Machine learning of protein interactions in fungal secretory pathways

Jana Kludas, Mikko Arvas, Sandra Castillo, Tiina Pakula, Merja Oja, Céline Brouard, Jussi Jäntti, Merja Penttilä, Juho Rousu

Research output: Contribution to journalArticleScientificpeer-review

4 Citations (Scopus)

Abstract

In this paper we apply machine learning methods for predicting protein interactions in fungal secretion pathways. We assume an inter-species transfer setting, where training data is obtained from a single species and the objective is to predict protein interactions in other, related species. In our methodology, we combine several state of the art machine learning approaches, namely, multiple kernel learning (MKL), pairwise kernels and kernelized structured output prediction in the supervised graph inference framework. For MKL, we apply recently proposed centered kernel alignment and p-norm path following approaches to integrate several feature sets describing the proteins, demonstrating improved performance. For graph inference, we apply input-output kernel regression (IOKR) in supervised and semi-supervised modes as well as output kernel trees (OK3). In our experiments simulating increasing genetic distance, Input-Output Kernel Regression proved to be the most robust prediction approach. We also show that the MKL approaches improve the predictions compared to uniform combination of the kernels. We evaluate the methods on the task of predicting protein-protein-interactions in the secretion pathways in fungi, S.cerevisiae, baker's yeast, being the source, T. reesei being the target of the inter-species transfer learning. We identify completely novel candidate secretion proteins conserved in filamentous fungi. These proteins could contribute to their unique secretion capabilities.

Original languageEnglish
Article numbere0159302
JournalPLoS ONE
Volume11
Issue number7
DOIs
Publication statusPublished - 1 Jul 2016
MoE publication typeA1 Journal article-refereed

Fingerprint

artificial intelligence
Secretory Pathway
Learning systems
seeds
Proteins
proteins
learning
Learning
Fungi
Saccharomyces cerevisiae
secretion
prediction
Machine Learning
bakers yeast
fungi
Yeast
protein secretion
protein-protein interactions
genetic distance
methodology

Cite this

Kludas, Jana ; Arvas, Mikko ; Castillo, Sandra ; Pakula, Tiina ; Oja, Merja ; Brouard, Céline ; Jäntti, Jussi ; Penttilä, Merja ; Rousu, Juho. / Machine learning of protein interactions in fungal secretory pathways. In: PLoS ONE. 2016 ; Vol. 11, No. 7.
@article{06e92a7a30e04bb98c4f22db892d5821,
title = "Machine learning of protein interactions in fungal secretory pathways",
abstract = "In this paper we apply machine learning methods for predicting protein interactions in fungal secretion pathways. We assume an inter-species transfer setting, where training data is obtained from a single species and the objective is to predict protein interactions in other, related species. In our methodology, we combine several state of the art machine learning approaches, namely, multiple kernel learning (MKL), pairwise kernels and kernelized structured output prediction in the supervised graph inference framework. For MKL, we apply recently proposed centered kernel alignment and p-norm path following approaches to integrate several feature sets describing the proteins, demonstrating improved performance. For graph inference, we apply input-output kernel regression (IOKR) in supervised and semi-supervised modes as well as output kernel trees (OK3). In our experiments simulating increasing genetic distance, Input-Output Kernel Regression proved to be the most robust prediction approach. We also show that the MKL approaches improve the predictions compared to uniform combination of the kernels. We evaluate the methods on the task of predicting protein-protein-interactions in the secretion pathways in fungi, S.cerevisiae, baker's yeast, being the source, T. reesei being the target of the inter-species transfer learning. We identify completely novel candidate secretion proteins conserved in filamentous fungi. These proteins could contribute to their unique secretion capabilities.",
author = "Jana Kludas and Mikko Arvas and Sandra Castillo and Tiina Pakula and Merja Oja and C{\'e}line Brouard and Jussi J{\"a}ntti and Merja Penttil{\"a} and Juho Rousu",
year = "2016",
month = "7",
day = "1",
doi = "10.1371/journal.pone.0159302",
language = "English",
volume = "11",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "7",

}

Machine learning of protein interactions in fungal secretory pathways. / Kludas, Jana; Arvas, Mikko; Castillo, Sandra; Pakula, Tiina; Oja, Merja; Brouard, Céline; Jäntti, Jussi; Penttilä, Merja; Rousu, Juho.

In: PLoS ONE, Vol. 11, No. 7, e0159302, 01.07.2016.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Machine learning of protein interactions in fungal secretory pathways

AU - Kludas, Jana

AU - Arvas, Mikko

AU - Castillo, Sandra

AU - Pakula, Tiina

AU - Oja, Merja

AU - Brouard, Céline

AU - Jäntti, Jussi

AU - Penttilä, Merja

AU - Rousu, Juho

PY - 2016/7/1

Y1 - 2016/7/1

N2 - In this paper we apply machine learning methods for predicting protein interactions in fungal secretion pathways. We assume an inter-species transfer setting, where training data is obtained from a single species and the objective is to predict protein interactions in other, related species. In our methodology, we combine several state of the art machine learning approaches, namely, multiple kernel learning (MKL), pairwise kernels and kernelized structured output prediction in the supervised graph inference framework. For MKL, we apply recently proposed centered kernel alignment and p-norm path following approaches to integrate several feature sets describing the proteins, demonstrating improved performance. For graph inference, we apply input-output kernel regression (IOKR) in supervised and semi-supervised modes as well as output kernel trees (OK3). In our experiments simulating increasing genetic distance, Input-Output Kernel Regression proved to be the most robust prediction approach. We also show that the MKL approaches improve the predictions compared to uniform combination of the kernels. We evaluate the methods on the task of predicting protein-protein-interactions in the secretion pathways in fungi, S.cerevisiae, baker's yeast, being the source, T. reesei being the target of the inter-species transfer learning. We identify completely novel candidate secretion proteins conserved in filamentous fungi. These proteins could contribute to their unique secretion capabilities.

AB - In this paper we apply machine learning methods for predicting protein interactions in fungal secretion pathways. We assume an inter-species transfer setting, where training data is obtained from a single species and the objective is to predict protein interactions in other, related species. In our methodology, we combine several state of the art machine learning approaches, namely, multiple kernel learning (MKL), pairwise kernels and kernelized structured output prediction in the supervised graph inference framework. For MKL, we apply recently proposed centered kernel alignment and p-norm path following approaches to integrate several feature sets describing the proteins, demonstrating improved performance. For graph inference, we apply input-output kernel regression (IOKR) in supervised and semi-supervised modes as well as output kernel trees (OK3). In our experiments simulating increasing genetic distance, Input-Output Kernel Regression proved to be the most robust prediction approach. We also show that the MKL approaches improve the predictions compared to uniform combination of the kernels. We evaluate the methods on the task of predicting protein-protein-interactions in the secretion pathways in fungi, S.cerevisiae, baker's yeast, being the source, T. reesei being the target of the inter-species transfer learning. We identify completely novel candidate secretion proteins conserved in filamentous fungi. These proteins could contribute to their unique secretion capabilities.

UR - http://www.scopus.com/inward/record.url?scp=84979556451&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0159302

DO - 10.1371/journal.pone.0159302

M3 - Article

VL - 11

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 7

M1 - e0159302

ER -