DeepSol: a Deep Learning Framework for Sequence-based Protein Solubility Prediction

Overview

Journal Bioinformatics

Publisher Oxford University Press

Specialty Biology

Date 2018 Mar 20

PMID 29554211

Citations 75

Authors

Sameer Khurana

Reda Rawi

Khalid Kunji

Gwo-Yu Chuang

Halima Bensmail

Raghvendra Mall

Affiliations

Soon will be listed here.

Abstract

Motivation: Protein solubility plays a vital role in pharmaceutical research and production yield. For a given protein, the extent of its solubility can represent the quality of its function, and is ultimately defined by its sequence. Thus, it is imperative to develop novel, highly accurate in silico sequence-based protein solubility predictors. In this work we propose, DeepSol, a novel Deep Learning-based protein solubility predictor. The backbone of our framework is a convolutional neural network that exploits k-mer structure and additional sequence and structural features extracted from the protein sequence.

Results: DeepSol outperformed all known sequence-based state-of-the-art solubility prediction methods and attained an accuracy of 0.77 and Matthew's correlation coefficient of 0.55. The superior prediction accuracy of DeepSol allows to screen for sequences with enhanced production capacity and can more reliably predict solubility of novel proteins.

Availability And Implementation: DeepSol's best performing models and results are publicly deposited at https://doi.org/10.5281/zenodo.1162886 (Khurana and Mall, 2018).

Supplementary Information: Supplementary data are available at Bioinformatics online.

Citing Articles

ProG-SOL: Predicting Protein Solubility Using Protein Embeddings and Dual-Graph Convolutional Networks.

Li G, Zhang N, Fan L ACS Omega. 2025; 10(4):3910-3916.

PMID: 39926503 PMC: 11800053. DOI: 10.1021/acsomega.4c09688.

Advances in cyclotide research: bioactivity to cyclotide-based therapeutics.

Grover A, Singh S, Sindhu S, Lath A, Kumar S Mol Divers. 2025; .

PMID: 39862350 DOI: 10.1007/s11030-025-11113-w.

Benchmarking protein language models for protein crystallization.

Mall R, Kaushik R, Martinez Z, Thomson M, Castiglione F Sci Rep. 2025; 15(1):2381.

PMID: 39827171 PMC: 11743144. DOI: 10.1038/s41598-025-86519-5.

Protein engineering in the deep learning era.

Zhou B, Tan Y, Hu Y, Zheng L, Zhong B, Hong L mLife. 2025; 3(4):477-491.

PMID: 39744096 PMC: 11685842. DOI: 10.1002/mlf2.12157.

Synergistic growth suppression of Fusarium oxysporum MLY127 through Dimethachlon Nanoencapsulation and co-application with Bacillus velezensis MLY71.

Yang L, Gao J, Xiang D, Hu X, Lin G, Liu Y Sci Rep. 2024; 14(1):29967.

PMID: 39623089 PMC: 11612293. DOI: 10.1038/s41598-024-81356-4.

References

Smialowski P, Martin-Galiano A, Mikolajka A, Girschick T, Holak T, Frishman D . Protein solubility: sequence based prediction and experimental verification. Bioinformatics. 2006; 23(19):2536-42. DOI: 10.1093/bioinformatics/btl623. View

Asgari E, Mofrad M . Continuous Distributed Representation of Biological Sequences for Deep Proteomics and Genomics. PLoS One. 2015; 10(11):e0141287. PMC: 4640716. DOI: 10.1371/journal.pone.0141287. View

Wang S, Sun S, Li Z, Zhang R, Xu J . Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model. PLoS Comput Biol. 2017; 13(1):e1005324. PMC: 5249242. DOI: 10.1371/journal.pcbi.1005324. View

van den Berg B, Reinders M, Hulsman M, Wu L, Pel H, Roubos J . Exploring sequence characteristics related to high-level production of secreted proteins in Aspergillus niger. PLoS One. 2012; 7(10):e45869. PMC: 3462195. DOI: 10.1371/journal.pone.0045869. View

Magnan C, Randall A, Baldi P . SOLpro: accurate sequence-based prediction of protein solubility. Bioinformatics. 2009; 25(17):2200-7. DOI: 10.1093/bioinformatics/btp386. View

Hou J, Adhikari B, Cheng J . DeepSF: deep convolutional neural network for mapping protein sequences to folds. Bioinformatics. 2017; 34(8):1295-1303. PMC: 5905591. DOI: 10.1093/bioinformatics/btx780. View

Wilkinson D, HARRISON R . Predicting the solubility of recombinant proteins in Escherichia coli. Biotechnology (N Y). 1991; 9(5):443-8. DOI: 10.1038/nbt0591-443. View

Bertone P, Kluger Y, Lan N, Zheng D, Christendat D, Yee A . SPINE: an integrated tracking database and data mining approach for identifying feasible targets in high-throughput structural proteomics. Nucleic Acids Res. 2001; 29(13):2884-98. PMC: 55760. DOI: 10.1093/nar/29.13.2884. View

Fu L, Niu B, Zhu Z, Wu S, Li W . CD-HIT: accelerated for clustering the next-generation sequencing data. Bioinformatics. 2012; 28(23):3150-2. PMC: 3516142. DOI: 10.1093/bioinformatics/bts565. View

10.

Li W, Godzik A . Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics. 2006; 22(13):1658-9. DOI: 10.1093/bioinformatics/btl158. View

11.

Khurana S, Rawi R, Kunji K, Chuang G, Bensmail H, Mall R . DeepSol: a deep learning framework for sequence-based protein solubility prediction. Bioinformatics. 2018; 34(15):2605-2613. PMC: 6355112. DOI: 10.1093/bioinformatics/bty166. View

12.

DAVIS G, Elisee C, Newham D, HARRISON R . New fusion protein systems designed to give soluble expression in Escherichia coli. Biotechnol Bioeng. 1999; 65(4):382-8. View

13.

Christendat D, Yee A, Dharamsi A, Kluger Y, Savchenko A, Cort J . Structural proteomics of an archaeon. Nat Struct Biol. 2000; 7(10):903-9. DOI: 10.1038/82823. View

14.

Agostini F, Vendruscolo M, Tartaglia G . Sequence-based prediction of protein solubility. J Mol Biol. 2011; 421(2-3):237-41. DOI: 10.1016/j.jmb.2011.12.005. View

15.

Trainor K, Broom A, Meiering E . Exploring the relationships between protein sequence, structure and solubility. Curr Opin Struct Biol. 2017; 42:136-146. DOI: 10.1016/j.sbi.2017.01.004. View

16.

Rawi R, Mall R, Kunji K, Shen C, Kwong P, Chuang G . PaRSnIP: sequence-based protein solubility prediction using gradient boosting machine. Bioinformatics. 2017; 34(7):1092-1098. PMC: 6031027. DOI: 10.1093/bioinformatics/btx662. View

17.

Huang H, Charoenkwan P, Kao T, Lee H, Chang F, Huang W . Prediction and analysis of protein solubility using a novel scoring card method with dipeptide composition. BMC Bioinformatics. 2013; 13 Suppl 17:S3. PMC: 3521471. DOI: 10.1186/1471-2105-13-S17-S3. View

18.

Idicula-Thomas S, Balaji P . Understanding the relationship between the primary structure of proteins and its propensity to be soluble on overexpression in Escherichia coli. Protein Sci. 2005; 14(3):582-92. PMC: 2279285. DOI: 10.1110/ps.041009005. View

19.

Smialowski P, Doose G, Torkler P, Kaufmann S, Frishman D . PROSO II--a new method for protein solubility prediction. FEBS J. 2012; 279(12):2192-200. DOI: 10.1111/j.1742-4658.2012.08603.x. View

20.

Wang S, Peng J, Ma J, Xu J . Protein Secondary Structure Prediction Using Deep Convolutional Neural Fields. Sci Rep. 2016; 6:18962. PMC: 4707437. DOI: 10.1038/srep18962. View