| At line 1 changed one line |
| __MILP_k__: Mixed Integer Linear Programming for multiple-biomarker panel identification |
| __MIMIC__: Mixed Integer programming Model to Identify Cell type specific marker panel |
| At line 7 changed one line |
| Multi-biomarker panels can capture the nonlinear synergy among biomarkers and they are important to aid in the early diagnosis and ultimately battle complex diseases. However, the multi-biomarker panel identification is challenging from case and control data. For example, the exhaustive search method is computationally infeasible when the data dimension is high. Here, we aim to propose a novel method to identify multi-biomarker panel and apply it to distinguish colorectal cancers (CRC) from benign colorectal tumors based on serum measurement. |
| Cell sorting aims to separate a heterogeneous mixture of cells and further research into the hierarchical topology of these cells according to the intracellular process (DNA, RNA, and protein interaction) or extracellular properties (morphology and surface marker expression). The ENCODE produces large amounts of such data and provides the opportunity and challenge in cell sorting. However, the challenge always goes with the high dimension. Here we aim to propose a novel model to identify the cell type specific marker panel and finally assist in cell sorting. |
| At line 11 changed one line |
| We developed a novel mixed integer programming model for multi-biomarker panel detection. This model directly minimizes the classification error (maximizes the classification accuracy) given the number of biomarkers in the optimal multi-biomarker panel. This mixed integer programming model allows us to go through all the optimal combinations by varying parameter from 1 to n. Moreover, we can check their accuracy and compare the selected combinations. In particular, an optimal multi-biomarker panel can be selected by balancing the parameter k and the classification accuracy. |
| We developed a novel mixed integer programming model for identify the cell type specific marker panel. This model directly selected the cell type specific markers with simultaneously maintaining the hierarchical topology among different cell types given the number of markers. This mixed integer programming model allows us to go through all the optimal combinations by varying parameter from 1 to n (the number of markers). Moreover, we can check their accuracy and compare the selected combinations. In particular, an optimal cell type specific marker panel can be selected by balancing the number of selected markers and the classification accuracy. |
| At line 13 changed one line |
| !!!Software |
| !!!Software and dataset |
| At line 19 added one line |
| The dataset used in our paper serves as an example to demonstrate the implementation for MIMIC. The raw data(.xlsx) and processed data(.mat) are available as follows. |
| At line 20 changed one line |
| * [source.rar|source.rar] |
| * [MIMIC.rar|MIMIC.rar] |
| At line 22 removed one line |
| !!!Dataset |
| At line 24 removed one line |
| The dataset used in our paper serves as an example to demonstrate the implementation for MILP_k. The raw data(.xlsx) and processed data(.mat) are available as follows. |
| At line 26 removed 3 lines |
| * [data.rar|data.rar] |
|
|
| At line 31 changed one line |
| * Meng Zou, Peng-Jun Zhang, Xin-Yu Wen, Luonan Chen, Ya-Ping Tian, and Yong Wang, A novel mixed integer programming for multi-biomarker panel identification by distinguishing malignant from benign colorectal tumors. Methods, In submission. |
| * Meng Zou, Zhana Duren, Qiuyue Yuan, Henry Li, Henry Li, Andrew Hutchins, Wing Hung Wong, Yong Wang, An optimization method to identify cell type specific marker panel for cell sorting. NAR, In submission. |
