An Interpretable Machine-Learning Algorithm to Predict Disordered Protein Phase Separation Based on Biophysical Interactions
Protein phase separation is increasingly understood to be an important mechanism of biological organization and biomaterial formation. Intrinsically disordered protein regions (IDRs) are often significant drivers of protein phase separation. A number of protein phase-separation-prediction algorithms...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-08-01
|
Series: | Biomolecules |
Subjects: | |
Online Access: | https://www.mdpi.com/2218-273X/12/8/1131 |
_version_ | 1797432349911154688 |
---|---|
author | Hao Cai Robert M. Vernon Julie D. Forman-Kay |
author_facet | Hao Cai Robert M. Vernon Julie D. Forman-Kay |
author_sort | Hao Cai |
collection | DOAJ |
description | Protein phase separation is increasingly understood to be an important mechanism of biological organization and biomaterial formation. Intrinsically disordered protein regions (IDRs) are often significant drivers of protein phase separation. A number of protein phase-separation-prediction algorithms are available, with many being specific for particular classes of proteins and others providing results that are not amenable to the interpretation of the contributing biophysical interactions. Here, we describe LLPhyScore, a new predictor of IDR-driven phase separation, based on a broad set of physical interactions or features. LLPhyScore uses sequence-based statistics from the RCSB PDB database of folded structures for these interactions, and is trained on a manually curated set of phase-separation-driving proteins with different negative training sets including the PDB and human proteome. Competitive training for a variety of physical chemical interactions shows the greatest contribution of solvent contacts, disorder, hydrogen bonds, pi–pi contacts, and kinked beta-structures to the score, with electrostatics, cation–pi contacts, and the absence of a helical secondary structure also contributing. LLPhyScore has strong phase-separation-prediction recall statistics and enables a breakdown of the contribution from each physical feature to a sequence’s phase-separation propensity, while recognizing the interdependence of many of these features. The tool should be a valuable resource for guiding experiments and providing hypotheses for protein function in normal and pathological states, as well as for understanding how specificity emerges in defining individual biomolecular condensates. |
first_indexed | 2024-03-09T10:00:11Z |
format | Article |
id | doaj.art-2a824a7e044a4604a225289120d2eca6 |
institution | Directory Open Access Journal |
issn | 2218-273X |
language | English |
last_indexed | 2024-03-09T10:00:11Z |
publishDate | 2022-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Biomolecules |
spelling | doaj.art-2a824a7e044a4604a225289120d2eca62023-12-01T23:29:18ZengMDPI AGBiomolecules2218-273X2022-08-01128113110.3390/biom12081131An Interpretable Machine-Learning Algorithm to Predict Disordered Protein Phase Separation Based on Biophysical InteractionsHao Cai0Robert M. Vernon1Julie D. Forman-Kay2Molecular Medicine Program, Hospital for Sick Children, Toronto, ON M5G 0A4, CanadaMolecular Medicine Program, Hospital for Sick Children, Toronto, ON M5G 0A4, CanadaMolecular Medicine Program, Hospital for Sick Children, Toronto, ON M5G 0A4, CanadaProtein phase separation is increasingly understood to be an important mechanism of biological organization and biomaterial formation. Intrinsically disordered protein regions (IDRs) are often significant drivers of protein phase separation. A number of protein phase-separation-prediction algorithms are available, with many being specific for particular classes of proteins and others providing results that are not amenable to the interpretation of the contributing biophysical interactions. Here, we describe LLPhyScore, a new predictor of IDR-driven phase separation, based on a broad set of physical interactions or features. LLPhyScore uses sequence-based statistics from the RCSB PDB database of folded structures for these interactions, and is trained on a manually curated set of phase-separation-driving proteins with different negative training sets including the PDB and human proteome. Competitive training for a variety of physical chemical interactions shows the greatest contribution of solvent contacts, disorder, hydrogen bonds, pi–pi contacts, and kinked beta-structures to the score, with electrostatics, cation–pi contacts, and the absence of a helical secondary structure also contributing. LLPhyScore has strong phase-separation-prediction recall statistics and enables a breakdown of the contribution from each physical feature to a sequence’s phase-separation propensity, while recognizing the interdependence of many of these features. The tool should be a valuable resource for guiding experiments and providing hypotheses for protein function in normal and pathological states, as well as for understanding how specificity emerges in defining individual biomolecular condensates.https://www.mdpi.com/2218-273X/12/8/1131biomolecular condensatesmachine learningpredictorphysical interactionsintrinsically disordered proteinsphase separation |
spellingShingle | Hao Cai Robert M. Vernon Julie D. Forman-Kay An Interpretable Machine-Learning Algorithm to Predict Disordered Protein Phase Separation Based on Biophysical Interactions Biomolecules biomolecular condensates machine learning predictor physical interactions intrinsically disordered proteins phase separation |
title | An Interpretable Machine-Learning Algorithm to Predict Disordered Protein Phase Separation Based on Biophysical Interactions |
title_full | An Interpretable Machine-Learning Algorithm to Predict Disordered Protein Phase Separation Based on Biophysical Interactions |
title_fullStr | An Interpretable Machine-Learning Algorithm to Predict Disordered Protein Phase Separation Based on Biophysical Interactions |
title_full_unstemmed | An Interpretable Machine-Learning Algorithm to Predict Disordered Protein Phase Separation Based on Biophysical Interactions |
title_short | An Interpretable Machine-Learning Algorithm to Predict Disordered Protein Phase Separation Based on Biophysical Interactions |
title_sort | interpretable machine learning algorithm to predict disordered protein phase separation based on biophysical interactions |
topic | biomolecular condensates machine learning predictor physical interactions intrinsically disordered proteins phase separation |
url | https://www.mdpi.com/2218-273X/12/8/1131 |
work_keys_str_mv | AT haocai aninterpretablemachinelearningalgorithmtopredictdisorderedproteinphaseseparationbasedonbiophysicalinteractions AT robertmvernon aninterpretablemachinelearningalgorithmtopredictdisorderedproteinphaseseparationbasedonbiophysicalinteractions AT juliedformankay aninterpretablemachinelearningalgorithmtopredictdisorderedproteinphaseseparationbasedonbiophysicalinteractions AT haocai interpretablemachinelearningalgorithmtopredictdisorderedproteinphaseseparationbasedonbiophysicalinteractions AT robertmvernon interpretablemachinelearningalgorithmtopredictdisorderedproteinphaseseparationbasedonbiophysicalinteractions AT juliedformankay interpretablemachinelearningalgorithmtopredictdisorderedproteinphaseseparationbasedonbiophysicalinteractions |