Main Page

Major News Our disorder predictors, flDPnn and flDPnn2, secured top results in the CAID1 experiment (DisProt dataset; results were published in Nature Methods) and the CAID2 experiment (Disorder-NOX dataset; results were published in Proteins journal).
These accoplishements were highlighted in a commentary article in Nature Methods and press release.

Our (un)structural bioinformatics lab focuses on:

  • Structure and function prediction and modeling of proteins and small RNAs
  • Discovery and characterization of sequence-structure/intrinsic disorder-function relationships in proteins
  • Binding of small ligands (including drugs), proteins, RNAs and DNA to proteins
  • Prediction and functional characterization of intrinsic disorder in proteins
  • Target selection methods for structural genomics

Our overarching aim is to improve understanding of life at the molecular level by discovering relations between sequences, structures and functions of biological macromolecules. We design and use in-silico approaches to search for patterns, generate accurate high-throughput predictive models, and interpret information encoded in proteins and small RNAs. Our research spans a wide spectrum of scales, from individual molecules to projects that span thousands of proteomes/genomes, and relies on cutting-edge advances in machine learning and data science.

Our recently published models and databases include:

The most exciting phrase to hear in science, one that heralds the most discoveries, is not Eureka! but That's funny…”