Protein function in precision medicine: deep understanding with machine learning

Burkhard Rost, Predrag Radivojac, Yana Bromberg

Research output: Contribution to journalReview article

17 Citations (Scopus)

Abstract

Precision medicine and personalized health efforts propose leveraging complex molecular, medical and family history, along with other types of personal data toward better life. We argue that this ambitious objective will require advanced and specialized machine learning solutions. Simply skimming some low-hanging results off the data wealth might have limited potential. Instead, we need to better understand all parts of the system to define medically relevant causes and effects: how do particular sequence variants affect particular proteins and pathways? How do these effects, in turn, cause the health or disease-related phenotype? Toward this end, deeper understanding will not simply diffuse from deeper machine learning, but from more explicit focus on understanding protein function, context-specific protein interaction networks, and impact of variation on both.

Original languageEnglish (US)
Pages (from-to)2327-2341
Number of pages15
JournalFEBS Letters
DOIs
StatePublished - Aug 1 2016

Fingerprint

Precision Medicine
Medicine
Learning systems
Medical History Taking
Protein Interaction Maps
Health
Data privacy
Proteins
Phenotype
Machine Learning

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Genetics
  • Cell Biology

Keywords

  • computational prediction
  • molecular mechanism of disease
  • protein function
  • variant effect

Cite this

@article{fd39639d4cfd42d48e29b467e03f218d,
title = "Protein function in precision medicine: deep understanding with machine learning",
abstract = "Precision medicine and personalized health efforts propose leveraging complex molecular, medical and family history, along with other types of personal data toward better life. We argue that this ambitious objective will require advanced and specialized machine learning solutions. Simply skimming some low-hanging results off the data wealth might have limited potential. Instead, we need to better understand all parts of the system to define medically relevant causes and effects: how do particular sequence variants affect particular proteins and pathways? How do these effects, in turn, cause the health or disease-related phenotype? Toward this end, deeper understanding will not simply diffuse from deeper machine learning, but from more explicit focus on understanding protein function, context-specific protein interaction networks, and impact of variation on both.",
keywords = "computational prediction, molecular mechanism of disease, protein function, variant effect",
author = "Burkhard Rost and Predrag Radivojac and Yana Bromberg",
year = "2016",
month = "8",
day = "1",
doi = "10.1002/1873-3468.12307",
language = "English (US)",
pages = "2327--2341",
journal = "FEBS Letters",
issn = "0014-5793",
publisher = "Elsevier",

}

Protein function in precision medicine : deep understanding with machine learning. / Rost, Burkhard; Radivojac, Predrag; Bromberg, Yana.

In: FEBS Letters, 01.08.2016, p. 2327-2341.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Protein function in precision medicine

T2 - deep understanding with machine learning

AU - Rost, Burkhard

AU - Radivojac, Predrag

AU - Bromberg, Yana

PY - 2016/8/1

Y1 - 2016/8/1

N2 - Precision medicine and personalized health efforts propose leveraging complex molecular, medical and family history, along with other types of personal data toward better life. We argue that this ambitious objective will require advanced and specialized machine learning solutions. Simply skimming some low-hanging results off the data wealth might have limited potential. Instead, we need to better understand all parts of the system to define medically relevant causes and effects: how do particular sequence variants affect particular proteins and pathways? How do these effects, in turn, cause the health or disease-related phenotype? Toward this end, deeper understanding will not simply diffuse from deeper machine learning, but from more explicit focus on understanding protein function, context-specific protein interaction networks, and impact of variation on both.

AB - Precision medicine and personalized health efforts propose leveraging complex molecular, medical and family history, along with other types of personal data toward better life. We argue that this ambitious objective will require advanced and specialized machine learning solutions. Simply skimming some low-hanging results off the data wealth might have limited potential. Instead, we need to better understand all parts of the system to define medically relevant causes and effects: how do particular sequence variants affect particular proteins and pathways? How do these effects, in turn, cause the health or disease-related phenotype? Toward this end, deeper understanding will not simply diffuse from deeper machine learning, but from more explicit focus on understanding protein function, context-specific protein interaction networks, and impact of variation on both.

KW - computational prediction

KW - molecular mechanism of disease

KW - protein function

KW - variant effect

UR - http://www.scopus.com/inward/record.url?scp=84981709993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84981709993&partnerID=8YFLogxK

U2 - 10.1002/1873-3468.12307

DO - 10.1002/1873-3468.12307

M3 - Review article

C2 - 27423136

AN - SCOPUS:84981709993

SP - 2327

EP - 2341

JO - FEBS Letters

JF - FEBS Letters

SN - 0014-5793

ER -