Visible Machine Learning for Biomedicine

Michael K Yu¹, Jianzhu Ma², Jasmin Fisher³, Jason F Kreisberg², Benjamin J Raphael⁴, Trey Ideker⁵

Affiliations

¹ Division of Genetics, Department of Medicine, University of California San Diego, La Jolla, CA, USA; Cancer Cell Map Initiative, University of California San Diego, La Jolla, CA, USA; UCSD Program in Bioinformatics and Systems Biology, University of California San Diego, La Jolla, CA, USA.
² Division of Genetics, Department of Medicine, University of California San Diego, La Jolla, CA, USA; Cancer Cell Map Initiative, University of California San Diego, La Jolla, CA, USA.
³ Department of Biochemistry, University of Cambridge, Cambridge, UK.
⁴ Department of Computer Science, Princeton University, Princeton, NJ, USA. Electronic address: braphael@princeton.edu.
⁵ Division of Genetics, Department of Medicine, University of California San Diego, La Jolla, CA, USA; Cancer Cell Map Initiative, University of California San Diego, La Jolla, CA, USA; UCSD Program in Bioinformatics and Systems Biology, University of California San Diego, La Jolla, CA, USA. Electronic address: tideker@ucsd.edu.

PMID: 29906441
PMCID: PMC6483071
DOI: 10.1016/j.cell.2018.05.056

Visible Machine Learning for Biomedicine

Michael K Yu et al. Cell. 2018.

. 2018 Jun 14;173(7):1562-1565.

doi: 10.1016/j.cell.2018.05.056.

Authors

Michael K Yu¹, Jianzhu Ma², Jasmin Fisher³, Jason F Kreisberg², Benjamin J Raphael⁴, Trey Ideker⁵

Affiliations

¹ Division of Genetics, Department of Medicine, University of California San Diego, La Jolla, CA, USA; Cancer Cell Map Initiative, University of California San Diego, La Jolla, CA, USA; UCSD Program in Bioinformatics and Systems Biology, University of California San Diego, La Jolla, CA, USA.
² Division of Genetics, Department of Medicine, University of California San Diego, La Jolla, CA, USA; Cancer Cell Map Initiative, University of California San Diego, La Jolla, CA, USA.
³ Department of Biochemistry, University of Cambridge, Cambridge, UK.
⁴ Department of Computer Science, Princeton University, Princeton, NJ, USA. Electronic address: braphael@princeton.edu.
⁵ Division of Genetics, Department of Medicine, University of California San Diego, La Jolla, CA, USA; Cancer Cell Map Initiative, University of California San Diego, La Jolla, CA, USA; UCSD Program in Bioinformatics and Systems Biology, University of California San Diego, La Jolla, CA, USA. Electronic address: tideker@ucsd.edu.

PMID: 29906441
PMCID: PMC6483071
DOI: 10.1016/j.cell.2018.05.056

Abstract

A major ambition of artificial intelligence lies in translating patient data to successful therapies. Machine learning models face particular challenges in biomedicine, however, including handling of extreme data heterogeneity and lack of mechanistic insight into predictions. Here, we argue for "visible" approaches that guide model structure with experimental biology.

PubMed Disclaimer

Conflict of interest statement

DECLARATION OF INTERESTS

T.I. is co-founder of Data4Cure and has an equity interest. T.I. has an equity interest in Ideaya BioSciences. The terms of this arrangement have been reviewed and approved by the University of California, San Diego in accordance with its conflict of interest policies. B.J.R. is a founder of Medley Genomics and a member of its board of directors.

Figures

**Figure 1.. Current Approaches Relevant to Analysis of Big Biomedical Data**
First subheading (blue): what each of four approaches (A)–(D) accomplish. Second subheading (orange): limitations and challenges for these approaches. Box: this commentary argues for the synthesis of two approaches in particular–machine learning (B) and experimental cell and tissue biology (C)–resulting in an infrastructure for visible intelligence.

**Figure 2.. Visible Models**
(A) The Visible V8 was a popular quarter-scale model of an internal combustion engine sold by Renwal Model Company starting in 1958. It conveys the concept and value of visible machine learning. Photo: Trey Ideker. (B) Guiding machine learning systems with visible multi-scale biological structure.

See this image and copyright information in PMC

References

1. Alvarez MJ, Shen Y, Giorgi FM, Lachmann A, Ding BB, Ye BH, and Califano A (2016). Functional characterization of somatic mutations in cancer using network-based inference of protein activity. Nat. Genet. 48, 838–847. - PMC - PubMed
1. Boyle EA, Li YI, and Pritchard JK (2017). An Expanded View of Complex Traits: From Polygenic to Omnigenic. Cell 169, 1177–1186. - PMC - PubMed
1. Chuang H-Y, Lee E, Liu Y-T, Lee D, and Ideker T (2007). Network-based classification of breast cancer metastasis. Mol. Syst. Biol. 3, 140. - PMC - PubMed
1. Fisher J, and Henzinger TA (2007). Executable cell biology. Nat. Biotechnol. 25, 1239–1249. - PubMed
1. Karr JR, Sanghvi JC, Macklin DN, Gutschow MV, Jacobs JM, Bolival B Jr., Assad-Garcia N, Glass JI, and Covert MW (2012). A whole-cell computational model predicts phenotype from genotype. Cell 150, 389–401. - PMC - PubMed

Publication types

Actions

MeSH terms

Actions
Actions
Actions
Actions

Grants and funding

LinkOut - more resources

Full Text Sources
Other Literature Sources
- scite Smart Citations

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Visible Machine Learning for Biomedicine

Affiliations

Visible Machine Learning for Biomedicine

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

Publication types

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources

Other Literature Sources