Nikša Praljak

praljak_selfie.jpg

Google Scholar: link

X (formerly Twitter): link

University of Chicago: link

LinkedIn: link

About Me

Welcome to my site! I’m Nikša Praljak, a PhD student in Biophysics at the University of Chicago, where I develop and apply deep generative models for synthetic protein design, leveraging high-throughput next-gen sequencing assays (news on my PhD work). I’m fortunate to be co-advised by Professors Rama Ranganathan and Andrew Ferguson.

Before my doctoral studies, I earned dual degrees in Honors Physics and Mathematics from CSU (2016-2020). During this time, I was honored to receive the NSF Graduate Research Fellowship and was named COSHP Valedictorian. My research journey began in Michael Hinczewski’s lab, where I explored the intersection of Biophysics and computational biology, collaborating with the Umut Gurkan lab on projects related to sickle cell adhesion.

I’m passionate about research at the crossroads of machine learning, evolution, and synthetic biology. I created this site to share my ongoing work and future projects. Given my love for teaching, I’ll also be posting educational blogs on machine learning and computational biology.

Outside of research, I enjoy cooking, reading, sports, and working out, but most importantly, I cherish time spent with family, especially during the holidays.

Feel free to explore and stay up to date with my academic journey through my Google Scholar profile.

news

Aug 09, 2024 A perspective article on our innovative approach to designing synthetic SH3 domains using Variational Autoencoders (VAEs) was published in Cell Systems. The article summarizes our key findings and discusses future directions for this research in protein design and understanding of orthology (see link).
Aug 07, 2024 Participated and interviewed in the Argonne National Laboratory GPU Hackathon, advancing high-performance computing skills (see link).
Feb 27, 2024 Launched research project: “Discovering the Design Rules Linking Protein Sequence to Function”. This study utilizes and develops advanced multi-modal generative AI models to map the relationship between protein sequences and their functions, aiming to enable the design of novel proteins with desired properties (see link).
Jan 12, 2024 Our research on ProtWave-VAE featured in ACS Synthetic Biology, offering a comprehensive summary of our novel protein design methodology and its potential impact on synthetic biology (link).
Aug 16, 2020 Awarded the prestigious NSF Graduate Research Fellowship, supporting ongoing doctoral studies in Biophysics (see link)

selected publications

  1. Cell Syst.
    Deep-learning-based design of synthetic orthologs of SH3 signaling domains
    Xinran Lian, Nikša Praljak, Subu K Subramanian, and 3 more authors
    Cell Systems, 2024
  2. ACS Synth. Biol.
    ProtWave-VAE: Integrating autoregressive sampling with latent-based inference for data-driven protein design
    Niksa Praljak, Xinran Lian, Rama Ranganathan, and 1 more author
    ACS synthetic biology, 2023
  3. PLoS Comput. Biol.
    Integrating deep learning with microfluidics for biophysical classification of sickle red blood cells adhered to laminin
    Niksa Praljak, Shamreen Iram, Utku Goreke, and 4 more authors
    PLOS Computational Biology, 2021