Machine learning methods in the computational biology of cancer

@article{Vidyasagar2014MachineLM,
  title={Machine learning methods in the computational biology of cancer},
  author={Mathukumalli Vidyasagar},
  journal={Proceedings. Mathematical, Physical, and Engineering Sciences / The Royal Society},
  year={2014},
  volume={470}
}
  • M. Vidyasagar
  • Published 23 February 2014
  • Computer Science
  • Proceedings. Mathematical, Physical, and Engineering Sciences / The Royal Society
The objectives of this Perspective paper are to review some recent advances in sparse feature selection for regression and classification, as well as compressed sensing, and to discuss how these might be used to develop tools to advance personalized cancer therapy. As an illustration of the possibilities, a new algorithm for sparse regression is presented and is applied to predict the time to tumour recurrence in ovarian cancer. A new algorithm for sparse feature selection in classification… 

Figures and Tables from this paper

Machine Learning for In Silico Modeling of Tumor Growth
TLDR
Machine learning methods for tumor growth profiles and model validation can be of great help here, particularly, discrete multi-agent approaches that make sense out of publicly available big data sets.
Identifying predictive features in drug response using machine learning: opportunities and challenges.
  • M. Vidyasagar
  • Computer Science
    Annual review of pharmacology and toxicology
  • 2015
This article reviews several techniques from machine learning that can be used to study the problem of identifying a small number of features, from among tens of thousands of measured features, that
USING MACHINE LEARNING TECHNIQUES FOR FINDING MEANINGFUL TRANSCRIPTS IN PROSTATE CANCER PROGRESSION
TLDR
This research proposes a new method for finding transcripts that can be used as genomic features in prostate cancer progression and identifies potential transcripts associated with prostate cancer progress.
10-19-2015 USING MACHINE LEARNING TECHNIQUES FOR FINDING MEANINGFUL TRANSCRIPTS IN PROSTATE CANCER PROGRESSION
TLDR
This research proposes a new method for finding transcripts that can be used as genomic features in prostate cancer progression and identifies potential transcripts associated with prostate cancer progress.
Optimized Prediction of Extreme Treatment Outcomes in Ovarian Cancer
TLDR
A small number of highly predictive biomarkers are identified that can distinguish between the two extreme responders and then extrapolate to all patients, achieved using the lone star algorithm that is specifically developed for biological applications.
FOR FINDING MEANINGFUL TRANSCRIPTS IN PROSTATE CANCER PROGRESSION
TLDR
This research proposes a new method for finding transcripts that can be used as genomic features in prostate cancer progression and identifies potential transcripts associated with prostate cancer progress.
Single-sample classification of breast cancer tumors using data-driven reference genes
TLDR
This paper is the first to present a method for classifying breast cancer tumors into ER+ and ER-, one tumor at a time, in the presence of the batch effect and platform variation.
Radiomics as Applied in Precision Medicine
TLDR
Radiomics is the process of transferring the medical imaging interpretation knowledge and skill set from humans to machines in a way that they can see more, process more information, and have deeper insights into what the disease is and how it behaves and might respond to therapeutic intervention.
Development of artificial intelligence technology in diagnosis, treatment, and prognosis of colorectal cancer
TLDR
The application ofAI in the diagnosis, treatment, and prognosis of CRC is reviewed and the prospects for the broader application of AI in CRC are provided.
...
...

References

SHOWING 1-10 OF 90 REFERENCES
A new feature selection algorithm for two-class classification problems and application to endometrial cancer
TLDR
The ℓ1-StaR algorithm is illustrated by applying it to the problem of determining which endometrial cancer patients are at risk of having the cancer spreading to their lymph nodes, and achieving two-fold cross validation accuracies and combined accuracy, sensitivity and specificity in excess of 93%.
Improved Sparse Multi-Class SVM and Its Application for Gene Selection in Cancer Classification
TLDR
The method is improved by introducing soft-thresholding type penalties to incorporate variable selection into multi-class classification for high dimensional data and demonstrates that the new methods can select a small number of genes for building accurate multi- class classification rules.
Optimized application of penalized regression methods to diverse genomic data
TLDR
This work provides an optimized set of guidelines for the application of penalized regression for reproducible class comparison and prediction with genomic data and demonstrates the real-life application to predicting the survival of cancer patients from microarray data, and to classification of obese and lean individuals from metagenomic data.
Systematic genomic identification of colorectal cancer genes delineating advanced from early clinical stage and metastasis
TLDR
An analysis integrating multiple genomic features including mutations, copy number alterations, gene expression and methylation performs better than any individual genomic assay in suggesting their possible role in colorectal cancer metastatic progression.
A prognostic gene expression index in ovarian cancer—validation across different independent data sets
TLDR
A combined score of molecular data (OPI) and clinical parameters (residual tumour), which was able to define patient groups with highly significant differences in survival, can be used for optimized assessment of the prognosis of platinum‐taxol‐treated ovarian cancer.
Gene Expression Profiles Predict Early Relapse in Ovarian Cancer after Platinum-Paclitaxel Chemotherapy
TLDR
Predictive markers for early recurrence can be identified for platinum-paclitaxel combination chemotherapy in primary ovarian carcinoma using a 14-gene predictive model.
...
...