Dataset Information

Precision Oncology beyond Targeted Therapy: Combining Omics Data with Machine Learning Matches the Majority of Cancer Cells to Effective Therapeutics.

ABSTRACT: Precision oncology involves identifying drugs that will effectively treat a tumor and then prescribing an optimal clinical treatment regimen. However, most first-line chemotherapy drugs do not have biomarkers to guide their application. For molecularly targeted drugs, using the genomic status of a drug target as a therapeutic indicator has limitations. In this study, machine learning methods (e.g., deep learning) were used to identify informative features from genome-scale omics data and to train classifiers for predicting the effectiveness of drugs in cancer cell lines. The methodology introduced here can accurately predict the efficacy of drugs, regardless of whether they are molecularly targeted or nonspecific chemotherapy drugs. This approach, on a per-drug basis, can identify sensitive cancer cells with an average sensitivity of 0.82 and specificity of 0.82; on a per-cell line basis, it can identify effective drugs with an average sensitivity of 0.80 and specificity of 0.82. This report describes a data-driven precision medicine approach that is not only generalizable but also optimizes therapeutic efficacy. The framework detailed herein, when successfully translated to clinical environments, could significantly broaden the scope of precision oncology beyond targeted therapies, benefiting an expanded proportion of cancer patients. Mol Cancer Res; 16(2); 269-78. ©2017 AACR.

SUBMITTER: Ding MQ

PROVIDER: S-EPMC5821274 | biostudies-literature | 2018 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Precision Oncology beyond Targeted Therapy: Combining Omics Data with Machine Learning Matches the Majority of Cancer Cells to Effective Therapeutics.

Ding Michael Q MQ Chen Lujia L Cooper Gregory F GF Young Jonathan D JD Lu Xinghua X

Molecular cancer research : MCR 20171113 2

Precision oncology involves identifying drugs that will effectively treat a tumor and then prescribing an optimal clinical treatment regimen. However, most first-line chemotherapy drugs do not have biomarkers to guide their application. For molecularly targeted drugs, using the genomic status of a drug target as a therapeutic indicator has limitations. In this study, machine learning methods (e.g., deep learning) were used to identify informative features from genome-scale omics data and to trai ...[more]

PMID: 29133589

Similar Datasets

Project description:An innovative strategy for cancer therapy is to combine the inhibition of cancer cell-intrinsic oncogenic signaling with cancer cell-extrinsic immunological activation of the tumor microenvironment (TME). In general, such approaches will focus on two or more distinct molecular targets in the malignant cells and in cells of the surrounding TME. In contrast, the protease Mucosa-associated lymphoid tissue protein 1 (MALT1) represents a candidate to enable such a dual approach by engaging only a single target. Originally identified and now in clinical trials as a lymphoma drug target based on its role in the survival and proliferation of malignant lymphomas addicted to chronic B cell receptor signaling, MALT1 proteolytic activity has recently gained additional attention through reports describing its tumor-promoting roles in several types of non-hematological solid cancer, such as breast cancer and glioblastoma. Besides cancer cells, regulatory T (Treg) cells in the TME are particularly dependent on MALT1 to sustain their immune-suppressive functions, and MALT1 inhibition can selectively reprogram tumor-infiltrating Treg cells into Foxp3-expressing proinflammatory antitumor effector cells. Thereby, MALT1 inhibition induces local inflammation in the TME and synergizes with anti-PD-1 checkpoint blockade to induce antitumor immunity and facilitate tumor control or rejection. This new concept of boosting tumor immunotherapy in solid cancer by MALT1 precision targeting in the TME has now entered clinical evaluation. The dual effects of MALT1 inhibitors on cancer cells and immune cells therefore offer a unique opportunity for combining precision oncology and immunotherapy to simultaneously impair cancer cell growth and neutralize immunosuppression in the TME. Further, MALT1 targeting may provide a proof of concept that modulation of Treg cell function in the TME represents a feasible strategy to augment the efficacy of cancer immunotherapy. Here, we review the role of MALT1 protease in physiological and oncogenic signaling, summarize the landscape of tumor indications for which MALT1 is emerging as a therapeutic target, and consider strategies to increase the chances for safe and successful use of MALT1 inhibitors in cancer therapy.

Dataset Information

Precision Oncology beyond Targeted Therapy: Combining Omics Data with Machine Learning Matches the Majority of Cancer Cells to Effective Therapeutics.

Publications

Precision Oncology beyond Targeted Therapy: Combining Omics Data with Machine Learning Matches the Majority of Cancer Cells to Effective Therapeutics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets