scholarly journals Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines

2021 ◽  
Author(s):  
Krzysztof Koras ◽  
Ewa Kizling ◽  
Dilafruz Juraeva ◽  
Eike Staub ◽  
Ewa Szczurek
Keyword(s):  
Neural Network ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Drug Sensitivity ◽  
Kinase Inhibitor ◽  
Cancer Cell Line ◽  
Cancer Cell Lines ◽  
Biological Processes ◽  
Drug Sensitivity Prediction

Computational models for drug sensitivity prediction have the potential to revolutionise personalized cancer medicine. Drug sensitivity assays, as well as profiling of cancer cell lines and drugs becomes increasingly available for training such models. Machine learning methods for drug sensitivity prediction must be optimized for: (i) leveraging the wealth of information about both cancer cell lines and drugs, (ii) predictive performance and (iii) interpretability. Multiple methods were proposed for predicting drug sensitivity from cancer cell line features, some in a multi-task fashion. So far, no such model leveraged drug inhibition profiles. Recent neural network-based recommender systems arise as models capable of predicting cancer cell line response to drugs from their biological features with high prediction accuracy. These models, however, require a tailored approach to model interpretability. In this work, we develop a neural network recommender system for kinase inhibitor sensitivity prediction called DEERS. The model utilizes molecular features of the cancer cell lines and kinase inhibition profiles of the drugs. DEERS incorporates two autoencoders to project cell line and drug features into 10-dimensional hidden representations and a feed-forward neural network to combine them into response prediction. We propose a novel model interpretability approach offering the widest possible assessment of the specific genes and biological processes that underlie the action of the drugs on the cell lines. The approach considers also such genes and processes that were not included in the set of modeled features. Our approach outperforms simpler matrix factorization models, achieving R=0.82 correlation between true and predicted response for the unseen cell lines. Using the interpretability analysis, we evaluate correlation of all human genes with each of the hidden cell line dimensions. Subsequently, we identify 67 biological processes associated with these dimensions. Combined with drug response data, these associations point at the processes that drive the cell line sensitivity to particular compounds. Detailed case studies are shown for PHA-793887, XMD14-99 and Dabrafenib. Our framework provides an expressive, multitask neural network model with a custom interpretability approach for inferring underlying biological factors and explaining cancer cell response to drugs.

scholarly journals Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Krzysztof Koras ◽  
Ewa Kizling ◽  
Dilafruz Juraeva ◽  
Eike Staub ◽  
Ewa Szczurek
Keyword(s):  
Neural Network ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Recommender System ◽  
Computational Models ◽  
Drug Sensitivity ◽  
Kinase Inhibitor ◽  
Cancer Cell Lines ◽  
Molecular Features

AbstractComputational models for drug sensitivity prediction have the potential to significantly improve personalized cancer medicine. Drug sensitivity assays, combined with profiling of cancer cell lines and drugs become increasingly available for training such models. Multiple methods were proposed for predicting drug sensitivity from cancer cell line features, some in a multi-task fashion. So far, no such model leveraged drug inhibition profiles. Importantly, multi-task models require a tailored approach to model interpretability. In this work, we develop DEERS, a neural network recommender system for kinase inhibitor sensitivity prediction. The model utilizes molecular features of the cancer cell lines and kinase inhibition profiles of the drugs. DEERS incorporates two autoencoders to project cell line and drug features into 10-dimensional hidden representations and a feed-forward neural network to combine them into response prediction. We propose a novel interpretability approach, which in addition to the set of modeled features considers also the genes and processes outside of this set. Our approach outperforms simpler matrix factorization models, achieving R $$=$$ =  0.82 correlation between true and predicted response for the unseen cell lines. The interpretability analysis identifies 67 biological processes that drive the cell line sensitivity to particular compounds. Detailed case studies are shown for PHA-793887, XMD14-99 and Dabrafenib.

scholarly journals Drug Sensitivity Prediction From Cell Line-Based Pharmacogenomics Data: Guidelines for Developing Machine Learning Models

2021 ◽  
Author(s):  
Hossein Sharifi-Noghabi ◽  
Soheil Jahangiri-Tazehkand ◽  
Casey Hon ◽  
Petr Smirnov ◽  
Anthony Mammoliti ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Drug Sensitivity ◽  
Cancer Cell Lines ◽  
Precision Oncology ◽  
Learning Models ◽  
Drug Sensitivity Prediction ◽  
Machine Learning Models

ABSTRACTThe goal of precision oncology is to tailor treatment for patients individually using the genomic profile of their tumors. Pharmacogenomics datasets such as cancer cell lines are among the most valuable resources for drug sensitivity prediction, a crucial task of precision oncology. Machine learning methods have been employed to predict drug sensitivity based on the multiple omics data available for large panels of cancer cell lines. However, there are no comprehensive guidelines on how to properly train and validate such machine learning models for drug sensitivity prediction. In this paper, we introduce a set of guidelines for different aspects of training a predictor using cell line datasets. These guidelines provide extensive analysis of the generalization of drug sensitivity predictors, and challenge many current practices in the community including the choice of training dataset and measure of drug sensitivity. Application of these guidelines in future studies will enable the development of more robust preclinical biomarkers.

scholarly journals Network-based clustering for drug sensitivity prediction in cancer cell lines

2019 ◽  
Author(s):  
Maryam Pouryahya ◽  
Jung Hun Oh ◽  
James C. Mathews ◽  
Zehor Belkhatir ◽  
Caroline Moosmüller ◽  
...  
Keyword(s):  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Large Scale ◽  
Computational Models ◽  
Drug Sensitivity ◽  
Cancer Cell Lines ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Drug Sensitivity Prediction

AbstractThe study of large-scale pharmacogenomics provides an unprecedented opportunity to develop computational models that can accurately predict large cohorts of cell lines and drugs. In this work, we present a novel method for predicting drug sensitivity in cancer cell lines which considers both cell line genomic features and drug chemical features. Our network-based approach combines the theory of optimal mass transport (OMT) with machine learning techniques. It starts with unsupervised clustering of both cell line and drug data, followed by the prediction of drug sensitivity in the paired cluster of cell lines and drugs. We show that prior clustering of the heterogenous cell lines and structurally diverse drugs significantly improves the accuracy of the prediction. In addition, it facilities the interpretability of the results and identification of molecular biomarkers which are significant for both clustering of the cell lines and predicting the drug response.

Synthesis, Anticancer Activity on Prostate Cancer Cell Lines and Molecular Modeling Studies of Flurbiprofen-Thioether Derivatives as Potential Target of MetAP (Type II)

2020 ◽  
Vol 16 (6) ◽  
pp. 735-749 ◽  
Author(s):  
Özgür Yılmaz ◽  
Burak Bayer ◽  
Hatice Bekçi ◽  
Abdullahi I. Uba ◽  
Ahmet Cumaoğlu ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Molecular Modeling ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Prostate Cancer Cell ◽  
Cancer Cell Line ◽  
Cancer Cell Lines ◽  
Prostate Cancer Cell Lines ◽  
Molecular Modeling Studies

Background:: Prostate cancer is still one of the serious causes of mortality and morbidity in men. Despite recent advances in anticancer therapy, there is a still need of novel agents with more efficacy and specificity in the treatment of prostate cancer. Because of its function on angiogenesis and overexpression in the prostate cancer, methionine aminopeptidase-2 (MetAP-2) has been a potential target for novel drug design recently. Objective:: A novel series of Flurbiprofen derivatives N-(substituted)-2-(2-(2-fluoro-[1,1'- biphenyl]-4-il)propanoyl)hydrazinocarbothioamide (3a-c), 4-substituted-3-(1-(2-fluoro-[1,1'-biphenyl]- 4-yl)ethyl)-1H-1,2,4-triazole-5(4H)-thione (4a-d), 3-(substitutedthio)-4-(substituted-phenyl)- 5-(1-(2-fluoro-[1,1'-biphenyl]-4-yl)ethyl)-4H-1,2,4-triazole (5a-y) were synthesized. The purpose of the research was to evaluate these derivatives against MetAP-2 in vitro and in silico to obtain novel specific and effective anticancer agents against prostate cancer. Methods: The chemical structures and purities of the compounds were defined by spectral methods (1H-NMR, 13C-NMR, HR-MS and FT-IR) and elemental analysis. Anticancer activities of the compounds were evaluated in vitro by using MTS method against PC-3 and DU-143 (androgenindependent human prostate cancer cell lines) and LNCaP (androgen-sensitive human prostate adenocarcinoma) prostate cancer cell lines. Cisplatin was used as a positive sensitivity reference standard. Results:: Compounds 5b and 5u; 3c, 5b and 5y; 4d and 5o showed the most potent biological activity against PC3 cancer cell line (IC50= 27.1 μM, and 5.12 μM, respectively), DU-145 cancer cell line (IC50= 11.55 μM, 6.9 μM and 9.54 μM, respectively) and LNCaP cancer cell line (IC50= 11.45 μM and 26.91 μM, respectively). Some compounds were evaluated for their apoptotic caspases protein expression (EGFR/PI3K/AKT pathway) by Western blot analysis in androgen independent- PC3 cells. BAX, caspase 9, caspsase 3 and anti-apoptotic BcL-2 mRNA levels of some compounds were also investigated. In addition, molecular modeling studies of the compounds on MetAP-2 enzyme active site were evaluated in order to get insight into binding mode and energy. Conclusion:: A series of Flurbiprofen-thioether derivatives were synthesized. This study presented that some of the synthesized compounds have remarkable anticancer and apoptotic activities against prostate cancer cells. Also, molecular modeling studies exhibited that there is a correlation between molecular modeling and anticancer activity results.

Design, Synthesis, Molecular Docking, and Anticancer Evaluation of Pyrazole Linked Pyrazoline Derivatives with Carbothioamide Tail as EGFR Kinase Inhibitors

2020 ◽  
Vol 21 (1) ◽  
pp. 42-60
Author(s):  
Farah Nawaz ◽  
Ozair Alam ◽  
Ahmad Perwez ◽  
Moshahid A. Rizvi ◽  
Mohd. Javed Naim ◽  
...  
Keyword(s):  
Molecular Docking ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Cancer Cell Line ◽  
Cancer Cell Lines ◽  
Kinase Assay ◽  
Cervix Uteri ◽  
Egfr Kinase

Background: The Epidermal Growth Factor Receptor (known as EGFR) induces cell differentiation and proliferation upon activation through the binding of its ligands. Since EGFR is thought to be involved in the development of cancer, the identification of new target inhibitors is the most viable approach, which recently gained momentum as a potential anticancer therapy. Objective: To assess various pyrazole linked pyrazoline derivatives with carbothioamide for EGFR kinase inhibitory as well as anti-proliferative activity against human cancer cell lines viz. A549 (non-small cell lung tumor), MCF-7 (breast cancer cell line), SiHa (cancerous tissues of the cervix uteri), and HCT-116 (colon cancer cell line). Methods: In vitro EGFR kinase assay, in vitro MTT assay, Lactate dehydrogenase release, nuclear staining (DAPI), and flow cytometry cell analysis. Results: Compounds 6h and 6j inhibited EGFR kinase at concentrations of 1.66μM and 1.9μM, respectively. Furthermore, compounds 6h and 6j showed the most potent anti-proliferative results against the A549 KRAS mutation cell line (IC50 = 9.3 & 10.2μM). Through DAPI staining and phase contrast microscopy, it was established that compounds 6h and 6j also induced apoptotic activity in A549 cells. This activity was further confirmed by FACS using Annexin-V-FITC and Propidium Iodide (PI) labeling. Molecular docking studies performed on 6h and 6j suggested that the compounds can bind to the hinge region of ATP binding site of EGFR tyrosine kinase in a similar pose as that of the standard drug gefitinib. Conclusion: The potential anticancer activity of compounds 6h and 6j was confirmed and need further exploration in cancer cell lines of different tissue origin and signaling pathways, as well as in animal models of cancer development.

scholarly journals Drug Sensitivity Prediction by CpG Island Methylation Profile in the NCI-60 Cancer Cell Line Panel

2007 ◽  
Vol 67 (23) ◽  
pp. 11335-11343 ◽  
Author(s):  
Lanlan Shen ◽  
Yutaka Kondo ◽  
Saira Ahmed ◽  
Yanis Boumber ◽  
Kazuo Konishi ◽  
...  
Keyword(s):  
Cell Line ◽  
Cancer Cell ◽  
Drug Sensitivity ◽  
Cpg Island ◽  
Cancer Cell Line ◽  
Methylation Profile ◽  
Cell Line Panel ◽  
Drug Sensitivity Prediction ◽  
Cpg Island Methylation

Effect of the Method of Preparation on the Composition and Cytotoxic Activity of the Essential Oil of Pituranthos tortuosus

2011 ◽  
Vol 66 (3-4) ◽  
pp. 143-148 ◽  
Author(s):  
Hossam M. Abdallah ◽  
Shahira M. Ezzat
Keyword(s):  
Breast Cancer ◽  
Essential Oil ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Human Cancer ◽  
Cancer Cell Line ◽  
Cancer Cell Lines ◽  
Human Cancer Cell ◽  
Human Cancer Cell Lines

The aerial parts of Pituranthos tortuosus (Desf.) Benth and Hook (Apiaceae), growing wild in Egypt, yielded 0.8%, 0.6%, and 1.5% (v/w) of essential oil when prepared by hydrodistillation (HD), simultaneous hydrodistillation-solvent (n-pentane) extraction (Lickens- Nickerson, DE), and conventional volatile solvent extraction (preparation of the “absolute”, SE), respectively. GC-MS analysis showed that the major components in the HD sample were β-myrcene (18.81%), sabinene (18.49%), trans-iso-elemicin (12.90%), and terpinen- 4-ol (8.09%); those predominent in the DE sample were terpinen-4-ol (29.65%), sabinene (7.38%), γ-terpinene (7.27%), and β-myrcene (5.53%); while the prominent ones in the SE sample were terpinen-4-ol (15.40%), dill apiol (7.90%), and allo-ocimene (4E,6Z) (6.00%). The oil prepared in each case was tested for its cytotoxic activity on three human cancer cell lines, i.e. liver cancer cell line (HEPG2), colon cancer cell line (HCT116), and breast cancer cell line (MCF7). The DE sample showed the most potent activity against the three human cancer cell lines (with IC50 values of 1.67, 1.34, and 3.38 μg/ml against the liver, colon, and breast cancer cell lines, respectively). Terpinen-4-ol, sabinene, γ-terpinene, and β-myrcene were isolated from the DE sample and subjected to a similar evaluation of cytotoxic potency; signifi cant activity was observed

Evaluation of the performance of breast cancer cell line–derived multigene predictors of chemotherapy response in multiple clinical trials.

2011 ◽  
Vol 29 (27_suppl) ◽  
pp. 64-64
Author(s):  
N. Song ◽  
S. D. Rice ◽  
D. Gingrich ◽  
D. Wang ◽  
C. Tian ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Clinical Trials ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Breast Cancer Cell ◽  
Breast Cancer Cell Line ◽  
Cancer Cell Line ◽  
Cancer Cell Lines ◽  
Chemotherapy Response

64 Background: While various multi-gene predictors (MGPs) of chemotherapy response have been developed based on cancer patient primary tissues or cancer cell-lines, the accuracy and consistency of these predictors remain a concern in clinical validation studies. In this study we developed four unique MGPs for chemotherapy response from breast cancer cell lines and performed a systematic evaluation of the performance of these MGPs using data from five distinct clinical trials. Methods: Forty-six immortalized breast cancer cell-lines were exposed to various concentrations of drug combinations [paclitaxel, 5-fluorouracil, doxorubicin, cyclophosphamide (TFAC); 5-fluorouracil, doxorubicin, cyclophosphamide (FAC); 5-fluorouracil, epirubicin, cyclophosphamide (FEC) and epirubicin, cyclophosphamide (EC)] using an in vitro chemosensitivity assay. Utilizing publicly available breast cancer cell-line microarray data, genes highly associated with in vitro chemosensitivity were selected as candidate MGPs. Five independent and publicly available clinical trials were used for validation. In three of these clinical trials patients were treated by TFAC, while EC, FAC or FEC were used in the other two trials. All five studies involved neoadjuvant chemotherapy treatment, and pathologic complete response (pCR) was used as the endpoint. The association of MGPs with pCR was assessed using receiver-operator curve (ROC) analysis and area under the ROC (AUC) was used to evaluate the performance of prediction. Results: In five independent clinical trials, the MGPs predicted patient pCR to EC, FAC/FEC and three TFAC treatments with an AUC of, 0.671, 0.632, 0.735, 0.738 and 0.647 respectively. Conclusions: In the five independent clinical trials in which patients were treated by various chemotherapy agents, the performance of MGPs is promising. These results demonstrate the feasibility of using breast cancer cell-line derived MGPs to predict breast cancer patients’ chemotherapy responses.

The estrogenic hormone effect in gastric cancer.

2018 ◽  
Vol 36 (4_suppl) ◽  
pp. 85-85
Author(s):  
Youjin Jang ◽  
Youjae Mok
Keyword(s):  
Gastric Cancer ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Treatment Effect ◽  
Cancer Cell Line ◽  
Cancer Cell Lines ◽  
High Expression ◽  
Lauren Classification ◽  
Laurén Classification

85 Background: Estrogen receptors (ERs) are steroid hormone receptors that regulate cellular activities in many physiological and pathological processes in different tissues. A few of studies have examined the expression of ER in gastric cancer. However, considerable controversy is raised as to the expression level of ER and its prognostic value in gastric cancer. In the present study, the expression profile of ERα, ERβ was determined in gastric cancer cell lines according Lauren classification and evaluate that the treatment effect of selective estrogen receptor modulator. Methods: Using four cell lines established from human gastric carcinomas according Lauren classification, check endogenous ERα, ERβ expression levels with RT-PCR. The SERM treatment effect were detected MTT test. Using immunohistochemical detection, the present study analyzed the clinical relevance of ERα, ERβ expression in tumor cells in 197 patients who underwent curative radical surgery and who were observed on long-term follow-up. Results: Endogenous ERα was high expression not intestinal cancer cell lines but in diffuse cancer cell line. Endogenous ERβ was high expression both type cancer cell line than normal gastrointestinal cell lines. According MTT assay, only raloxifene among SERM was significant treatment effect. In immonohistochemial study of gastric tissue, ERα negative and ERβ positive was associated with good prognosis. Conclusions: ERβ may be partly involved in gastric carcinogenesis and ERβ antagonist might be new therapeutic drug for gastric cancer.

Sign in / Sign up

Export Citation Format

Share Document