids. This paper proposed the Stockwell transform (ST) based optimized machine learning approach, to locate the faults and to identify the faulty sections in the distribution grids. This research employed the ST to extract useful features from the recorded three-phase current signals and fetches them as inputs to different machine learning tools (MLT), including the multilayer perceptron neural networks (MLP-NN), support vector machines (SVM), and extreme learning machines (ELM). The proposed approach employed the constriction-factor particle swarm optimization (CF-PSO) technique, to optimize the parameters of the SVM and ELM for their better generalization performance. Hence, it compared the obtained results of the test datasets in terms of the selected statistical performance indices, including the root mean squared error (RMSE), mean absolute percentage error (MAPE), percent bias (PBIAS), RMSE-observations to standard deviation ratio (RSR), coefficient of determination (R2), Willmott’s index of agreement (WIA), and Nash–Sutcliffe model efficiency coefficient (NSEC) to confirm the effectiveness of the developed fault location scheme. The satisfactory values of the statistical performance indices, indicated the superiority of the optimized machine learning tools over the non-optimized tools in locating faults. In addition, this research confirmed the efficacy of the faulty section identification scheme based on overall accuracy. Furthermore, the presented results validated the robustness of the developed approach against the measurement noise and uncertainties associated with pre-fault loading condition, fault resistance, and inception angle.

scholarly journals Pan-Cancer Analysis Identifies Liver Metastases as Negative Predictive Factor for Immune Checkpoint Inhibitors Treatment Outcome

2021 ◽  
Vol 12 ◽  
Author(s):  
Xiao-Juan Chen ◽  
Aiqun Ren ◽  
Liang Zheng ◽  
En-Dian Zheng ◽  
Tao Jiang
Keyword(s):  
Combination Therapy ◽  
Liver Metastases ◽  
Predictive Factor ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Checkpoint Inhibitors ◽  
Intrinsic Resistance ◽  
The Impact ◽  
Pan Cancer ◽  
Negative Predictive Factor

This study aimed to investigate the predictive value of liver metastases (LM) in patients with various advanced cancers received immune-checkpoint inhibitors (ICIs). First, clinical and survival data from a published cohort of 1,661 patients who received ICIs therapy were downloaded and analyzed. Second, a retrospective review of 182 patients with advanced non-small-cell lung cancer (NSCLC) who received PD-1/PD-L1 monotherapy was identified. Third, a meta-analysis of published trials was performed to explore the impact of LM on the efficacy of anti-PD-1/PD-L1 based therapy in advanced lung cancers. Pan-cancer analysis revealed that patients with LM had significantly shorter overall survival (OS) than those without LM (10 vs. 20 months; P < 0.0001). Subgroup analysis showed that the presence of LM was associated with markedly shorter OS than those without LM in ICI monotherapy group (P < 0.0001), but it did not reach the statistical significance in ICI-based combination therapy (P = 0.0815). In NSCLC, the presence of LM was associated with significantly inferior treatment outcomes in both pan-cancer and real-world cohort. Interestingly, ICI-based monotherapy and combination therapy could simultaneously prolong progression-free survival (PFS) and OS than chemotherapy in patients without LM. However, ICI-based monotherapy could not prolong PFS than chemotherapy in patients with LM while ICI-based combination therapy could dramatically prolong both PFS and OS. Together, these findings suggested that the presence of LM was the negative predictive factor in cancer patients received ICIs monotherapy, especially in NSCLC. ICI-based combination therapy might overcome the intrinsic resistance of LM to ICIs while the optimal combinatorial strategies remain under further investigation.

scholarly journals Arabic English Cross-Lingual Plagiarism Detection Based on Keyphrases Extraction, Monolingual and Machine Learning Approach

2019 ◽  
pp. 1-12
Author(s):  
Mokhtar Al-Suhaiqi ◽  
Muneer A. S. Hazaa ◽  
Mohammed Albared
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Detection Methods ◽  
Support Vector ◽  
Svm Classifier ◽  
Learning Approach ◽  
Plagiarism Detection ◽  
Machine Learning Approach ◽  
Cross Lingual ◽  
Cross Language

Due to rapid growth of research articles in various languages, cross-lingual plagiarism detection problem has received increasing interest in recent years. Cross-lingual plagiarism detection is more challenging task than monolingual plagiarism detection. This paper addresses the problem of cross-lingual plagiarism detection (CLPD) by proposing a method that combines keyphrases extraction, monolingual detection methods and machine learning approach. The research methodology used in this study has facilitated to accomplish the objectives in terms of designing, developing, and implementing an efficient Arabic – English cross lingual plagiarism detection. This paper empirically evaluates five different monolingual plagiarism detection methods namely i)N-Grams Similarity, ii)Longest Common Subsequence, iii)Dice Coefficient, iv)Fingerprint based Jaccard Similarity  and v) Fingerprint based Containment Similarity. In addition, three machine learning approaches namely i) naïve Bayes, ii) Support Vector Machine, and iii) linear logistic regression classifiers are used for Arabic-English Cross-language plagiarism detection. Several experiments are conducted to evaluate the performance of the key phrases extraction methods. In addition, Several experiments to investigate the performance of machine learning techniques to find the best method for Arabic-English Cross-language plagiarism detection. According to the experiments of Arabic-English Cross-language plagiarism detection, the highest result was obtained using SVM   classifier with 92% f-measure. In addition, the highest results were obtained by all classifiers are achieved, when most of the monolingual plagiarism detection methods are used. 

Sign in / Sign up

Export Citation Format

Share Document