Department of Biological Sciences

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1922

Browse

Filters

2024 - 20262

Settings

Author: search.filters.author.Basu, SushmitaSubject: search.filters.subject.Disorder prediction

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Taxonomy-specific assessment of intrinsic disorder predictions at residue and region levels in higher eukaryotes, protists, archaea, bacteria and viruses
    (Elsevier, 2024-12) Basu, Sushmita
    Intrinsic disorder predictors were evaluated in several studies including the two large CAID experiments. However, these studies are biased towards eukaryotic proteins and focus primarily on the residue-level predictions. We provide first-of-its-kind assessment that comprehensively covers the taxonomy and evaluates predictions at the residue and disordered region levels. We curate a benchmark dataset that uniformly covers eukaryotic, archaeal, bacterial, and viral proteins. We find that predictive performance differs substantially across taxonomy, where viruses are predicted most accurately, followed by protists and higher eukaryotes, while bacterial and archaeal proteins suffer lower levels of accuracy. These trends are consistent across predictors. We also find that current tools, except for flDPnn, struggle with reproducing native distributions of the numbers and sizes of the disordered regions. Moreover, analysis of two variants of disorder predictions derived from the AlphaFold2 predicted structures reveals that they produce accurate residue-level propensities for archaea, bacteria and protists. However, they underperform for higher eukaryotes and generally struggle to accurately identify disordered regions. Our results motivate development of new predictors that target bacteria and archaea and which produce accurate results at both residue and region levels. We also stress the need to include the region-level assessments in future assessments.
  • No Thumbnail Available
    Item
    flDPnn3: Fast and accurate prediction of intrinsic disorder in protein sequences
    (Elsevier, 2026-01) Basu, Sushmita
    flDPnn3 provides fast and highly accurate predictions of intrinsic disorder. Compared to its earlier versions, it uses a more sophisticated sequence-derived profile as input, covering a modern protein language model and additional predicted disorder functions, while maintaining a similarly small computational footprint. flDPnn3 and over 70 other disorder predictors were independently evaluated on the Disorder-NOX dataset by assessors in CAID3 (3rd Critical Assessment of protein Intrinsic Disorder prediction). A side-by-side comparison in CAID3, including low-sequence-similarity subsets of the CAID3 test data, reveals that our method matches the predictive quality of the best disorder predictors. The runtime analysis shows that flDPnn3 produces results between 3 and 8 times faster than similarly accurate disorder predictors and can be used to produce predictions at the whole-proteome scale. Additionally, flDPnn3 achieves 100% coverage by predicting all proteins, while some other accurate tools fail to predict some proteins. The CAID3 results also demonstrate that flDPnn3 is significantly more accurate than its previous versions, flDPnn and flDPnn2, which were among the top-ranked methods in CAID1 and CAID2, respectively. The flDPnn3’s web server supports batch predictions, provides interactive visualization of results, offers a tutorial page,