Novel Machine Learning Application for Prediction of Membrane Insertion Potential of Cell-Penetrating Peptides.

Cell-penetrating peptides (CPPs) are often used as transporter systems to deliver various therapeutic agents into the cell. We developed a novel machine learning application which can quantitatively screen the insertion/interaction potential of various CPPs into three model phospholipid monolayers. An artificial neural network (ANN) was designed, trained, and ultimately tested on an external dataset using Langmuir experimental data for 13 CPPs (hydrophilic and amphiphilic) together with various features related to the insertion/interaction efficiency of CPPs. The trained ANN provided accurate predictions of the maximum change in surface pressure of CPPs when injected below three membrane models at pH 7.4. The accuracy of predictions was high for the dataset which was used to construct the model (r2 = 0.986) as well as for the external "prospective" dataset (r2 = 0.969). In conclusion, this study demonstrates the promising potential of ANNs for screening the insertion potential of CPPs into membrane models for efficient intracellular delivery of therapeutic agents.

[1]  V. Labhasetwar,et al.  Biomechanics and Thermodynamics of Nanoparticle Interactions with Plasma and Endosomal Membrane Lipids in Cellular Uptake and Endosomal Escape , 2014, Langmuir : the ACS journal of surfaces and colloids.

[2]  C. Berkland,et al.  Dynamic measurements of membrane insertion potential of synthetic cell penetrating peptides. , 2013, Langmuir : the ACS journal of surfaces and colloids.

[3]  A. Fakhari,et al.  “Soft” Calcium Crosslinks Enable Highly Efficient Gene Transfection Using TAT Peptide , 2009, Pharmaceutical Research.

[4]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[5]  D. Rossi,et al.  Cell-Penetrating Peptides: From Basic Research to Clinics. , 2017, Trends in pharmacological sciences.

[6]  Ű. Langel,et al.  Cell-penetrating peptides--a brief introduction. , 2006, Biochimica et biophysica acta.

[7]  Gianluca Pollastri,et al.  CPPpred: prediction of cell penetrating peptides , 2013, Bioinform..

[8]  P. Greimel,et al.  Lipid compartmentalization in the endosome system. , 2014, Seminars in cell & developmental biology.

[9]  Eric Vives,et al.  Cell-penetrating Peptides , 2003, The Journal of Biological Chemistry.

[10]  L. Chernomordik,et al.  Dengue Virus Ensures Its Fusion in Late Endosomes Using Compartment-Specific Lipids , 2010, PLoS pathogens.

[11]  Justin M. Wolfe,et al.  Machine Learning To Predict Cell-Penetrating Peptides for Antisense Delivery , 2018, ACS central science.

[12]  A. Krogh.  What are artificial neural networks? , 2008, Nature Biotechnology.

[13]  G. Brezesinski,et al.  Adsorption of the antimicrobial peptide arenicin and its linear derivative to model membranes--a maximum insertion pressure study. , 2013, Chemistry and physics of lipids.

[14]  R. Zhuo,et al.  Bioreducible Polypeptide Containing Cell-Penetrating Sequence for Efficient Gene Delivery , 2013, Pharmaceutical Research.

[15]  C. Berkland,et al.  Effect of lipid headgroup charge and pH on the stability and membrane insertion potential of calcium condensed gene complexes. , 2015, Langmuir : the ACS journal of surfaces and colloids.

[16]  M. Morris,et al.  Cell-penetrating peptides: tools for intracellular delivery of therapeutics , 2005, Cellular and Molecular Life Sciences CMLS.

[17]  S. Futaki,et al.  Membrane permeability commonly shared among arginine‐rich peptides , 2003, Journal of molecular recognition : JMR.

[18]  L. Chernomordik,et al.  Cell-penetrating peptide induces leaky fusion of liposomes containing late endosome-specific anionic lipid. , 2010, Biophysical journal.

[19]  C. Berkland,et al.  Calcium condensed cell penetrating peptide complexes offer highly efficient, low toxicity gene silencing. , 2012, International journal of pharmaceutics.

[20]  M. Deleu,et al.  From biological membranes to biomimetic model membranes , 2010 .

[21]  C. Berkland,et al.  Noncovalently associated cell-penetrating peptides for gene delivery applications. , 2013, Therapeutic delivery.

[22]  J. Seelig,et al.  Protein transduction domains of HIV-1 and SIV TAT interact with charged lipid vesicles. Binding mechanism and thermodynamic analysis. , 2003, Biochemistry.

[23]  I. Alves,et al.  Structure and dynamics of the two amphipathic arginine-rich peptides RW9 and RL9 in a lipid environment investigated by solid-state NMR and MD simulations. , 2013, Biochimica et biophysica acta.

[24]  Stephen R. Marsland,et al.  Machine Learning - An Algorithmic Perspective , 2009, Chapman and Hall / CRC machine learning and pattern recognition series.

[25]  C. Berkland,et al.  Calcium condensation of DNA complexed with cell-penetrating peptides offers efficient, noncytotoxic gene delivery. , 2011, Journal of pharmaceutical sciences.

[26]  R. Hancock,et al.  Interaction of Cationic Antimicrobial Peptides with Model Membranes* , 2001, The Journal of Biological Chemistry.

[27]  C. Berkland,et al.  Calcium condensed LABL-TAT complexes effectively target gene delivery to ICAM-1 expressing cells. , 2011, Molecular pharmaceutics.

[28]  D. Phoenix,et al.  Effect of salt on the interaction of Hal18 with lipid membranes , 2012, European Biophysics Journal.

[29]  S. Futaki,et al.  Arginine-rich peptides and their internalization mechanisms. , 2007, Biochemical Society transactions.

[30]  Tarmo Tamm,et al.  Prediction of Cell-Penetrating Peptides Using Artificial Neural Networks. , 2010, Current computer-aided drug design.

[31]  Alanna Schepartz,et al.  Fluorescence correlation spectroscopy reveals highly efficient cytosolic delivery of certain penta-arg proteins and stapled peptides. , 2015, Journal of the American Chemical Society.

[32]  Wioletta Zielińska,et al.  Cell-penetrating peptides and their utility in genome function modifications (Review) , 2017, International journal of molecular medicine.

[33]  I. Alves,et al.  Membrane interactions of two arginine-rich peptides with different cell internalization capacities. , 2012, Biochimica et biophysica acta.

[34]  Safa A. Damiati,et al.  Application of machine learning in prediction of hydrotrope-enhanced solubilisation of indomethacin. , 2017, International journal of pharmaceutics.

[35]  F. Ruddle,et al.  Mechanisms of DNA uptake by mammalian cells: fate of exogenously added DNA monitored by the use of fluorescent dyes. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[36]  Maurice Green,et al.  Autonomous functional domains of chemically synthesized human immunodeficiency virus tat trans-activator protein , 1988, Cell.

[37]  Å. Rasmuson,et al.  Prediction of solid state properties of co-crystals using artificial neural network modelling , 2018 .

[38]  M. Morris,et al.  Twenty years of cell-penetrating peptides: from molecular mechanisms to therapeutics , 2009, British journal of pharmacology.

[39]  C. Berkland,et al.  Polyarginine molecular weight determines transfection efficiency of calcium condensed complexes. , 2013, Molecular pharmaceutics.

[40]  C. Berkland,et al.  Charge Type, Charge Spacing, and Hydrophobicity of Arginine-Rich Cell-Penetrating Peptides Dictate Gene Transfection. , 2016, Molecular pharmaceutics.

[41]  Daniel G. Anderson,et al.  Rationally designed tumor-penetrating nanocomplexes. , 2012, ACS nano.

[42]  K. Leong,et al.  Quantitative comparison of intracellular unpacking kinetics of polyplexes by a model constructed from quantum dot-FRET. , 2008, Molecular therapy : the journal of the American Society of Gene Therapy.

[43]  C. Berkland,et al.  Intratracheal administration of a nanoparticle-based therapy with the angiotensin II type 2 receptor gene attenuates lung cancer growth. , 2012, Cancer research.

[44]  Carl O. Pabo,et al.  Cellular uptake of the tat protein from human immunodeficiency virus , 1988, Cell.

[45]  Wong,et al.  Biological barriers to cellular delivery of lipid-based DNA carriers. , 1999, Advanced drug delivery reviews.

[46]  C. Coutelle,et al.  Calcium ions as efficient cofactor of polycation-mediated gene transfer. , 1999, Biochimica et biophysica acta.

[47]  John P. McDermott,et al.  R1: A Rule-Based Configurer of Computer Systems , 1982, Artif. Intell..

[48]  Balachandran Manavalan,et al.  Machine-Learning-Based Prediction of Cell-Penetrating Peptides and Their Uptake Efficiency with Improved Accuracy. , 2018, Journal of proteome research.