references.bib

@book{Aitchison1986,
  author    = {Aitchison, John},
  title     = {The Statistical Analysis of Compositional Data},
  year      = {1986},
  publisher = {Chapman and Hall},
  address   = {London},
  doi       = {10.1007/978-94-009-4109-0}
}

@book{PawlowskyGlahn2011,
  editor    = {Pawlowsky-Glahn, Vera and Buccianti, Antonella},
  title     = {Compositional Data Analysis: Theory and Applications},
  year      = {2011},
  publisher = {Wiley},
  address   = {Chichester}
}

@article{Needleman1970,
  author  = {Needleman, Saul B. and Wunsch, Christian D.},
  title   = {A General Method Applicable to the Search for Similarities in the Amino Acid Sequence of Two Proteins},
  journal = {Journal of Molecular Biology},
  year    = {1970},
  volume  = {48},
  number  = {3},
  pages   = {443--453},
  doi     = {10.1016/0022-2836(70)90057-4}
}

@article{Smith1981,
  author  = {Smith, Temple F. and Waterman, Michael S.},
  title   = {Identification of Common Molecular Subsequences},
  journal = {Journal of Molecular Biology},
  year    = {1981},
  volume  = {147},
  number  = {1},
  pages   = {195--197},
  doi     = {10.1016/0022-2836(81)90087-5}
}

@article{Henikoff1992,
  author  = {Henikoff, Steven and Henikoff, Jorja G.},
  title   = {Amino Acid Substitution Matrices from Protein Blocks},
  journal = {Proceedings of the National Academy of Sciences},
  year    = {1992},
  volume  = {89},
  number  = {22},
  pages   = {10915--10919},
  doi     = {10.1073/pnas.89.22.10915}
}

@article{Atkinson2009,
  author  = {Atkinson, Hilary J. and Morris, John H. and Ferrin, Thomas E. and Babbitt, Patricia C.},
  title   = {Using Sequence Similarity Networks for Visualization of Relationships Across Diverse Protein Superfamilies},
  journal = {PLoS ONE},
  year    = {2009},
  volume  = {4},
  number  = {2},
  pages   = {e4345},
  doi     = {10.1371/journal.pone.0004345}
}

@article{Gerlt2015,
  author  = {Gerlt, John A. and Bouvier, Jonathan T. and Davidson, D. B. and Imker, Heidi J. and Sadkhin, Boris and Slater, David R. and Whalen, Kristen L.},
  title   = {Enzyme Function Initiative-Enzyme Similarity Tool ({EFI}-{EST}): A Web Tool for Generating Protein Sequence Similarity Networks},
  journal = {Biochimica et Biophysica Acta},
  year    = {2015},
  volume  = {1854},
  number  = {8},
  pages   = {1019--1037},
  doi     = {10.1016/j.bbapap.2015.04.015}
}

@article{Oberg2023,
  author  = {Oberg, Nolan and Zallot, Remi and Gerlt, John A.},
  title   = {{EFI}-{EST}, {EFI}-{GNT}, and {EFI}-{CGFP}: Enzyme Function Initiative Web Resource for Genomic Enzymology Tools},
  journal = {Biochemistry},
  year    = {2023},
  volume  = {62},
  number  = {15},
  pages   = {2299--2310},
  doi     = {10.1021/acs.biochem.3c00117}
}

@article{Dauparas2022,
  author  = {Dauparas, Justas and Anishchenko, Ivan and Bennett, Nathaniel and Bai, Hua and Ragotte, Robert J. and Milles, Lukas F. and Wicky, Basile I. M. and Courbet, Alexis and de Haas, Renzo J. and Bethel, Neville and Leung, Phoebe J. Y. and Huddy, Thomas F. and Strauch, Eva-Maria and Maguire, James B. and Warshaviak, David and Baker, David},
  title   = {Robust Deep Learning-Based Protein Sequence Design Using {ProteinMPNN}},
  journal = {Science},
  year    = {2022},
  volume  = {378},
  number  = {6615},
  pages   = {49--56},
  doi     = {10.1126/science.add2187}
}

@misc{ProteinMPNNGitHub,
  author       = {Dauparas, Justas and others},
  title        = {{ProteinMPNN} Official Implementation},
  year         = {2022},
  howpublished = {\url{https://github.com/dauparas/ProteinMPNN}},
  note         = {Accessed 2026-03-16}
}

@incollection{Dayhoff1978,
  author    = {Dayhoff, Margaret O. and Schwartz, Robert M. and Orcutt, Barbara C.},
  title     = {A Model of Evolutionary Change in Proteins},
  booktitle = {Atlas of Protein Sequence and Structure},
  year      = {1978},
  editor    = {Dayhoff, Margaret O.},
  publisher = {National Biomedical Research Foundation},
  address   = {Washington, DC},
  volume    = {5},
  suppl     = {3},
  pages     = {345--352}
}

@article{Karlin1990,
  author  = {Karlin, Samuel and Altschul, Stephen F.},
  title   = {Methods for Assessing the Statistical Significance of Molecular Sequence Features by Using General Scoring Schemes},
  journal = {Proceedings of the National Academy of Sciences},
  year    = {1990},
  volume  = {87},
  number  = {6},
  pages   = {2264--2268},
  doi     = {10.1073/pnas.87.6.2264}
}

@article{Altschul1997,
  author  = {Altschul, Stephen F. and Madden, Thomas L. and Sch{\"a}ffer, Alejandro A. and Zhang, Jinghui and Zhang, Zheng and Miller, Webb and Lipman, David J.},
  title   = {Gapped {BLAST} and {PSI}-{BLAST}: A New Generation of Protein Database Search Programs},
  journal = {Nucleic Acids Research},
  year    = {1997},
  volume  = {25},
  number  = {17},
  pages   = {3389--3402},
  doi     = {10.1093/nar/25.17.3389}
}

@article{Feng1987,
  author  = {Feng, Da-Fei and Doolittle, Russell F.},
  title   = {Progressive Sequence Alignment as a Prerequisite to Correct Phylogenetic Trees},
  journal = {Journal of Molecular Evolution},
  year    = {1987},
  volume  = {25},
  number  = {4},
  pages   = {351--360},
  doi     = {10.1007/BF02603120}
}

@article{Brenner1998,
  author  = {Brenner, Steven E. and Chothia, Cyrus and Hubbard, Tim J. P.},
  title   = {Assessing Sequence Comparison Methods with Reliable Structurally Identified Distant Evolutionary Relationships},
  journal = {Proceedings of the National Academy of Sciences},
  year    = {1998},
  volume  = {95},
  number  = {11},
  pages   = {6073--6078},
  doi     = {10.1073/pnas.95.11.6073}
}

@article{Edgar2004,
  author  = {Edgar, Robert C.},
  title   = {{MUSCLE}: Multiple Sequence Alignment with High Accuracy and High Throughput},
  journal = {Nucleic Acids Research},
  year    = {2004},
  volume  = {32},
  number  = {5},
  pages   = {1792--1797},
  doi     = {10.1093/nar/gkh340}
}

@inproceedings{DeSilva2004,
  author    = {de Silva, Vin and Tenenbaum, Joshua B.},
  title     = {Sparse Multidimensional Scaling Using Landmark Points},
  booktitle = {Advances in Neural Information Processing Systems 16},
  year      = {2004},
  publisher = {MIT Press},
  pages     = {1197--1204},
  doi       = {10.1162/089976604773717621}
}

@book{Legendre2012,
  author    = {Legendre, Pierre and Legendre, Louis},
  title     = {Numerical Ecology},
  edition   = {3},
  year      = {2012},
  publisher = {Elsevier},
  address   = {Amsterdam}
}

@book{Mount2004,
  author    = {Mount, David W.},
  title     = {Bioinformatics: Sequence and Genome Analysis},
  edition   = {2},
  year      = {2004},
  publisher = {Cold Spring Harbor Laboratory Press},
  address   = {Cold Spring Harbor, NY}
}