Chifeng Ma

The University of Texas at San Antonio

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Yidong Chen

The University of Texas Health Science Center at San Antonio

Yufei Huang

UPMC Hillman Cancer Center

Hung-I Harry Chen

NGM Biopharmaceuticals (United States)

Tim Hui-Ming Huang

The University of Texas Health Science Center at San Antonio

Issam Al‐Bozom

Hamad Medical Corporation

Huang-I Harry

The University of Texas Health Science Center at San Antonio

Erchin Serpedin

Texas A&M University

Konduru S. Sastry

Anti-Doping Laboratory

Mario Flores

The University of Texas at San Antonio

Mario Flore

The University of Texas at San Antonio

Cooperative Institutions

The University of Texas Health Science Center at San Antonio

The University of Texas at San Antonio

Weill Cornell Medical College in Qatar

Brown University

Hamad Medical Corporation

Genomics (United Kingdom)

National Institutes of Health

The University of Texas Health Science Center at Houston

Sidra Medical and Research Center

Qatar Airways (Qatar)

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Constructing a compound mode-of-action network for personalized drug effectiveness prediction

Chifeng Ma Hung-I Chen Yufei Huang Yidong Chen

The problem of large scale computational drug screening is considered in this paper. A new concept of Mode-of-Action (MoA) network, or MoNet, is introduced to model the relationship of therapeutic effectiveness between different drugs. A new algorithm for constructing Mode-of-Action groups and subsequently MoNet based on gene expression profile of drug treatment is proposed. The algorithm has been applied to the data from the Connectivity Map (cMap) project and a cMap MoNet was obtained. A new drug effectiveness prediction algorithm based on MoNet is also developed and applied to an independent breast cancer data set. The prediction result shows improvement in precision over cMap.

Mode (computer interface)

10.1145/1854776.1854876

Cite

Citations (2)

BIMMER: a novel algorithm for detecting differential DNA methylation regions from MBDCap-seq data

BMC Bioinformatics (2014)

Zijing Mao Chifeng Ma Tim Hui-Ming Huang Yidong Chen Yufei Huang

DNA methylation is a common epigenetic marker that regulates gene expression. A robust and cost-effective way for measuring whole genome methylation is Methyl-CpG binding domain-based capture followed by sequencing (MBDCap-seq). In this study, we proposed BIMMER, a Hidden Markov Model (HMM) for differential Methylation Regions (DMRs) identification, where HMMs were proposed to model the methylation status in normal and cancer samples in the first layer and another HMM was introduced to model the relationship between differential methylation and methylation statuses in normal and cancer samples. To carry out the prediction for BIMMER, an Expectation-Maximization algorithm was derived. BIMMER was validated on the simulated data and applied to real MBDCap-seq data of normal and cancer samples. BIMMER revealed that 8.83% of the breast cancer genome are differentially methylated and the majority are hypo-methylated in breast cancer.

Differentially methylated regions

CpG site

10.1186/1471-2105-15-s12-s6

Cite

Citations (5)

A computational framework for predicting drug Mode-of-Action

Chifeng Ma Hung-I Harry Chen Yufei Huang Yidong Chen

The problem of large scale computational drug screening is considered in this paper. A computational framework is developed for microarray profile of drug treatment from the Connectivity Map (cMap) project. The framework is proposed to address the deficiency of cMap prediction. This scheme includes construction of drug Mode-of-Actions (MoA) and subsequently Mode-of-Action (MoA) network, or MoANet and a MoA prediction algorithm based on MoAs. The scheme is tested on the cMap data and an independent data set. The result shows significant improvement over cMap.

Mode (computer interface)

10.1109/bibmw.2010.5703831

Cite

Citations (0)

CrossLink: a novel method for cross-condition classification of cancer subtypes

BMC Genomics (2016)

Chifeng Ma Konduru S. Sastry Mario Flore Salah Gehani Issam Al‐Bozom

We considered the prediction of cancer classes (e.g. subtypes) using patient gene expression profiles that contain both systematic and condition-specific biases when compared with the training reference dataset. The conventional normalization-based approaches cannot guarantee that the gene signatures in the reference and prediction datasets always have the same distribution for all different conditions as the class-specific gene signatures change with the condition. Therefore, the trained classifier would work well under one condition but not under another. To address the problem of current normalization approaches, we propose a novel algorithm called CrossLink (CL). CL recognizes that there is no universal, condition-independent normalization mapping of signatures. In contrast, it exploits the fact that the signature is unique to its associated class under any condition and thus employs an unsupervised clustering algorithm to discover this unique signature. We assessed the performance of CL for cross-condition predictions of PAM50 subtypes of breast cancer by using a simulated dataset modeled after TCGA BRCA tumor samples with a cross-validation scheme, and datasets with known and unknown PAM50 classification. CL achieved prediction accuracy >73 %, highest among other methods we evaluated. We also applied the algorithm to a set of breast cancer tumors derived from Arabic population to assign a PAM50 classification to each tumor based on their gene expression profiles. A novel algorithm CrossLink for cross-condition prediction of cancer classes was proposed. In all test datasets, CL showed robust and consistent improvement in prediction performance over other state-of-the-art normalization and classification algorithms.

Normalization

Cross-validation

10.1186/s12864-016-2903-z

Cite

Citations (2)

Comprehensive investigation of connectivity map data-towards a drug mode of action network for personalized thnerapy

Chifeng Ma Huang-I Harry Yufei Huang Yidong Chen

This work aims at addressing the problems existed in the original cMap algorithm and proposed a new drug Mode-of Action Network construction scheme including data pre-processing, signature gene extraction, network construction and query prediction. Multiple analyses were conducted to investigate the structure of constructed drug mode-of-action network and the cMap based Mode-of-Action network is tested on the independent drug treatment datasets. All result shows our cMap based drug Mode-of-Action network is both statistically and biologically significant and out-perform the original cMap project.

Mode of Action

Mode (computer interface)

10.1109/bibmw.2011.6112555

Cite

Citations (0)

BRCA-Monet: a breast cancer specific drug treatment mode-of-action network for treatment effective prediction using large scale microarray database

BMC Systems Biology (2013)

Chifeng Ma Hung-I Harry Chen Mario Flores Yufei Huang Yidong Chen

Connectivity map (cMap) is a recent developed dataset and algorithm for uncovering and understanding the treatment effect of small molecules on different cancer cell lines. It is widely used but there are still remaining challenges for accurate predictions.Here, we propose BRCA-MoNet, a network of drug mode of action (MoA) specific to breast cancer, which is constructed based on the cMap dataset. A drug signature selection algorithm fitting the characteristic of cMap data, a quality control scheme as well as a novel query algorithm based on BRCA-MoNet are developed for more effective prediction of drug effects.BRCA-MoNet was applied to three independent data sets obtained from the GEO database: Estrodial treated MCF7 cell line, BMS-754807 treated MCF7 cell line, and a breast cancer patient microarray dataset. In the first case, BRCA-MoNet could identify drug MoAs likely to share same and reverse treatment effect. In the second case, the result demonstrated the potential of BRCA-MoNet to reposition drugs and predict treatment effects for drugs not in cMap data. In the third case, a possible procedure of personalized drug selection is showcased.The results clearly demonstrated that the proposed BRCA-MoNet approach can provide increased prediction power to cMap and thus will be useful for identification of new therapeutic candidates.

10.1186/1752-0509-7-s5-s5

Cite

Citations (7)