Michelle E. McCully
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Michelle E. McCully has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Catrina Nguyen
Department of Biology Santa Clara University Santa Clara California USA
2 shared publications- Brigitte A Li
Department of Biology, Santa Clara University , 500 El Camino Real, Santa Clara, CA 95053, USA
1 shared publication - David A. C. Beck
University of Washington
1 shared publication - David Anastasiu
Santa Clara University
1 shared publication - Gabriel Gouvea Slade
Institute of Exact Sciences, Naturals and Education, Federal University of Triângulo Mineiro (UFTM), Uberaba, Brazil
1 shared publication - Hamed Akbari
Department of Bioengineering, School of Engineering, Santa Clara University, Santa Clara, CA, USA
1 shared publication
Latest Publications
- Open Access
Uncovering Features of ProteinMPNN with Sparse Autoencoders
Customization and modification of machine learning derived sequences can be achieved by understanding the mechanics behind state-of-the-art protein design models such as ProteinMPNN. Uninterpretability is hypothesized to be due largely to polysemanticity where neural networks store more features than they have dimensions. Here, we introduce sparse autoencoders (SAEs) into ProteinMPNN which expand its latent space and uncovers correlations between the activations in sparse dimensions and the presence of protein features such as secondary structure, residue volume, residue shape, disulfide bridges, and coordination to ligands. Additionally, we show that sparse activations can be manipulated to produce a variant of the short chain variable fragment Brolucizumab that is more thermostable than variants produced by traditional machine learning methods based on high temperature molecular dynamics simulations. Thus, SAEs provide both mechanistic understanding of protein design models and allow customizable manipulation of sequence prediction.
Open AccessUncovering Features of ProteinMPNN with Sparse Autoencoders
Customization and modification of machine learning derived sequences can be achieved by understanding the mechanics behind state-of-the-art protein design models such as ProteinMPNN. Uninterpretability is hypothesized to be due largely to polysemanticity where neural networks store more features than they have dimensions. Here, we introduce sparse autoencoders (SAEs) into ProteinMPNN which expand its latent space and uncovers correlations between the activations in sparse dimensions and the presence of protein features such as secondary structure, residue volume, residue shape, disulfide bridges, and coordination to ligands. Additionally, we show that sparse activations can be manipulated to produce a variant of the short chain variable fragment Brolucizumab that is more thermostable than variants produced by traditional machine learning methods based on high temperature molecular dynamics simulations. Thus, SAEs provide both mechanistic understanding of protein design models and allow customizable manipulation of sequence prediction.
- 1 March 2022
- Published by Elsevier in Current Opinion in Structural Biology
- Vol. 73, 102347
Editorial overview: Theory and simulation: Molecular modeling from atoms to complexes
- 1 March 2022
- Published by Elsevier in Current Opinion in Structural Biology
- Vol. 73, 102347
Editorial overview: Theory and simulation: Molecular modeling from atoms to complexes
- Open Access
- 17 February 2022
- Published by Oxford University Press (OUP) in Protein Engineering, Design and Selection
- Vol. 35
The stability and dynamics of computationally designed proteins
Protein stability, dynamics and function are intricately linked. Accordingly, protein designers leverage dynamics in their designs and gain insight to their successes and failures by analyzing their proteins’ dynamics. Molecular dynamics (MD) simulations are a powerful computational tool for quantifying both local and global protein dynamics. This review highlights studies where MD simulations were applied to characterize the stability and dynamics of designed proteins and where dynamics were incorporated into computational protein design. First, we discuss the structural basis underlying the extreme stability and thermostability frequently observed in computationally designed proteins. Next, we discuss examples of designed proteins, where dynamics were not explicitly accounted for in the design process, whose coordinated motions or active site dynamics, as observed by MD simulation, enhanced or detracted from their function. Many protein functions depend on sizeable or subtle conformational changes, so we finally discuss the computational design of proteins to perform a specific function that requires consideration of motion by multi-state design.
- 17 February 2022
- Published by Oxford University Press (OUP) in Protein Engineering, Design and Selection
- Vol. 35
Open AccessThe stability and dynamics of computationally designed proteins
Protein stability, dynamics and function are intricately linked. Accordingly, protein designers leverage dynamics in their designs and gain insight to their successes and failures by analyzing their proteins’ dynamics. Molecular dynamics (MD) simulations are a powerful computational tool for quantifying both local and global protein dynamics. This review highlights studies where MD simulations were applied to characterize the stability and dynamics of designed proteins and where dynamics were incorporated into computational protein design. First, we discuss the structural basis underlying the extreme stability and thermostability frequently observed in computationally designed proteins. Next, we discuss examples of designed proteins, where dynamics were not explicitly accounted for in the design process, whose coordinated motions or active site dynamics, as observed by MD simulation, enhanced or detracted from their function. Many protein functions depend on sizeable or subtle conformational changes, so we finally discuss the computational design of proteins to perform a specific function that requires consideration of motion by multi-state design.
- Open Access
- 5 November 2021
- Published by Wiley in Journal of Computational Chemistry
- Vol. 43 (3) , 197-205
Thermostabilization mechanisms in thermophilic versus mesophilic three‐helix bundle proteins
The engineered three‐helix bundle, UVF, is thermostabilized entropically due to heightened, native‐state dynamics. However, it is unclear whether this thermostabilization strategy is observed in natural proteins from thermophiles. We performed all‐atom, explicit solvent molecular dynamics simulations of two three‐helix bundles from thermophilic H. butylicus (2lvsN and 2lvsC) and compared their dynamics to a mesophilic three‐helix bundle, the Engrailed homeodomain (EnHD). Like UVF, 2lvsC had heightened native dynamics, which it maintained without unfolding at 100°C. Shortening and rigidification of loops in 2lvsN and 2lvsC and increased surface hydrogen bonds in 2lvsN were observed, as is common in thermophilic proteins. A buried disulfide and salt bridge in 2lvsN and 2lvsC, respectively, provided some stabilization, and addition of a homologous disulfide bond in EnHD slowed unfolding. The transferability and commonality of stabilization strategies among members of the three‐helix bundle fold suggest that these strategies may be general and deployable in designing thermostable proteins.
- 5 November 2021
- Published by Wiley in Journal of Computational Chemistry
- Vol. 43 (3) , 197-205
Open AccessThermostabilization mechanisms in thermophilic versus mesophilic three‐helix bundle proteins
The engineered three‐helix bundle, UVF, is thermostabilized entropically due to heightened, native‐state dynamics. However, it is unclear whether this thermostabilization strategy is observed in natural proteins from thermophiles. We performed all‐atom, explicit solvent molecular dynamics simulations of two three‐helix bundles from thermophilic H. butylicus (2lvsN and 2lvsC) and compared their dynamics to a mesophilic three‐helix bundle, the Engrailed homeodomain (EnHD). Like UVF, 2lvsC had heightened native dynamics, which it maintained without unfolding at 100°C. Shortening and rigidification of loops in 2lvsN and 2lvsC and increased surface hydrogen bonds in 2lvsN were observed, as is common in thermophilic proteins. A buried disulfide and salt bridge in 2lvsN and 2lvsC, respectively, provided some stabilization, and addition of a homologous disulfide bond in EnHD slowed unfolding. The transferability and commonality of stabilization strategies among members of the three‐helix bundle fold suggest that these strategies may be general and deployable in designing thermostable proteins.
- Open Access
- 1 July 2019
- Published by Oxford University Press (OUP) in Protein Engineering, Design and Selection
- Vol. 32 (7) , 317-329
Molecular dynamics simulations suggest stabilizing mutations in a de novo designed α/β protein
Designing functional proteins that can withstand extreme heat is beneficial for industrial and protein therapeutic applications. Thus, elucidating the atomic-level determinants of thermostability is a major interest for rational protein design. To that end, we compared the structure and dynamics of a set of previously designed, thermostable proteins based on the activation domain of human procarboxypeptidase A2 (AYEwt). The mutations in these designed proteins were intended to increase hydrophobic core packing and inter-secondary-structure interactions. To evaluate whether these design strategies were successfully deployed, we performed all-atom, explicit-solvent molecular dynamics (MD) simulations of AYEwt and three designed variants at both 25 and 100°C. Our MD simulations agreed with the relative experimental stabilities of the designs based on their secondary structure content, Cα root-mean-square deviation/fluctuation, and buried-residue solvent accessible surface area. Using a contact analysis, we found that the designs stabilize inter-secondary structure interactions and buried hydrophobic surface area, as intended. Based on our analysis, we designed three additional variants to test the role of helix stabilization, core packing, and a Phe → Met mutation on thermostability. We performed the additional MD simulations and analysis on these variants, and these data supported our predictions.
- 1 July 2019
- Published by Oxford University Press (OUP) in Protein Engineering, Design and Selection
- Vol. 32 (7) , 317-329
Open AccessMolecular dynamics simulations suggest stabilizing mutations in a de novo designed α/β protein
Designing functional proteins that can withstand extreme heat is beneficial for industrial and protein therapeutic applications. Thus, elucidating the atomic-level determinants of thermostability is a major interest for rational protein design. To that end, we compared the structure and dynamics of a set of previously designed, thermostable proteins based on the activation domain of human procarboxypeptidase A2 (AYEwt). The mutations in these designed proteins were intended to increase hydrophobic core packing and inter-secondary-structure interactions. To evaluate whether these design strategies were successfully deployed, we performed all-atom, explicit-solvent molecular dynamics (MD) simulations of AYEwt and three designed variants at both 25 and 100°C. Our MD simulations agreed with the relative experimental stabilities of the designs based on their secondary structure content, Cα root-mean-square deviation/fluctuation, and buried-residue solvent accessible surface area. Using a contact analysis, we found that the designs stabilize inter-secondary structure interactions and buried hydrophobic surface area, as intended. Based on our analysis, we designed three additional variants to test the role of helix stabilization, core packing, and a Phe → Met mutation on thermostability. We performed the additional MD simulations and analysis on these variants, and these data supported our predictions.
- Open Access
- 1 February 2019
- Published by Elsevier in Biophysical Journal
- Vol. 116 (4) , 621-632
A Dynamic Hydrophobic Core and Surface Salt Bridges Thermostabilize a Designed Three-Helix Bundle
- 1 February 2019
- Published by Elsevier in Biophysical Journal
- Vol. 116 (4) , 621-632
Open AccessA Dynamic Hydrophobic Core and Surface Salt Bridges Thermostabilize a Designed Three-Helix Bundle