Integrative analysis of chemo-transcriptomic profiles for drug-feature specific gene expression signatures

Chang Sik Kim, Qing Wen, Shu-Dong Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

One of the major challenges in systems biology is to understand the complex responses of a biological system to external perturbations or internal signalling depending on its biological conditions. Genome-wide transcriptomic profiling of cellular systems under various chemical perturbations allows the manifestation of certain features of the chemicals through their transcriptomic expression profiles. The insights obtained may help to establish the connections between human diseases, associated genes and therapeutic drugs. The main objective of this study was to systematically analyse cellular gene expression data under various drug treatments to elucidate drug-feature specific transcriptomic signatures. We first extracted drug-related information (drug features) from the collected textual description of DrugBank entries using text-mining techniques. A novel statistical method employing orthogonal least square learning was proposed to obtain drug-feature-specific signatures by integrating gene expression with DrugBank data. To obtain robust signatures from noisy input datasets, a stringent ensemble approach was applied with the combination of three techniques: resampling, leave-one-out cross validation, and aggregation. The validation experiments showed that the proposed method has the capacity of extracting biologically meaningful drug-feature-specific gene expression signatures. It was also shown that most of signature genes are connected with common hub genes by regulatory network analysis. The common hub genes were further shown to be related to general drug metabolism by Gene Ontology analysis. Each set of genes has relatively few interactions with other sets, indicating the modular nature of each signature and its drug-feature-specificity. Based on Gene Ontology analysis, we also found that each set of drug feature (DF)-specific genes were indeed enriched in biological processes related to the drug feature. The results of these experiments demonstrated the pot- ntial of the method for predicting certain features of new drugs using their transcriptomic profiles, providing a useful methodological framework and a valuable resource for drug development and characterization.
Original languageEnglish
Title of host publicationProceedings for 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages113-118
Number of pages6
DOIs
Publication statusPublished - Nov 2014
EventThe IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2014 - Belfast, United Kingdom
Duration: 02 Nov 201405 Nov 2014

Conference

ConferenceThe IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2014
CountryUnited Kingdom
CityBelfast
Period02/11/201405/11/2014

Fingerprint

Transcriptome
Pharmaceutical Preparations
Gene Ontology
Genes
Biological Phenomena
Systems Biology
Data Mining
Gene Regulatory Networks
Least-Squares Analysis
Learning
Genome
Gene Expression

Cite this

Kim, C. S., Wen, Q., & Zhang, S-D. (2014). Integrative analysis of chemo-transcriptomic profiles for drug-feature specific gene expression signatures. In Proceedings for 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 113-118). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/BIBM.2014.6999138
Kim, Chang Sik ; Wen, Qing ; Zhang, Shu-Dong. / Integrative analysis of chemo-transcriptomic profiles for drug-feature specific gene expression signatures. Proceedings for 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Institute of Electrical and Electronics Engineers (IEEE), 2014. pp. 113-118
@inproceedings{0cb9ded0762748048932527aef2e764d,
title = "Integrative analysis of chemo-transcriptomic profiles for drug-feature specific gene expression signatures",
abstract = "One of the major challenges in systems biology is to understand the complex responses of a biological system to external perturbations or internal signalling depending on its biological conditions. Genome-wide transcriptomic profiling of cellular systems under various chemical perturbations allows the manifestation of certain features of the chemicals through their transcriptomic expression profiles. The insights obtained may help to establish the connections between human diseases, associated genes and therapeutic drugs. The main objective of this study was to systematically analyse cellular gene expression data under various drug treatments to elucidate drug-feature specific transcriptomic signatures. We first extracted drug-related information (drug features) from the collected textual description of DrugBank entries using text-mining techniques. A novel statistical method employing orthogonal least square learning was proposed to obtain drug-feature-specific signatures by integrating gene expression with DrugBank data. To obtain robust signatures from noisy input datasets, a stringent ensemble approach was applied with the combination of three techniques: resampling, leave-one-out cross validation, and aggregation. The validation experiments showed that the proposed method has the capacity of extracting biologically meaningful drug-feature-specific gene expression signatures. It was also shown that most of signature genes are connected with common hub genes by regulatory network analysis. The common hub genes were further shown to be related to general drug metabolism by Gene Ontology analysis. Each set of genes has relatively few interactions with other sets, indicating the modular nature of each signature and its drug-feature-specificity. Based on Gene Ontology analysis, we also found that each set of drug feature (DF)-specific genes were indeed enriched in biological processes related to the drug feature. The results of these experiments demonstrated the pot- ntial of the method for predicting certain features of new drugs using their transcriptomic profiles, providing a useful methodological framework and a valuable resource for drug development and characterization.",
author = "Kim, {Chang Sik} and Qing Wen and Shu-Dong Zhang",
year = "2014",
month = "11",
doi = "10.1109/BIBM.2014.6999138",
language = "English",
pages = "113--118",
booktitle = "Proceedings for 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

Kim, CS, Wen, Q & Zhang, S-D 2014, Integrative analysis of chemo-transcriptomic profiles for drug-feature specific gene expression signatures. in Proceedings for 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Institute of Electrical and Electronics Engineers (IEEE), pp. 113-118, The IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2014, Belfast, United Kingdom, 02/11/2014. https://doi.org/10.1109/BIBM.2014.6999138

Integrative analysis of chemo-transcriptomic profiles for drug-feature specific gene expression signatures. / Kim, Chang Sik; Wen, Qing; Zhang, Shu-Dong.

Proceedings for 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Institute of Electrical and Electronics Engineers (IEEE), 2014. p. 113-118.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Integrative analysis of chemo-transcriptomic profiles for drug-feature specific gene expression signatures

AU - Kim, Chang Sik

AU - Wen, Qing

AU - Zhang, Shu-Dong

PY - 2014/11

Y1 - 2014/11

N2 - One of the major challenges in systems biology is to understand the complex responses of a biological system to external perturbations or internal signalling depending on its biological conditions. Genome-wide transcriptomic profiling of cellular systems under various chemical perturbations allows the manifestation of certain features of the chemicals through their transcriptomic expression profiles. The insights obtained may help to establish the connections between human diseases, associated genes and therapeutic drugs. The main objective of this study was to systematically analyse cellular gene expression data under various drug treatments to elucidate drug-feature specific transcriptomic signatures. We first extracted drug-related information (drug features) from the collected textual description of DrugBank entries using text-mining techniques. A novel statistical method employing orthogonal least square learning was proposed to obtain drug-feature-specific signatures by integrating gene expression with DrugBank data. To obtain robust signatures from noisy input datasets, a stringent ensemble approach was applied with the combination of three techniques: resampling, leave-one-out cross validation, and aggregation. The validation experiments showed that the proposed method has the capacity of extracting biologically meaningful drug-feature-specific gene expression signatures. It was also shown that most of signature genes are connected with common hub genes by regulatory network analysis. The common hub genes were further shown to be related to general drug metabolism by Gene Ontology analysis. Each set of genes has relatively few interactions with other sets, indicating the modular nature of each signature and its drug-feature-specificity. Based on Gene Ontology analysis, we also found that each set of drug feature (DF)-specific genes were indeed enriched in biological processes related to the drug feature. The results of these experiments demonstrated the pot- ntial of the method for predicting certain features of new drugs using their transcriptomic profiles, providing a useful methodological framework and a valuable resource for drug development and characterization.

AB - One of the major challenges in systems biology is to understand the complex responses of a biological system to external perturbations or internal signalling depending on its biological conditions. Genome-wide transcriptomic profiling of cellular systems under various chemical perturbations allows the manifestation of certain features of the chemicals through their transcriptomic expression profiles. The insights obtained may help to establish the connections between human diseases, associated genes and therapeutic drugs. The main objective of this study was to systematically analyse cellular gene expression data under various drug treatments to elucidate drug-feature specific transcriptomic signatures. We first extracted drug-related information (drug features) from the collected textual description of DrugBank entries using text-mining techniques. A novel statistical method employing orthogonal least square learning was proposed to obtain drug-feature-specific signatures by integrating gene expression with DrugBank data. To obtain robust signatures from noisy input datasets, a stringent ensemble approach was applied with the combination of three techniques: resampling, leave-one-out cross validation, and aggregation. The validation experiments showed that the proposed method has the capacity of extracting biologically meaningful drug-feature-specific gene expression signatures. It was also shown that most of signature genes are connected with common hub genes by regulatory network analysis. The common hub genes were further shown to be related to general drug metabolism by Gene Ontology analysis. Each set of genes has relatively few interactions with other sets, indicating the modular nature of each signature and its drug-feature-specificity. Based on Gene Ontology analysis, we also found that each set of drug feature (DF)-specific genes were indeed enriched in biological processes related to the drug feature. The results of these experiments demonstrated the pot- ntial of the method for predicting certain features of new drugs using their transcriptomic profiles, providing a useful methodological framework and a valuable resource for drug development and characterization.

U2 - 10.1109/BIBM.2014.6999138

DO - 10.1109/BIBM.2014.6999138

M3 - Conference contribution

SP - 113

EP - 118

BT - Proceedings for 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Kim CS, Wen Q, Zhang S-D. Integrative analysis of chemo-transcriptomic profiles for drug-feature specific gene expression signatures. In Proceedings for 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Institute of Electrical and Electronics Engineers (IEEE). 2014. p. 113-118 https://doi.org/10.1109/BIBM.2014.6999138