scholarly journals Applications of Machine Learning to Predict Cisplatin Resistance in Lung Cancer

Author(s):  
Yanan Gao ◽  
Qiong Lyu ◽  
Rui Zhou ◽  
Peng Luo ◽  
Jian Zhang ◽  
...  

Abstract Background: Lung cancer, mainly including lung adenocarcinoma, lung squamous cell carcinoma and small cell lung cancer, is the cancer with the highest incidence and cancer-related mortality in the world. Platinum-based chemotherapy plays an important role in the treatment of various lung cancer subtypes, but not all patients can benefit from it, so it is worth identifying lung cancer patients who are resistant or insensitive.Method: The drug response and sequencing data of 170 lung cancer cell lines were downloaded from the Genomics of Drug Sensitivity in Cancer (GDSC) database, and support vector machines (SVMs) and beam search were used to select an optimal gene panel that can predict the sensitivity of cell lines to cisplatin. Then, we used the available cell line data to explore the potential mechanisms.Result: In this study, SVMs and beam search were used to screen a 9-gene panel related to lung cancer cell line resistance to cisplatin, with an area under the curve (AUC) of 0.873 ± 0.004. The natural logarithm of the half maximal inhibitory concentration (lnIC50) values of the panel-MT group were significantly higher than those of the panel-WT group, regardless of whether lung cancer subtype was considered. In addition, we found that the differentially expressed pathways between the two groups may explain the difference.Conclusion: In this study, we found that a panel including nine genes (PLXNC1, KIAA0649, SPTBN4, SLC14A2, F13A1, COL5A1, SCN2A, PLEC, and ALMS1) can accurately predict sensitivity to cisplatin, which may provide individualized treatment recommendations to improve the prognosis of patients with lung cancer.

2019 ◽  
Vol 18 ◽  
pp. 153303381986197 ◽  
Author(s):  
Xiaohong Yan ◽  
Hui Yu ◽  
Yao Liu ◽  
Jie Hou ◽  
Qiao Yang ◽  
...  

MicroRNA-27a-3p has been implicated to play crucial roles in human cancers. However, the biological role and underlying mechanisms of microRNA-27a-3p in regulating nonsmall lung cancer remain unclear. MicroRNA-27a-3p expression levels in non-small lung cancer cell lines were detected by quantitative real-time polymerase chain reaction, using a normal cell line as control. The effects of microRNA-27a-3p on cell proliferation and apoptosis were analyzed by Cell Counting Kit-8 assay and flow cytometry assay. Luciferase activity reporter assay and Western blot were conducted to validate the potential targets of miR27a-3p after preliminary screening by TargetScan. Effect of microRNA-27a-3p or homeobox B8 on the overall survival of patients with non-small lung cancer was analyzed at Kaplan-Meier Plotter website. MicroRNA-27a-3p expression levels were significantly reduced in non-small lung cancer cell lines compared with normal cell line. Overexpression of microRNA-27a-3p inhibits non-small lung cancer cell proliferation but promotes cell apoptosis. Homeobox B8 was further validated as a functional target of microRNA-27a-3p. Collectively, our results indicated that microRNA-27a-3p acts as a tumor suppressor in non-small lung cancer via targeting homeobox B8.


Blood ◽  
1993 ◽  
Vol 82 (9) ◽  
pp. 2837-2844 ◽  
Author(s):  
MS Topp ◽  
M Koenigsmann ◽  
A Mire-Sluis ◽  
D Oberberg ◽  
F Eitelbach ◽  
...  

Abstract Cytokines play an important role in activating the immune system against malignant cells. One of these cytokines, interleukin-4 (IL-4) has entered clinical phase I trials because of its immunoregulatory potency. In the present study we report that recombinant human (rh) IL- 4 has major direct antiproliferative effects on one human lung cancer cell line (CCL 185) in vitro as measured by a human tumor cloning assay (HTCA), tritiated thymidine uptake, and counting cell numbers and marginal activity in a second cell line (HTB 56) in the HTCA. This activity could be abolished by neutralizing antibody against rhIL-4. The biological response of the tumor cells to the cytokine is correlated with expression of receptors for human IL-4 on both the mRNA level and the protein level. The responsive cell line, CCL 185, secretes IL-6 after being incubated with rhIL-4. On the other hand, neutralizing antibodies against IL-6 showed no influence on the growth modulatory efficacy of rhIL-4 in this cell line. Furthermore, CCL 185 does not show detectable production of IL-1, tumor necrosis factor alpha or interferon gamma after incubation with rhIL-4. Thus, the response to rhIL-4 is not mediated through autocrine production of these cytokines triggered by rhIL-4. In a next series of experiments some of the cell lines were xenotransplanted to BALB/c nu/nu mice. Subsequently, the mice were treated for 12 days with two doses of 0.5 mg/m2 rhIL-4 or control vehicle subcutaneously per day. Treatment with rhIL-4 yielded a significant inhibition of tumor growth versus control in two of the non-small cell lung cancer cell lines being responsive in vitro (CCL 185, HTB 56). Histology of the tumors in both groups showed no marked infiltration of the tumors with murine hematopoietic and lymphocytic cells consistent with the species specificity of IL-4. In contrast, no tumor growth inhibition was found in the small cell lung cancer cell lines (HTB 119, HTB 120) being nonresponsive in vitro. We conclude that rhIL-4 has direct antiproliferative effects on the growth of some human non-small cell lung cancer cell lines in vitro and in vivo, which together with its regulatory effects on various effector cell populations makes this cytokine an interesting candidate for further investigation in experimental cancer treatment.


2021 ◽  
Author(s):  
K. Bougoffa-Sadaoui ◽  
F. Maiza-Benabdesselam ◽  
H. Ouadid-Ahidouch

Little information is reported on the antitumor effects of isoquinoline alkaloids, particularly protopine, a major component of Fumaria agraria, on lung cancer. The purpose of our study is to determine the cytotoxic effect of protopine from an extraction by fractionation of the aerial part of Fumaria agraria on two lung cancer cell lines, NCI-H23 and NCI-H460. The basic fraction containing protopine (60.7%) has cytotoxicity to the two lung cancer cell lines studied here. The cell line NCI-H460 is more sensitive after 72 h of treatment by protopine with an IC50 of 08.5 ± 0.09 μMthan the cell line NCI-H23 (IC50 = 14.8 ± 0.03 μM).


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hadi Hashemzadeh ◽  
Seyedehsamaneh Shojaeilangari ◽  
Abdollah Allahverdi ◽  
Mario Rothbauer ◽  
Peter Ertl ◽  
...  

AbstractLung cancer is a leading cause of cancer death in both men and women worldwide. The high mortality rate in lung cancer is in part due to late-stage diagnostics as well as spread of cancer-cells to organs and tissues by metastasis. Automated lung cancer detection and its sub-types classification from cell’s images play a crucial role toward an early-stage cancer prognosis and more individualized therapy. The rapid development of machine learning techniques, especially deep learning algorithms, has attracted much interest in its application to medical image problems. In this study, to develop a reliable Computer-Aided Diagnosis (CAD) system for accurately distinguishing between cancer and healthy cells, we grew popular Non-Small Lung Cancer lines in a microfluidic chip followed by staining with Phalloidin and images were obtained by using an IX-81 inverted Olympus fluorescence microscope. We designed and tested a deep learning image analysis workflow for classification of lung cancer cell-line images into six classes, including five different cancer cell-lines (P-C9, SK-LU-1, H-1975, A-427, and A-549) and normal cell-line (16-HBE). Our results demonstrate that ResNet18, a residual learning convolutional neural network, is an efficient and promising method for lung cancer cell-lines categorization with a classification accuracy of 98.37% and F1-score of 97.29%. Our proposed workflow is also able to successfully distinguish normal versus cancerous cell-lines with a remarkable average accuracy of 99.77% and F1-score of 99.87%. The proposed CAD system completely eliminates the need for extensive user intervention, enabling the processing of large amounts of image data with robust and highly accurate results.


Cancers ◽  
2021 ◽  
Vol 13 (14) ◽  
pp. 3477
Author(s):  
Elisabetta Sauta ◽  
Francesca Reggiani ◽  
Federica Torricelli ◽  
Eleonora Zanetti ◽  
Elena Tagliavini ◽  
...  

Lung cancer is the leading cause of cancer-related human death. It is a heterogeneous disease, classified in two main histotypes, small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC), which is further subdivided into squamous-cell carcinoma (SCC) and adenocarcinoma (AD) subtypes. Despite the introduction of innovative therapeutics, mainly designed to specifically treat AD patients, the prognosis of lung cancer remains poor. In particular, available treatments for SCLC and SCC patients are currently limited to platinum-based chemotherapy and immune checkpoint inhibitors. In this work, we used an integrative approach to identify novel vulnerabilities in lung cancer. First, we compared the data from a CRISPR/Cas9 dependency screening performed in our laboratory with Cancer Dependency Map Project data, essentiality comprising information on 73 lung cancer cell lines. Next, to identify relevant therapeutic targets, we integrated dependency data with pharmacological data and TCGA gene expression information. Through this analysis, we identified CSNK1A1, KDM2A, and LTB4R2 as relevant druggable essentiality genes in lung cancer. We validated the antiproliferative effect of genetic or pharmacological inhibition of these genes in two lung cancer cell lines. Overall, our results identified new vulnerabilities associated with different lung cancer histotypes, laying the basis for the development of new therapeutic strategies.


Blood ◽  
1993 ◽  
Vol 82 (9) ◽  
pp. 2837-2844
Author(s):  
MS Topp ◽  
M Koenigsmann ◽  
A Mire-Sluis ◽  
D Oberberg ◽  
F Eitelbach ◽  
...  

Cytokines play an important role in activating the immune system against malignant cells. One of these cytokines, interleukin-4 (IL-4) has entered clinical phase I trials because of its immunoregulatory potency. In the present study we report that recombinant human (rh) IL- 4 has major direct antiproliferative effects on one human lung cancer cell line (CCL 185) in vitro as measured by a human tumor cloning assay (HTCA), tritiated thymidine uptake, and counting cell numbers and marginal activity in a second cell line (HTB 56) in the HTCA. This activity could be abolished by neutralizing antibody against rhIL-4. The biological response of the tumor cells to the cytokine is correlated with expression of receptors for human IL-4 on both the mRNA level and the protein level. The responsive cell line, CCL 185, secretes IL-6 after being incubated with rhIL-4. On the other hand, neutralizing antibodies against IL-6 showed no influence on the growth modulatory efficacy of rhIL-4 in this cell line. Furthermore, CCL 185 does not show detectable production of IL-1, tumor necrosis factor alpha or interferon gamma after incubation with rhIL-4. Thus, the response to rhIL-4 is not mediated through autocrine production of these cytokines triggered by rhIL-4. In a next series of experiments some of the cell lines were xenotransplanted to BALB/c nu/nu mice. Subsequently, the mice were treated for 12 days with two doses of 0.5 mg/m2 rhIL-4 or control vehicle subcutaneously per day. Treatment with rhIL-4 yielded a significant inhibition of tumor growth versus control in two of the non-small cell lung cancer cell lines being responsive in vitro (CCL 185, HTB 56). Histology of the tumors in both groups showed no marked infiltration of the tumors with murine hematopoietic and lymphocytic cells consistent with the species specificity of IL-4. In contrast, no tumor growth inhibition was found in the small cell lung cancer cell lines (HTB 119, HTB 120) being nonresponsive in vitro. We conclude that rhIL-4 has direct antiproliferative effects on the growth of some human non-small cell lung cancer cell lines in vitro and in vivo, which together with its regulatory effects on various effector cell populations makes this cytokine an interesting candidate for further investigation in experimental cancer treatment.


2008 ◽  
Vol 3 (10) ◽  
pp. 1934578X0800301 ◽  
Author(s):  
Fabiola Salas ◽  
Janne Rojas ◽  
Antonio Morales ◽  
Maria E. Ramos-Nino ◽  
Nelida G. Colmenares

Sesamin extracted from Vismia baccifera var. dealbata was demonstrated to have cytostatic activity on the cancer cell lines tested, particularly the lung cancer cell line, with an IC50 of 1 g/L.


2021 ◽  

This study investigated the effects of lyophilized mare milk, human milk, and cow colostrum on both human lung cancer cell lines, called A549, and healthy lung cell lines, called MRC5. Mare milk, human milk, and cow colostrum varieties were applied to 6 replicates in both cell lines with lyophilized milk concentrations ranging from 50-3,200 ppm. The cell viability was monitored by optic microscopy and determined by the MTT test. ANOVA and Duncan's multiple range tests were used to analyze data. The results of this study indicated that the most effective milk type on reducing the A549 lung cancer cell line was human milk, followed by mare milk; however, cow colostrum showed little effect. It was observed that human milk and mare milk had anti-proliferative effects on lung cancer cell line at concentrations which were non-toxic to healthy lung cell line.


2017 ◽  
Vol 35 (15_suppl) ◽  
pp. e14095-e14095 ◽  
Author(s):  
Xi Liu ◽  
Jason Roszik ◽  
Masanori Karakami ◽  
Martin Sanders ◽  
Rosh Chandraratna ◽  
...  

e14095 Background: IRX4204 is a Retinoid X Receptor (RXR) specific agonist (rexinoid). IRX4204 has high potency as a RXR agonist with low binding affinity to Retinoic Acid Receptors (RARs), PPAR, FXR or LXR. Our prior work with the less specific rexinoid bexarotene and erlotinib showed clinical activity in patients with lung cancer cases that harbored KRAS mutations. IRX4204 inhibits lung cancer cell proliferation and can chemoprevent carcinogen-induced lung cancers in mice. We sought to explore the underlying mechanisms engaged by the combination of IRX4204 and erlotinib. Materials and Methods: Human (H1703 and HOP62) and murine (ED1 and LKR13) lung cancer cell lines were treated with IRX4204, erlotinib, IRX4204 plus erlotinib, or vehicle. Reverse phase protein array (RPPA) and mRNA microarray analyses were performed to analyze comprehensively for differentially expressed growth regulatory proteins. Results: Combination of IRX4204 and erlotinib suppressed proliferation of both KRAS mutant (HOP62 and LKR13) and wild-type (H1703 and ED1) lung cancer cell lines. Additive effect was observed as compared to IRX4204 or erlotinib treatment alone. Combining IRX4204 with erlotinib markedly increased inhibition of specific therapeutic targets including Src, phosphorylated Akt and ribosomal S6 proteins. At the mRNA level, Ingenuity Pathway Analysis of species significantly increased or decreased by the combination treatment revealed multiple pathways related to oncogenic signaling. Specifically, we found in H1703 cell line regulation of Granzyme A and AMPK signaling and in HOP62 cell line inhibition of angiogenesis was implicated by altering TSP1 expression. Notably, in ED1 cell line PPARα/RXRα activation, PTEN signaling, PI3K/AKT signaling, TGF-β signaling, and AMPK signaling were each associated with effects of IRX4204 combined with erlotinib. Conclusions: Taken together, these data highlight specific mechanisms and candidate pharmacodynamic biomarkers of response to the combination of this rexinoid and EGFR-TKI in lung cancer. Based on these findings, a clinical trial (NCT02991651) with IRX4204 in combination with erlotinib is underway to treat patients with chemotherapy-refractory non-small cell lung cancer.


Sign in / Sign up

Export Citation Format

Share Document