Ferguson Lab uses tools from theory, computation, data science, and machine learning to understand macromolecular folding, engineer self-assembling colloids and peptides, and design antiviral therapies.
Research Interests:
Research in the Ferguson Lab employs molecular simulation, machine learning, and statistical thermodynamics to understand and engineer molecules and soft materials. We develop new computational tools to establish new capabilities in molecular and materials modeling and deploy these tools to advance fundamental molecular understanding and perform computational design of new functional molecules and systems. Our application areas include proteins, peptides, peptoids, immunomodulators, colloids, and nanoparticles. A hallmark of our work is the integration of artificial intelligence tools with scientific domain knowledge, and close experimental collaborations to realize our molecular and materials designs.
Enhanced Sampling. The time scales accessible to molecular dynamics simulations is limited by the short integration time steps required for numerical stability. This frustrates comprehensive sampling of configurational phase space needed to compute converged thermodynamic averages, surmount free energy barriers, and simulate rare events. Building upon our historical contributions in this area, we integrated statistical mechanics, dynamical systems theory, deep learning, and generative modeling to identify and enhance sampling in the important slow collective modes. We have appealed to transfer operator theory to design a deep learning architecture capable of estimating the slow eigenfunctions of system from simulation data, Girsanov theory to perform iterative rounds of enhanced sampling and slow variable discovery, and pioneered the latent space simulator (LSS) technique to learn surrogate dynamical models capable of generating ultra-long simulation trajectories at up to six orders of magnitude lower cost than standard molecular dynamics.
Self-Assembly. The design of building blocks programmed to self-assemble desired materials is of long-standing interest in materials science. We have coupled molecular simulation, statistical thermodynamics, and machine learning to expose the relationship between building block chemistry and architecture and the morphology and properties of the resulting self-assembled aggregates. We have used these learned relations to understand and perform inverse design of self-assembling peptides, peptoids, colloids, nanoparticles, and nucleic acids.
STAR. Takens’ Delay Embedding Theory is a remarkable result from dynamical systems theory that prescribes how a time series in a single observable of a dynamical system can be used to reconstruct the high-dimensional system state. We combined this result with tools from statistical thermodynamics, manifold learning, artificial neural networks, and rigid graph theory to establish Single-molecule TAkens Reconstruction (STAR) as a technique to reconstruct molecular configurations from single molecule Förster resonance energy transfer (smFRET) measurements. We developed and validated the approach in applications to synthetic smFRET data extracted from molecular dynamics simulations of small proteins to demonstrate reconstruction accuracies to Angstrom-level resolution even in the presence of experimentally realistic noise.
Data-Driven Molecular Discovery. Bayesian optimization presents a powerful approach to efficiently search large molecular candidate spaces in a virtuous cycle of structure-property surrogate model construction and model-guided traversal of the design space. We have applied this technique in multiple applications, including a computational campaign to discover novel small molecule diagnostic dyes capable of preferential partitioning into cardiolipin-rich lipid membranes and one of the first realizations of a multi-fidelity active learning campaign fusing high-throughput/low-accuracy computation with low-throughput/high-accuracy experiments to discover π-conjugated oligopeptides capable of self-assembling into optically and electronically active supramolecular aggregates.
Data-Driven Immunomodulator Discovery. Wielding control of signaling in innate immune pathways can enhance prophylactic vaccines by mitigating inflammation and improve immunotherapies by amplifying interferon responses. Modulation is typically achieved though adjuvants, but it has proven challenging to develop adjuvants capable of simultaneously tuning the level of stimulation in desired and undesired pathways. As an alternative strategy, we sought to identify small molecule immunomodulators capable of modulating immune stimulation in concert with existing adjuvants. Working with experimental collaborators, we pioneered data-driven active learning approaches to guide high-throughput experimental screening of immunomodulators targeting the NF-κB and IRF pathways and are investigating approaches to direct T-cell fate in applications to influenza and tuberculosis.
Data-Driven Protein Design. The design of synthetic proteins with the desired function is a long-standing goal in biomolecular science with broad applications in biochemical engineering, agriculture, medicine, and public health. Deep generative models have established a powerful new modeling paradigm to learn sequence-function mappings and use these relations to guide and accelerate synthetic protein design campaigns. We have pioneered unsupervised, semi-supervised, and self-supervised deep learning architectures to guide experimental gene synthesis and assays within a virtuous design-build-test cycle. We have used these techniques to design and experimentally validate synthetic SH3 proteins with ligand binding affinities comparable to or stronger than wild type that rescue in vivo osmosensing function in S. cerevisiae, and engineered osmosensing function into SH3 paralogs evolved to perform alternative biological tasks. We are currently developing and deploying novel generative models for the design of high-affinity and high-specificity antibodies, and developing generative protein design models capable of conditioned generation of functional proteins using natural language prompts.
Selected References
11. A.W. Long and A.L. Ferguson* “Nonlinear machine learning of patchy colloid self-assembly mechanisms and pathways” J. Phys. Chem. B 118 15 4228-4244 (2014) [ http://dx.doi.org/10.1021/jp500350b ]
12. B.D. Wall, A.E. Zacca, A.M. Sanders, W.L. Wilson, A.L. Ferguson and J.D. Tovar “Supramolecular polymorphism: Tunable electronic interactions within pi-conjugated peptide nanostructures dictated by primary amino acid sequence” Langmuir 30 20 5946-5956 (2014) [ http://dx.doi.org/10.1021/la500222y ]
14. B.D. Wall, Y. Zhou, S. Mei, H.A.M. Ardoña, A.L. Ferguson and J.D. Tovar “Variation of formal hydrogen bonding networks within electronically delocalized pi-conjugated oligopeptide nanostructures” Langmuir 30 (38) 11375–11385 (2014) [ http://www.dx.doi.org/10.1021/la501999g ]
18. A.W. Long, J. Zhang, S. Granick, and A.L. Ferguson* “Machine learning assembly landscapes from particle tracking data” Soft Matter 11 8141-8153 (2015) [ http://dx.doi.org/10.1039/C5SM01981H ]
21. B.A. Thurston, J.D. Tovar, and A.L. Ferguson* “Thermodynamics, morphology, and kinetics of early-stage self-assembly of π-conjugated oligopeptides” Mol. Sim. 42 12 955-975 (2016) [ http://dx.doi.org/10.1080/08927022.2015.1125997 ]
22. J. Wang and A.L. Ferguson* “Nonlinear reconstruction of single-molecule free-energy surfaces from univariate time series” Phys. Rev. E 93 032412 (2016) [ http://link.aps.org/doi/10.1103/PhysRevE.93.032412 ]
25. A.W. Long, C.L. Phillips, E. Jankowski, and A.L. Ferguson* “Nonlinear machine learning and design of reconfigurable digital colloids” Soft Matter 12 7119-7135 (2016) [ http://dx.doi.org/10.1039/C6SM01156J ]
26. J. Wang and A.L. Ferguson* “Mesoscale simulation of asphaltene aggregation” J. Phys. Chem. B 120 32 8016-8035 (2016) [ http://dx.doi.org/10.1021/acs.jpcb.6b05925 ]
28. E.Y. Lee, B.M. Fulan, G.C.L. Wong, and A.L. Ferguson* “Mapping membrane activity in undiscovered peptide sequence space using machine learning” Proc. Natl. Acad. Sci. USA 113 48 13588-13593 (2016) [ http://dx.doi.org/10.1073/pnas.1609893113 ]
29. R.A. Mansbach and A.L. Ferguson* “Coarse-grained molecular simulation of the hierarchical self-assembly of π-conjugated optoelectronic peptides” J. Phys. Chem. B 121 7 1684–1706 (2017) [ http://dx.doi.org/10.1021/acs.jpcb.6b10165 ]
31. J. Wang, M. Gayatri, and A.L. Ferguson* “Mesoscale simulation and machine learning of asphaltene aggregation phase behavior and molecular assembly landscapes” J. Phys. Chem. B 121 18 4923-4944 (2017) [ http://dx.doi.org/10.1021/acs.jpcb.7b02574 ]
32. R.A. Mansbach and A.L. Ferguson* “Control of the hierarchical assembly of π-conjugated optoelectronic peptides by pH and flow” Org. Biomol. Chem. 15 26 5484-5502 (2017)
[ http://dx.doi.org/10.1039/C7OB00923B ]
→ Invited submission for “Peptide Materials” special issue
→ Selected as 2017 HOT Article in Organic and Biomolecular Chemistry
→ Featured as the cover article of Organic and Biomolecular Chemistry 15 26 (2017)
33. W.F. Reinhart, A.W. Long, M.P. Howard, A.L. Ferguson, and A.Z. Panagiotopoulos “Machine learning for autonomous crystal structure identification” Soft Matter 13 4733-4745 (2017) [ http://dx.doi.org/10.1039/c7sm00957g ]
39. A.W. Long and A.L. Ferguson* “Rational design of patchy colloids via landscape engineering” Mol. Syst. Des. Eng. 3 1 49-65 (2018) [ http://dx.doi.org/10.1039/C7ME00077D ]
39. A.W. Long and A.L. Ferguson* “Rational design of patchy colloids via landscape engineering” Mol. Syst. Des. Eng. 3 1 49-65 (2018) [ http://dx.doi.org/10.1039/C7ME00077D ]
→ Invited submission to the 2018 Emerging Investigators issue
→ Selected for inside front cover image
→ Selected by journal as winner of RSC MSDE Emerging Investigator Award
→ Awarded the Institution of Chemical Engineers 2018/19 Junior Moulton Medal
45. L. Valverde, B.A. Thurston, A.L. Ferguson, and W.L. Wilson “Evidence for prenucleated fibrilogenesis of acid-mediated self-assembling oligopeptides via molecular simulation and fluorescence correlation spectroscopy” Langmuir 34 25 7346-7354 (2018) [ https://doi.org/10.1021/acs.langmuir.8b00312 ]
46. J. Wang, M. Gayatri, and A.L. Ferguson* “Coarse-grained molecular simulation and nonlinear manifold learning of archipelago asphaltene aggregation and folding” J. Phys. Chem. B 122 25 6627-6647 (2018) [ https://doi.org/10.1021/acs.jpcb.8b01634 ]
47. B.A. Thurston and A.L. Ferguson* “Machine learning and molecular design of self-assembling π-conjugated oligopeptides” Mol. Sim. 44 11 930-945 (2018) [ https://doi.org/10.1080/08927022.2018.1469754 ]
48. R.A. Mansbach and A.L. Ferguson* “A patchy particle model of the hierarchical self-assembly of π-conjugated optoelectronic peptides” J. Phys. Chem. B 122 44 10219-10236 (2018)
[ https://doi.org/10.1021/acs.jpcb.8b05781 ]
52. J. Wang and A.L. Ferguson* “Recovery of protein folding funnels from single-molecule time series by delay embeddings and manifold learning” J. Phys. Chem. B 122 50 11931–11952(2018) [ https://doi.org/10.1021/acs.jpcb.8b08800 ]
→ Invited submission to the “Deciphering Molecular Complexity in Dynamics and Kinetics from the Single Biomolecule to Single Cell Levels” special issue
54. A.W. Long and A.L. Ferguson* “Landmark diffusion maps (L-dMaps): Accelerated manifold learning out-of-sample extension” Appl. Comput. Harmon. Anal. 47 1 190-211 (2019)
[ http://dx.doi.org/10.1016/j.acha.2017.08.004 ]
→ Invited submission for “Peptide Materials” special issue
→ Selected as 2017 HOT Article in Organic and Biomolecular Chemistry
→ Featured as the cover article of Organic and Biomolecular Chemistry 15 26 (2017)
56. W. Chen, H. Sidky, and A.L. Ferguson* “Nonlinear discovery of slow molecular modes using state-free reversible VAMPnets” J. Chem. Phys. 150 214114 (2019) [ https://doi.org/10.1063/1.5092521 ]
→ Selected as J. Chem. Phys. “Editor’s Pick”
59. Y. Ma and A.L. Ferguson* “Inverse design of self-assembling colloidal crystals with omnidirectional photonic bandgaps” Soft Matter 15 8808-8826 (2019) [ https://doi.org/10.1039/C9SM01500K ]
60. W. Chen, H. Sidky, and A.L. Ferguson* “Capabilities and limitations of time-lagged autoencoders for slow mode discovery in dynamical systems” J. Chem. Phys. 151 064123 (2019) [ https://doi.org/10.1063/1.5112048 ]
61. H. Sidky, W. Chen, and A.L. Ferguson* “High-resolution Markov state models for the dynamics of Trp-cage miniprotein constructed over slow folding modes identified by state-free reversible VAMPnets” J. Phys. Chem. B 123 38 7999-8009 (2019) [ http://dx.doi.org/10.1021/acs.jpcb.9b05578 ]
63. S. Panda, K. Shmilovich, A.L. Ferguson*, and J.D. Tovar “Controlling supramolecular chirality in peptide-π-peptide networks by variation of alkyl spacer length” Langmuir 35 43 14060-14073 (2019) [ https://doi.org/10.1021/acs.langmuir.9b02683 ]
64. B.A. Thurston, E.P. Shapera, J.D. Tovar, A. Schleife, and A.L. Ferguson* “Revealing the sequence-structure-electronic property relation of self-assembling π-conjugated oligopeptides by molecular and quantum mechanical modeling” Langmuir 35 47 15221-15231 (2019) [ https://doi.org/10.1021/acs.langmuir.9b02593 ]
66. H. Sidky, W. Chen, and A.L. Ferguson* “Machine learning for collective variable discovery and enhanced sampling in biomolecular simulation” Molecular Physics 118 5 e1737742 (2020)
[ https://doi.org/10.1080/00268976.2020.1737742 ]
68. K. Shmilovich, R.A. Mansbach, H. Sidky, O.E. Dunne, S.S. Panda, J.D. Tovar, and A.L. Ferguson* “Discovery of self-assembling π-conjugated peptides by active learning-directed coarse-grained molecular simulation” J. Phys. Chem. B 124 3873-3891 (2020) [ https://doi.org/10.1021/acs.jpcb.0c00708 ]
68. K. Shmilovich, R.A. Mansbach, H. Sidky, O.E. Dunne, S.S. Panda, J.D. Tovar, and A.L. Ferguson* “Discovery of self-assembling π-conjugated peptides by active learning-directed coarse-grained molecular simulation” J. Phys. Chem. B 124 3873-3891 (2020) [ https://doi.org/10.1021/acs.jpcb.0c00708 ]
→ Invited submission to the “Machine Learning in Physical Chemistry” special issue
→ Selected as ACS Editors’ Choice article (March 30, 2020)
→ Selected for front cover art of JPCB vol. 124, issue 19 (May 14, 2020)
69. E. Jira, K. Shmilovich, T. Kale, A.L. Ferguson, J.D. Tovar, and C. Schroeder “Effect of core oligomer length on the phase behavior and assembly of π-conjugated peptides” ACS Appl. Mater. Interfaces 12 20722-20732 (2020) [ https://dx.doi.org/10.1021/acsami.0c02095 ]
71. S. Panda, K. Shmilovich, A.L. Ferguson, and J.D. Tovar “Computationally guided tuning of amino acid configuration influences the chiroptical properties of supramolecular peptide-π-peptide nanostructures” Langmuir 36 24 6782–6792 (2020) [ https://dx.doi.org/10.1021/acs.langmuir.0c00961 ]
74. H. Sidky, W. Chen, and A.L. Ferguson* “Molecular latent space simulators” Chem. Sci. 11 9459 (2020) [ http://dx.doi.org/10.1039/D0SC03635H ]
→ Selected for 2020 Chemical Science HOT Article Collection
75. M. Topel and A.L. Ferguson* “Reconstruction of protein structures from single molecule time series” J. Chem. Phys. 153 194102 (2020) [ https://doi.org/10.1063/5.0024732 ]
→ Invited submission to the “2020 JCP Emerging Investigators in Science Collection”
76. B. Sharma, Y. Ma, A.L. Ferguson*, and A.P. Liu “In search of a novel chassis material for synthetic cells: Emergence of synthetic peptide compartment” Soft Matter 16 10769 (2020)
[ https://dx.doi.org/10.1039/D0SM01644F ]
82. Y. Ma, J. Aulicino, and A.L. Ferguson* “Inverse design of self-assembling diamond photonic lattices from anisotropic colloidal clusters” J. Phys. Chem B 125 9 2398-2410 (2021) [ https://dx.doi.org/10.1021/acs.jpcb.0c08723 ]
→ Invited article for “Carol K. Hall Festschrift”
83. A.L. Ferguson* and R. Ranganathan “100th Anniversary of Macromolecular Science Viewpoint: Data-driven protein design” ACS Macro. Lett. 10 327-340 (2021) [ https://dx.doi.org/10.1021/acsmacrolett.0c00885 ]
→ Invited Viewpoint article for 2020 special collection 100th Anniversary of Macromolecular Science
→ Selected for front cover art of ACS Macro. Lett. vol. 10, issue 4 (April 20, 2021)
→ Featured in editorial review M. Müller “Selection of advances in theory and simulation during the first decade of ACS Macro Letters” ACS Macro Lett. 10 1629-1635 (2021) [ https://doi.org/10.1021/acsmacrolett.1c00750 ]
85. W. Alvarado, J. Moller, A.L. Ferguson*, and J.J. de Pablo “Tetranucleosome interactions drive chromatin folding” ACS Cent. Sci. 7 6 1019–1027 (2021) [ https://doi.org/10.1021/acscentsci.1c00085 ]
→ Selected for supplementary cover art of ACS Cent. Sci. vol. 7, issue 6 (June 23, 2021)
86. S.S. Panda, K. Shmilovich, S.M. Herringer, N.J. Marin, A.L. Ferguson, and J.D. Tovar “Computationally guided tuning of peptide-conjugated perylene diimide self-assembly” Langmuir 37 28 8594-8606 (2021) [ https://doi.org/10.1021/acs.langmuir.1c01213 ]
87. M.S. Jones, B. Ashwood, A. Tokmakoff, and A.L. Ferguson* “Determining sequence-dependent DNA oligonucleotide hybridization and dehybridization mechanisms using coarse-grained molecular simulation, Markov state models, and infrared spectroscopy” J. Am. Chem. Soc. 143 17395-17411 (2021) [ https://doi.org/10.1021/jacs.1c05219 ]
→ Invited article for “Carol K. Hall Festschrift”
→ Invited submission to the “Machine Learning in Physical Chemistry” special issue
→ Selected as ACS Editors’ Choice article (March 30, 2020)
→ Selected for front cover art of JPCB vol. 124, issue 19 (May 14, 2020)
88. B. Sharma, Y. Ma, H.L. Hiraki, B.M. Baker, A.L. Ferguson, and A.P. Liu “Facile formation of giant elastin-like polypeptide vesicles as synthetic cells” Chem. Commun. 57 13202-13205 (2021)
[ https://doi.org/10.1039/D1CC05579H ]
89. M. Zhao, K.J. Lachowski, S. Alamdari, J. Sampath, P. Mu, C.J. Mundy, J. Pfaendtner, C.-L. Chen, L.D. Pozzo, and A.L. Ferguson* “Hierarchical self-assembly pathways of polypeptoid helices and sheets” Biomacromolecules 23 3 992-1008 (2022) [ https://doi.org/10.1021/acs.biomac.1c01385 ]
90. S. Dasetty, I. Coropceanu, J. Porter, J. Li, J.J. de Pablo, D. Talapin, and A.L. Ferguson* “Active learning of polarizable nanoparticle phase diagrams for the guided design of triggerable self-assembling superlattices” Mol. Syst. Des. Eng. 7 350 – 363 (2022) [ http://dx.doi.org/10.1039/D1ME00187F ]
→ Selected by editors as MSDE HOT article
91. B. Mohr, K. Shmilovich, I.S. Kleinwächter, D. Schneider, A.L. Ferguson*, and T. Bereau “Data-driven discovery of cardiolipin-selective small molecules by computational active learning” Chem. Sci. 13 4498-4511 (2022) [ http://dx.doi.org/10.1039/D2SC00116K ]
→ Selected for 2022 ChemSci “Pick of the Week” collection
→ Featured in commentary M. Aldeghi and C.W. Coley “A focus on simulation and machine learning as complementary tools for chemical space navigation” Chem. Sci. (2022) [ https://doi.org/10.1039/d2sc90130g ]
92. K. Shmilovich, Y. Yao, J.D. Tovar, H.E. Katz, A. Schleife, and A.L. Ferguson* “Computational discovery of high charge mobility self-assembling π-conjugated peptides” Mol. Syst. Des. Eng. 7 447-459 (2022) [ http://dx.doi.org/10.1039/D2ME00017B ]
→ Selected by editors as MSDE HOT article
94. K. Shmilovich, S.S. Panda, A. Stouffer, J.D. Tovar, and A.L. Ferguson* “Hybrid computational-experimental data-driven design of self-assembling π-conjugated peptides” Digital Discovery 1 448-462 (2022) [ https://dx.doi.org/10.1039/d1dd00047k ]
95. S. Chen, J.A. Parker, C.W. Peterson, S.A. Rice, N.F. Scherer, and A.L. Ferguson* “Understanding and design of non-conservative optical matter systems using Markov state models” Mol. Sys. Des. Eng. 7 1228-1238 (2022) [ http://dx.doi.org/10.1039/D2ME00087C ]
96. N.B. Rego, A.L. Ferguson*, and A.J. Patel “Learning the relationship between nanoscale chemical patterning and hydrophobicity” Proc. Natl. Acad. Sci. USA 119 48 e2200018119 (2022) [ https://doi.org/10.1073/pnas.2200018119 ]
99. Y. Ma, R. Kapoor, B. Sharma, A.P. Liu, and A.L. Ferguson* “Computational design of self-assembling peptide chassis materials for synthetic cells” Mol. Syst. Des. Eng. 8 39-52 (2023) [ https://dx.doi.org/10.1039/D2ME00169A ]
→ Selected by editors as MSDE HOT article
100. M. Topel, A. Ejaz, A.H. Squires, and A.L. Ferguson* “Learned reconstruction of protein folding trajectories from noisy single-molecule time series” J. Chem. Theory Comput. (in press, 2022) [ http://dx.doi.org/10.1021/acs.jctc.2c00920 ]
→ Invited article for Machine Learning for Molecular Simulation special issue
102. B. Ashwood, M.S. Jones, A.L. Ferguson, and A. Tokmakoff “Disruption of energetic and dynamic base pairing cooperativity in DNA duplexes by an abasic site” Proc. Natl. Acad. Sci. USA 120 14 e2219124120 (2023) [ https://doi.org/10.1073/pnas.2219124120 ]
103. K. Shmilovich and A.L. Ferguson* “Girsanov Reweighting Enhanced Sampling Technique (GREST): On-the-fly data-driven discovery of and enhanced sampling in slow collective variables” J. Phys. Chem. A 127 15 3497-3517 (2023) [ https://doi.org/10.1021/acs.jpca.3c00505 ]
→ Invited article for “Pablo G. Debenedetti Festschrift” virtual special issue
105. M. Zhao, S. Zhang, R. Zheng, S. Alamdari, C.J. Mundy, J. Pfaendtner, L.D. Pozzo, C.-L. Chen, J. DeYoreo, and A.L. Ferguson* “Computational and experimental determination of the properties, structure, and stability of peptoid nanosheets and nanotubes” Biomacromolecules (in press, 2023) [ https://doi.org/10.1021/acs.biomac.3c00107 ]
106. W. Alvarado, V. Agrawal, W.S. Li, V.P. Dravid, V. Backman, J.J. de Pablo, and A.L. Ferguson* “Denoising autoencoder trained on simulation-derived structures for noise reduction in chromatin scanning transmission electron microscopy” ACS Cent. Sci. (accepted, 2023) [ https://doi.org/10.1021/acscentsci.3c00178 ]
107. M.S. Jones, Z.A. McDargh, R.P. Wiewiora, J.A. Izaguirre, H. Xu, and A.L. Ferguson* “Molecular latent space simulators for distributed and multi-molecular trajectories” J. Phys. Chem. A (accepted, 2023)