Varun Ullanat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Varun Ullanat has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Shruthi Viswanath
National Centre for Biological Sciences, Tata Institute of Fundamental Research, Bangalore, Karnataka, India 560065
2 shared publications - Abhinav Gupta
Sanofi
1 shared publication - Bonnie Berger
Massachusetts Institute of Technology
1 shared publication - Bryan D. Bryson
Department of Biological Engineering, Massachusetts Institute of Technology
1 shared publication - Kartik Majila
National Centre for Biological Sciences, TATA Institute of Fundamental Research, Bangalore, INDIA
1 shared publication Nikhil Kasukurthi
National Center for Biological Sciences, Tata Institute of Fundamental Research, Bangalore, India
1 shared publication
Latest Publications
- Open Access
Breadth over Depth: Predictor-Agnostic Consensus for Improved Antibody--Antigen Structure Prediction
Antibody–antigen structure prediction commonly relies on sampling a single co-folding predictor deeply and selecting its highest-confidence output using model-specific confidence scores. We introduce AbPoolRank, a predictor-agnostic structural selector that ranks mixed pools using cross-pose agreement, within-source reproducibility and interface geometry, without native confidence, predictor identities or predictor-specific parameters. On 103 cluster-disjoint, post-2021 antibody–antigen complexes from SAbDab2, three structures each from Boltz-2, Promera, Protenix-v2, ESMFold2-Fast and OpenDDE form a 15-structure pool that reaches 58.0% medium-or-better Success@1 (DockQ ≥ 0.49), exceeding confidence-based selection from every individual predictor sampled 100 times (26–52%). Existing ranking methods did not rescue deep single-predictor sampling or surpass our selector on mixed pools, with no method exceeding 51.5% on 100 structures from one co-folder and AbPoolRank matching the strongest single-structure methods while significantly outperforming consensus methods. AbPoolRank trained without one predictor lost at most 3.0 percentage points, and the frozen model accepted full MSA-conditioned ESMFold2, a sixth predictor absent from method development, without retraining or loss of accuracy. Diversification also improved the accuracy–compute frontier, with the 15-structure pool using 1.8-fold less aggregate GPU time than the most accurate single-predictor setting in our compute benchmark and 3.3-fold less than sampling that predictor 100 times. Together, these results show that shallow sampling across complementary co-folders, coupled with a confidence-free selector, provides an accurate and computationally efficient inference strategy for antibody–antigen structure prediction.
Open AccessBreadth over Depth: Predictor-Agnostic Consensus for Improved Antibody--Antigen Structure Prediction
Antibody–antigen structure prediction commonly relies on sampling a single co-folding predictor deeply and selecting its highest-confidence output using model-specific confidence scores. We introduce AbPoolRank, a predictor-agnostic structural selector that ranks mixed pools using cross-pose agreement, within-source reproducibility and interface geometry, without native confidence, predictor identities or predictor-specific parameters. On 103 cluster-disjoint, post-2021 antibody–antigen complexes from SAbDab2, three structures each from Boltz-2, Promera, Protenix-v2, ESMFold2-Fast and OpenDDE form a 15-structure pool that reaches 58.0% medium-or-better Success@1 (DockQ ≥ 0.49), exceeding confidence-based selection from every individual predictor sampled 100 times (26–52%). Existing ranking methods did not rescue deep single-predictor sampling or surpass our selector on mixed pools, with no method exceeding 51.5% on 100 structures from one co-folder and AbPoolRank matching the strongest single-structure methods while significantly outperforming consensus methods. AbPoolRank trained without one predictor lost at most 3.0 percentage points, and the frozen model accepted full MSA-conditioned ESMFold2, a sixth predictor absent from method development, without retraining or loss of accuracy. Diversification also improved the accuracy–compute frontier, with the 15-structure pool using 1.8-fold less aggregate GPU time than the most accurate single-predictor setting in our compute benchmark and 3.3-fold less than sampling that predictor 100 times. Together, these results show that shallow sampling across complementary co-folders, coupled with a confidence-free selector, provides an accurate and computationally efficient inference strategy for antibody–antigen structure prediction.
- Open Access
Disobind: a sequence-based, partner-dependent contact map and interface residue predictor for intrinsically disordered regions
Summary: Intrinsically disordered proteins or regions (IDPs/IDRs) adopt diverse binding modes with different partners, from coupled-folding-and-binding, to fuzzy binding, to fully-disordered binding. Characterizing IDR interfaces is challenging experimentally and computationally. The state-of-the-art AlphaFold-multimer and AlphaFold3 can be used to predict IDR binding sites, although they are less accurate at their benchmarked confidence cutoffs. Here, we developed Disobind, a deep-learning method that predicts inter-protein contact maps and interface residues for an IDR and its partner, given their sequences. It uses sequence embeddings from the ProtT5 protein language model. Disobind outperforms state-of-the-art interface predictors for IDRs. It also outperforms AlphaFold-multimer and AlphaFold3 at multiple confidence cutoffs. Combining Disobind and AlphaFold-multimer predictions further improves the performance. In contrast to current methods, Disobind considers the context of the binding partner and does not depend on structures and multiple sequence alignments. Its predictions can be used to localize IDRs in large assemblies and characterize IDR-mediated interactions. A record of this paper’s transparent peer review process is included in the supplemental information.
Open AccessDisobind: a sequence-based, partner-dependent contact map and interface residue predictor for intrinsically disordered regions
Summary: Intrinsically disordered proteins or regions (IDPs/IDRs) adopt diverse binding modes with different partners, from coupled-folding-and-binding, to fuzzy binding, to fully-disordered binding. Characterizing IDR interfaces is challenging experimentally and computationally. The state-of-the-art AlphaFold-multimer and AlphaFold3 can be used to predict IDR binding sites, although they are less accurate at their benchmarked confidence cutoffs. Here, we developed Disobind, a deep-learning method that predicts inter-protein contact maps and interface residues for an IDR and its partner, given their sequences. It uses sequence embeddings from the ProtT5 protein language model. Disobind outperforms state-of-the-art interface predictors for IDRs. It also outperforms AlphaFold-multimer and AlphaFold3 at multiple confidence cutoffs. Combining Disobind and AlphaFold-multimer predictions further improves the performance. In contrast to current methods, Disobind considers the context of the binding partner and does not depend on structures and multiple sequence alignments. Its predictions can be used to localize IDRs in large assemblies and characterize IDR-mediated interactions. A record of this paper’s transparent peer review process is included in the supplemental information.
- Open Access
PrISM: Precision for Integrative Structural Models
Motivation: A single precision value is currently reported for an integrative model. However, precision may vary for different regions of an integrative model owing to varying amounts of input information. Results: We develop PrISM (Precision for Integrative Structural Models), to efficiently identify high and low-precision regions for integrative models. Availability: PrISM is written in Python and available under the GNU General Public License v3.0 at https://github.com/isblab/prism ; benchmark data used in this paper is available at doi:10.5281/zenodo.6241200. Contact: shruthiv@ncbs.res.in Supplementary information: Supplementary data are available at Bioinformatics online.
Open AccessPrISM: Precision for Integrative Structural Models
Motivation: A single precision value is currently reported for an integrative model. However, precision may vary for different regions of an integrative model owing to varying amounts of input information. Results: We develop PrISM (Precision for Integrative Structural Models), to efficiently identify high and low-precision regions for integrative models. Availability: PrISM is written in Python and available under the GNU General Public License v3.0 at https://github.com/isblab/prism ; benchmark data used in this paper is available at doi:10.5281/zenodo.6241200. Contact: shruthiv@ncbs.res.in Supplementary information: Supplementary data are available at Bioinformatics online.