A systematic analysis of genomics-based modeling approaches for prediction of drug response to cytotoxic chemotherapies.

A systematic analysis of genomics-based modeling approaches for prediction of drug response to cytotoxic chemotherapies.

Publication date: Jun 17, 2019

The availability and generation of large amounts of genomic data has led to the development of a new paradigm in cancer treatment emphasizing a precision approach at the molecular and genomic level. Statistical modeling techniques aimed at leveraging broad scale in vitro, in vivo, and clinical data for precision drug treatment has become an active area of research. As a rapidly developing discipline at the crossroads of medicine, computer science, and mathematics, techniques ranging from accepted to those on the cutting edge of artificial intelligence have been utilized. Given the diversity and complexity of these techniques a systematic understanding of fundamental modeling principles is essential to contextualize influential factors to better understand results and develop new approaches.

Using data available from the Genomics of Drug Sensitivity in Cancer (GDSC) and the NCI60 we explore principle components regression, linear and non-linear support vector regression, and artificial neural networks in combination with different implementations of correlation based feature selection (CBF) on the prediction of drug response for several cytotoxic chemotherapeutic agents.

Our results indicate that the regression method and features used have marginal effects on Spearman correlation between the predicted and measured values as well as prediction error. Detailed analysis of these results reveal that the bulk relationship between tissue of origin and drug response is a major driving factor in model performance.

These results display one of the challenges in building predictive models for drug response in pan-cancer models. Mainly, that bulk genotypic traits where the signal to noise ratio is high is the dominant behavior captured in these models. This suggests that improved techniques of feature selection that can discriminate individual cell response from histotype response will yield more successful pan-cancer models.

Open Access PDF

Mannheimer, J.D., Duval, D.L., Prasad, A., and Gustafson, D.L. A systematic analysis of genomics-based modeling approaches for prediction of drug response to cytotoxic chemotherapies. 04821. 2019 BMC Med Genomics (12):1.

Concepts Keywords
Artificial Intelligence Chemotherapies
Artificial Neural Networks Medicine
BMC Clinical medicine
Cancer Cancer
CBF Antineoplastic drugs
Chemotherapeutic Agents Oncology
Chemotherapies Estimation theory
Computer Science Linear regression
Correlation Conceptual model
Cytotoxic Chemotherapy
Genomics Genomics
Genotypic Artificial intelligence
Mathematics
Medicine
Paradigm
Regression
Signal Noise
Vector
Vivo

Semantics

Type Source Name
gene UNIPROT GTF2IRD1
drug DRUGBANK Carboxyamidotriazole
gene UNIPROT POC1A
gene UNIPROT APPL1
gene UNIPROT RNF2
drug DRUGBANK (S)-Des-Me-Ampa
gene UNIPROT CASP8
gene UNIPROT COPE
gene UNIPROT LRP1
gene UNIPROT PMAIP1
gene UNIPROT ZBP1
pathway BSID Colorectal cancer
disease DOID Colorectal Cancer
disease MESH Colorectal Cancer
pathway BSID Breast cancer
disease DOID breast cancer
disease MESH breast cancer
disease MESH glioblastoma
disease MESH lung cancers
gene UNIPROT ERAL1
gene UNIPROT ESR1
pathway BSID Melanoma
disease DOID melanoma
disease MESH melanoma
drug DRUGBANK Vemurafenib
gene UNIPROT FBXL15
disease MESH Oncogene addiction
gene UNIPROT INTU
disease DOID pancreatic carcinoma
disease MESH pancreatic carcinoma
gene UNIPROT SLC7A5
disease DOID primary ovarian cancer
gene UNIPROT PROC
gene UNIPROT NOD2
gene UNIPROT CBLIF
gene UNIPROT STC1
gene UNIPROT COL9A3
gene UNIPROT COMP
gene UNIPROT COL9A1
gene UNIPROT COL9A2
gene UNIPROT SCN8A
gene UNIPROT EXOG
gene UNIPROT BRD2
gene UNIPROT TNIP1
disease MESH B cell lymphoma
drug DRUGBANK Iron
gene UNIPROT TNFSF13
gene UNIPROT ANP32B
gene UNIPROT DLD
gene UNIPROT FAM3A
gene UNIPROT LDHD
disease MESH diagnosis
gene UNIPROT TOX
gene UNIPROT MRTFA
gene UNIPROT PHB2
disease DOID NSCLC
gene UNIPROT GEN1
gene UNIPROT IMPACT
gene UNIPROT ELK3
gene UNIPROT EPHB1
gene UNIPROT SLC6A2
gene UNIPROT SAR1B
gene UNIPROT INPP5D
gene UNIPROT PICK1
disease DOID adenocarcinoma
disease MESH adenocarcinoma
disease DOID lung carcinoma
drug DRUGBANK L-Phenylalanine
gene UNIPROT FBLIM1
gene UNIPROT AMIGO2
gene UNIPROT RXFP2
gene UNIPROT PDXP
gene UNIPROT TNFRSF11A
drug DRUGBANK Docetaxel
drug DRUGBANK Bortezomib
drug DRUGBANK Vinblastine
gene UNIPROT RELA
gene UNIPROT PDLIM5
gene UNIPROT PTPRF
drug DRUGBANK Coenzyme M
drug DRUGBANK Paclitaxel
drug DRUGBANK Gemcitabine
drug DRUGBANK Etoposide
drug DRUGBANK Cisplatin
drug DRUGBANK Cytarabine
drug DRUGBANK Doxorubicin
gene UNIPROT NR4A3
drug DRUGBANK Vorinostat
gene UNIPROT RASA1
gene UNIPROT RGS6
gene UNIPROT MAX
gene UNIPROT DEPP1
gene UNIPROT GOPC
gene UNIPROT MXD1
gene UNIPROT AMPD1
gene UNIPROT TNF
disease MESH dif
pathway BSID Gene Expression
gene UNIPROT CTSC
gene UNIPROT ADHFE1
gene UNIPROT SLC31A2
drug DRUGBANK Aspartame
gene UNIPROT CALCR
gene UNIPROT SLC31A1
gene UNIPROT THOP1
gene UNIPROT DEGS1
drug DRUGBANK Fluorouracil
drug DRUGBANK Mitomycin
gene UNIPROT MTX1
drug DRUGBANK Methotrexate
gene UNIPROT GMNN
gene UNIPROT GEM
drug DRUGBANK Ethionamide
gene UNIPROT CISH
gene UNIPROT CASC3
gene UNIPROT BLM
drug DRUGBANK Bleomycin
gene UNIPROT NT5E
disease MESH complications
gene UNIPROT SET
drug DRUGBANK L-Valine
drug DRUGBANK Serine Vanadate
gene UNIPROT CEL
gene UNIPROT MENT
drug DRUGBANK Trestolone
gene UNIPROT LITAF
gene UNIPROT TECR
gene UNIPROT TNFRSF19
gene UNIPROT ARSA
drug DRUGBANK Acetylsalicylic acid
drug DRUGBANK Spinosad
gene UNIPROT SLC25A4
gene UNIPROT SLC25A6
gene UNIPROT PLEKHG5
drug DRUGBANK Esomeprazole
gene UNIPROT KCNK3
disease MESH multi
pathway BSID Methylation
gene UNIPROT KCNIP3
disease MESH multiple
disease MESH community
gene UNIPROT EHD1
gene UNIPROT EAF2
gene UNIPROT ADA2
gene UNIPROT CEBPZ
drug DRUGBANK Tropicamide
disease DOID cancer
disease MESH cancer
disease MESH development
gene UNIPROT SMIM10L2A
gene UNIPROT SMIM10L2B
gene UNIPROT LARGE1

Similar

Original Article

Leave a Comment

Your email address will not be published. Required fields are marked *