PaRSnIP

Sequence-based protein solubility prediction using gradient boosting machine

Reda Rawi, RaghvenPhDa Mall, Khalid Kunji, Chen Hsiang Shen, Peter D. Kwong, Gwo Yu Chuang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Motivation Protein solubility can be a decisive factor in both research and production efficiency, and in silico sequence-based predictors that can accurately estimate solubility outcomes are highly sought. Results In this study, we present a novel approach termed PRotein SolubIlity Predictor (PaRSnIP), which uses a gradient boosting machine algorithm as well as an approximation of sequence and structural features of the protein of interest. Based on an independent test set, PaRSnIP outperformed other state-of-The-Art sequence-based methods by more than 9% in accuracy and 0.17 in Matthew's correlation coefficient, with an overall accuracy of 74% and Matthew's correlation coefficient of 0.48. Additionally, PaRSnIP provides importance scores for all features used in training. We observed higher fractions of exposed residues to associate positively with protein solubility and tripeptide stretches with multiple histidines to associate negatively with solubility. The improved prediction accuracy of PaRSnIP should enable it to predict protein solubility with greater reliability and to screen for sequence variants with enhanced manufacturability. Availability and implementation PaRSnIP software is available for download under GitHub (https://github.com/RedaRawi/PaRSnIP). Contact gwo-yu.chuang@nih.gov Supplementary informationSupplementary dataare available at Bioinformatics online.

Original languageEnglish
Pages (from-to)1092-1098
Number of pages7
JournalBioinformatics
Volume34
Issue number7
DOIs
Publication statusPublished - 1 Apr 2018

Fingerprint

Solubility
Boosting
Gradient
Proteins
Protein
Prediction
Correlation coefficient
Predictors
Approximation algorithms
Test Set
Bioinformatics
Stretch
Independent Set
Computational Biology
Histidine
Computer Simulation
Software
Availability
Contact
Predict

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

PaRSnIP : Sequence-based protein solubility prediction using gradient boosting machine. / Rawi, Reda; Mall, RaghvenPhDa; Kunji, Khalid; Shen, Chen Hsiang; Kwong, Peter D.; Chuang, Gwo Yu.

In: Bioinformatics, Vol. 34, No. 7, 01.04.2018, p. 1092-1098.

Research output: Contribution to journalArticle

Rawi, Reda ; Mall, RaghvenPhDa ; Kunji, Khalid ; Shen, Chen Hsiang ; Kwong, Peter D. ; Chuang, Gwo Yu. / PaRSnIP : Sequence-based protein solubility prediction using gradient boosting machine. In: Bioinformatics. 2018 ; Vol. 34, No. 7. pp. 1092-1098.
@article{d270a6ce9a284b87b1fda2d070c4f307,
title = "PaRSnIP: Sequence-based protein solubility prediction using gradient boosting machine",
abstract = "Motivation Protein solubility can be a decisive factor in both research and production efficiency, and in silico sequence-based predictors that can accurately estimate solubility outcomes are highly sought. Results In this study, we present a novel approach termed PRotein SolubIlity Predictor (PaRSnIP), which uses a gradient boosting machine algorithm as well as an approximation of sequence and structural features of the protein of interest. Based on an independent test set, PaRSnIP outperformed other state-of-The-Art sequence-based methods by more than 9{\%} in accuracy and 0.17 in Matthew's correlation coefficient, with an overall accuracy of 74{\%} and Matthew's correlation coefficient of 0.48. Additionally, PaRSnIP provides importance scores for all features used in training. We observed higher fractions of exposed residues to associate positively with protein solubility and tripeptide stretches with multiple histidines to associate negatively with solubility. The improved prediction accuracy of PaRSnIP should enable it to predict protein solubility with greater reliability and to screen for sequence variants with enhanced manufacturability. Availability and implementation PaRSnIP software is available for download under GitHub (https://github.com/RedaRawi/PaRSnIP). Contact gwo-yu.chuang@nih.gov Supplementary informationSupplementary dataare available at Bioinformatics online.",
author = "Reda Rawi and RaghvenPhDa Mall and Khalid Kunji and Shen, {Chen Hsiang} and Kwong, {Peter D.} and Chuang, {Gwo Yu}",
year = "2018",
month = "4",
day = "1",
doi = "10.1093/bioinformatics/btx662",
language = "English",
volume = "34",
pages = "1092--1098",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "7",

}

TY - JOUR

T1 - PaRSnIP

T2 - Sequence-based protein solubility prediction using gradient boosting machine

AU - Rawi, Reda

AU - Mall, RaghvenPhDa

AU - Kunji, Khalid

AU - Shen, Chen Hsiang

AU - Kwong, Peter D.

AU - Chuang, Gwo Yu

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Motivation Protein solubility can be a decisive factor in both research and production efficiency, and in silico sequence-based predictors that can accurately estimate solubility outcomes are highly sought. Results In this study, we present a novel approach termed PRotein SolubIlity Predictor (PaRSnIP), which uses a gradient boosting machine algorithm as well as an approximation of sequence and structural features of the protein of interest. Based on an independent test set, PaRSnIP outperformed other state-of-The-Art sequence-based methods by more than 9% in accuracy and 0.17 in Matthew's correlation coefficient, with an overall accuracy of 74% and Matthew's correlation coefficient of 0.48. Additionally, PaRSnIP provides importance scores for all features used in training. We observed higher fractions of exposed residues to associate positively with protein solubility and tripeptide stretches with multiple histidines to associate negatively with solubility. The improved prediction accuracy of PaRSnIP should enable it to predict protein solubility with greater reliability and to screen for sequence variants with enhanced manufacturability. Availability and implementation PaRSnIP software is available for download under GitHub (https://github.com/RedaRawi/PaRSnIP). Contact gwo-yu.chuang@nih.gov Supplementary informationSupplementary dataare available at Bioinformatics online.

AB - Motivation Protein solubility can be a decisive factor in both research and production efficiency, and in silico sequence-based predictors that can accurately estimate solubility outcomes are highly sought. Results In this study, we present a novel approach termed PRotein SolubIlity Predictor (PaRSnIP), which uses a gradient boosting machine algorithm as well as an approximation of sequence and structural features of the protein of interest. Based on an independent test set, PaRSnIP outperformed other state-of-The-Art sequence-based methods by more than 9% in accuracy and 0.17 in Matthew's correlation coefficient, with an overall accuracy of 74% and Matthew's correlation coefficient of 0.48. Additionally, PaRSnIP provides importance scores for all features used in training. We observed higher fractions of exposed residues to associate positively with protein solubility and tripeptide stretches with multiple histidines to associate negatively with solubility. The improved prediction accuracy of PaRSnIP should enable it to predict protein solubility with greater reliability and to screen for sequence variants with enhanced manufacturability. Availability and implementation PaRSnIP software is available for download under GitHub (https://github.com/RedaRawi/PaRSnIP). Contact gwo-yu.chuang@nih.gov Supplementary informationSupplementary dataare available at Bioinformatics online.

UR - http://www.scopus.com/inward/record.url?scp=85045857447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045857447&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btx662

DO - 10.1093/bioinformatics/btx662

M3 - Article

VL - 34

SP - 1092

EP - 1098

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 7

ER -