Generative Adversarial Learning of Protein Tertiary Structures

• Taseef Rahman, Yuanqi Du, Liang Zhao, and Amarda Shehu. This work has appeared in Molecules 2021. Data and selected trained models are publicly available through IEEE Dataport (ieee-dataport.org) under DOI 10.21227/m8sa-cz14 here.

ROMEO: A Plug-and-play Software Platform of Robotics-inspired Algorithms for Modeling Biomolecular Structures and Motions

• Kevin Molloy, Erion Paku, and Amarda Shehu. The source code can be downloaded at: here. It operates over Rosetta, which one needs to download from the Baker lab under an academic license.

SIfTER: A Structure-guided Memetic, Cellular, and Multiscale Evolutionary Algorithm for Mapping Protein Conformation Spaces

• This work has appeared in: Rudy Clausen, Buyong Ma, Ruth Nussinov, and Amarda Shehu. "Mapping the Conformation Space of Wildtype and Mutant H-Ras with a Memetic, Cellular, and Multiscale Evolutionary Algorithm." PLoS Computational Biology, 2015.
  
  An executable for linux is available here. It operates over Rosetta, which one needs to download from the Baker lab under an academic license, and over BBQ, which one needs to download, as well, per the instructions in the README file.

EFC-FCBF: Method for Feature Construction and Selection for Improved Recognition of Antimicrobial Peptides

• This work is currently under review: Daniel Veltri, Uday Kamath, and Amarda Shehu. "Improving Recognition of Antimicrobial Peptides and Target Selectivity through Machine Learning and Genetic Programming." IEEE/ACM Trans Comp Biol and Bioinf (TCBB), 2015 (under review). A preliminary version of this work has appeared in: Daniel Veltri, Uday Kamath, and Amarda Shehu. "Improved Prediction of Antimicrobial Peptides Through Distal Sequence-based Features." IEEE Intl Conf on Bioinf and Biomed (BIBM), Belfast, UK, 2014, pg. 371-378.
  
  A summary of the work is available here.
  
  Code, documentation, and data can be obtained here.

HEA-PSP: A Hybrid Evolutionary Search Framework with Various Crossover Implementations for Ab-initio Protein Structre Prediction

• This work has appeared in: Brian Olson, Kenneth A. De Jong, and Amarda Shehu. "Off-Lattice Protein Structure Prediction with Homologous Crossover." GECCO 2013, pages 287-294, Amsterdam, Netherlands.
  
  A summary of the work is available here.
  
  An executable for linux is available here. It operates over Rosetta, which one needs to download from the Baker lab under an academic license.
  
  We expect to release soon an open-source software platform that includes many other EAs, HEAs, GAs, and multi-objective HEAs we have developed for the ab-initio structure prediction problem. Stay tuned.

EFFECT: Framework for Automated Construction and Extraction of Features for Classification of Biological Sequences

• This work is in press: Uday Kamath, Kenneth A. De Jong, and Amarda Shehu. "Effective Automated Feature Construction and Selectionfor Classification of Biological Sequences." PLoS One, 2014 (in press).
  
  A summary of the work will be posted soon.
  
  Code, documentation, and data can be obtained here.

Computing Motions of Small- to Medium-Size Proteins:

• This work appears in various publications by Kevin Molloy and Amarda Shehu during 2012-2013.
  
  A summary of the work can be found here.
  
  An executable that allows application of our robotics-inspired framework for sampling conformational pathways connecting diverse functional states in small- to medium-size proteins will be posted soon for download.

Mapping Energy Minima in the Protein Energy Surface:

• This work appears in various publications by Brian Olson and Amarda Shehu during 2011-2013.
  
  A summary of the work can be found here.
  
  An executable that allows application of various of our evolutionary search algorithms for sampling low-energy minima in the protein conformational space will be posted soon for download.

Binary Response Models for Recognition of Antimicrobial Peptides:

• This work appears in: Elena Randou, Daniel Veltri and Amarda Shehu. "Binrary Response Models for Recognition of Antimicrobial Peptides." ACM Bioinf and Comp Biol (BCB), 2013.
  
  A summary of the work can be found here.
  
  The AMP-PASS web server can be found here.

Statistical Model Building for Antimicrobial Peptide Recognition:

• This work appears in: Elena Randou, Daniel Veltri and Amarda Shehu. "Systematic Analysis of Global Features and Model Building for Recognition of Antimicrobial Peptides." IEEE Intl Conf on Computational Advances in Bio and Medical Sciences (ICCABS), 2013.
  
  A summary of the work can be found here.
  
  The web server can be found here.

Novel features for Antimicrobial Peptide Recognition:

• This work appears in: Daniel Veltri and Amarda Shehu. "Physicochemical Determinants of Antimicrobial Activity." Intl Conf on Bioinformatics and Computational Biology (BICoB), 2013.
  
  A summary of the work can be found here.
  
  A physico-chemical profile explorer can be found on this web server.

Spatial EA Framework for Parallel Machine Learning:

• This work appears in: Uday Kamath, Johan Kaers, Amarda Shehu, and Kenneth A. De Jong. "A Spatial EA Framework for Parallelizing Machine Learning Methods." Intl Conf on Parallel Problem Solving From Nature (PPSN), LNCS vol. 7491, pg. 206-215, Taormina, Italy, 2012.
  
  A summary of the work can be found here.
  
  Code and implementation details can be obtained here.

An Evolutionary Algorithm For SVM Kernel Optimization:

• This work appears in: Uday Kamath, Amarda Shehu, and Kenneth A. De Jong. A Two-Stage Evolutionary Approach for Effective Classification of Hypersensitive DNA Sequences, J Bioinf and Comp Biol 2011, 9(3): 399-413.
  
  A summary of the work can be found here.
  
  Code and implementation details can be obtained here.

An Evolutionary Algorithm For Feature Generation from Sequence Data:

• This work appears in: Uday Kamath, Jack Compton, Rezarta Islamaj Dogan, Kenneth A. De Jong, and Amarda Shehu, An Evolutionary Algorithm Approach for Feature Generation from Sequence Data and its Application to DNA Splice-Site Prediction, Trans Comp Biol and Bioinf 2012, 9(5):1387-1398.
  
  A summary of the work can be found here.
  
  Code and implementation details can be obtained here.