Biology subjects

Haspel, N.

Publications and source records attributed to Haspel, N..

7 recordsLinked to original sources

bioRxiv2026

Handshake: Partner-Specific Protein-Protein Binding Site Prediction at Scale Using ProstT5 and Cross-Chain Attention

Partner-specific protein-protein binding site prediction, identifying which residues of a protein form the interface when bound to a specific partner, remains a challenging task with significant implications for drug discovery and understanding of protein structure and function. Existing computational methods are limited by small training datasets, inconsistent redundancy filtering, and reliance on three-dimensional structural information at test time. Here we present a sequence-only, partner-specific protein-protein interface predictor called HandShake. It combines ProstT5, a protein language model pre-trained on structural data, with Low-Rank Adaptation (LoRA), a cross-chain attention mechanism and a contact supervision head. Our method can detect both binding interfaces and pairwise contact matrices. We trained our model on very large datasets of non-redundant protein-protein pairs derived from the PPInterface dataset, the most comprehensive structural protein-protein database to date, and evaluated it on systematically filtered benchmarks at four redundancy thresholds (30%-90% sequence identity). We demonstrate that sequence redundancy inflates reported AUROC by up to 0.079 and MCC by up to 0.145 on identical models, representing a substantial methodological confound in the field. Even at 30% redundancy threshold, our results (AUROC=0.811, MCC=0.367, F1=0.45) exceed the best published sequence-only result on this convention. Our method also achieves comparable performance to existing partner-specific methods that use explicit structural information. The comprehensive training and evaluation dataset, in addition to the systematic redundancy inflation, can help gain insight into protein-protein interactions and the abilities and limitations of current detection methods. Data availabilityThe code and data can be found at http://github.com/nurith/Handshake. Author summaryUnderstanding which residues of a protein make contact with a specific protein partner is fundamental for designing drugs and understanding cellular processes, but predicting these interfaces remains challenging. We developed a deep learning method that takes only the amino acid sequences of two proteins and predicts, for each residue, whether it lies on their binding interface. The method combines ProstT5, a protein language model trained to translate between sequence and structure, with a cross-chain attention mechanism that lets each proteins residues attend to its partner. We train and evaluate on up to 32,503 non-redundant protein pairs across four sequence redundancy thresholds. To the best of our knowledge, this is by far the largest dataset trained and tested for this specific task. Our key methodological finding: sequence redundancy in evaluation benchmarks inflates reported metrics by up to 0.079 AUROC and 0.145 MCC on identical models when measured internally on PPInterface. Inference experiments on four independent benchmarks show that this internal inflation does not transfer cleanly to externally-curated datasets, where switching from 30%-trained to 90%-trained models changes performance only modestly. At 30% filtering, our method achieves AUROC values from 0.784 to 0.828 across five datasets, confirming genuine generalization. Through systematic negative controls and comparisons with the ESM-2 family of language models at matched parameter counts, we show that explicit structural pre-training, not just model scale, is what enables sequence-only binding site prediction to work.

bioinformatics↗

bioRxiv2026

How Functional Variants Reconfigure the Rac2 Conformational Landscape

Rac2, a member of the Rho family of small GTPases, is a fundamental regulator of essential cellular processes. Pathogenic substitutions near and within the Switch II region, specifically D57N and E62K, have been implicated in oncogenesis and immunodeficiency. Despite their proximity, D57N is characterized as a loss-of-function mutation, while E62K is a constitutively active, gain-of-function mutation. In this study, we addressed several critical questions: (i) the structural basis of their altered cellular functions, (ii) how these variants rearrange the conformational ensemble, and (iii) the subsequent impact on cellular signaling networks. Using molecular dynamics (MD) simulations, we characterized the conformational dynamics of these Rac2 variants in GDP- and GTP-bound states. Our results demonstrate that Rac2D57N predominantly adopts an inactive-like conformation, regardless of the bound nucleotide. GTP binding is insufficient to induce the canonical active state in this mutant. Conversely, Rac2E62K maintains a nucleotide-dependent toggle, appearing inactive when bound to GDP and active when bound to GTP. Additionally, we examined the assembly of these variants with the regulator p50-RhoGAP. In the wild-type complex, GAP binding facilitates a shift toward a near-transition-state ensemble. In stark contrast, both the D57N and E62K complexes remain sequestered in a ground-ON state configuration, effectively trapping the GTPase and hindering GAP-mediated hydrolysis. While both Rac2 mutations result in immune system dysfunction, the underlying mechanisms are opposite: inactive vs. overactive. This work provides a high-resolution, mechanistic framework for understanding how localized perturbations in the switch loops landscape dictate systemic cellular outcomes.

biophysics↗

bioRxiv2021

Characterizing Protein Conformational Spaces using Dimensionality Reduction and Algebraic Topology

Datasets representing the conformational landscapes of protein structures are high dimensional and hence present computational challenges. Efficient and effective dimensionality reduction of these datasets is therefore paramount to our ability to analyze the conformational landscapes of proteins and extract important information regarding protein folding, conformational changes and binding. Representing the structures with fewer attributes that capture the most variance of the data, makes for quicker and precise analysis of these structures. In this work we make use of dimensionality reduction methods for reducing the number of instances and for feature reduction. The reduced dataset that is obtained is then subjected to topological and quantitative analysis. In this step we perform hierarchical clustering to obtain different sets of conformation clusters that may correspond to intermediate structures. The structures represented by these conformations are then analyzed by studying their high dimension topological properties to identify truly distinct conformations and holes in the conformational space that may represent high energy barriers. Our results show that the clusters closely follow known experimental results about intermediate structures, as well as binding and folding events.

bioinformatics↗

bioRxiv2021

FDJD: RNA-Seq Based Fusion Transcript Detection Using Jaccard Distance

Gene fusions events, which are the result of two genes fused together to create a hybrid gene, were first described in cancer cells in the early 1980s. These events are relatively common in many cancers including prostate, lymphoid, soft tissue, and breast. Recent advances in next-generation sequencing (NGS) provide a high volume of genomic data, including cancer genomes. The detection of possible gene fusions requires fast and accurate methods. However, current methods suffer from inefficiency, lack of sufficient accuracy, and a high false-positive rate. We present an RNA-Seq fusion detection method that uses dimensionality reduction and parallel computing to speed up the computation. We convert the RNA categorical space into a compact binary array called binary fingerprints, which enables us to reduce the memory usage and increase efficiency. The search and detection of fusion candidates are done using the Jaccard distance. The detection of candidates is followed by refinement. We benchmarked our fusion prediction accuracy using both simulated and genuine RNA-Seq datasets. Paired-end Illumina RNA-Seq genuine data were obtained from 60 publicly available cancer cell line data sets. The results are compared against the state-of-the-art-methods such as STAR-Fusion, InFusion, and TopHat-Fusion. Our results show that FDJD exhibits superior accuracy compared to popular alternative fusion detection methods. We achieved 90% accuracy on simulated fusion transcript inputs, which is the highest among the compared methods while maintaining comparable run time.

bioinformatics↗

bioRxiv2021

Characterizing Protein Conformational Space Using Robotics-Based Search and Topological Data Analysis

An essential step to understanding how different functionalities of proteins work is to explore their conformational space. However, because of the fleeting nature of conformational changes in proteins, investigating protein conformational spaces is a challenging task to do experimentally. Nonetheless, computational methods have shown to be practical to explore these conformational pathways. In this work, we use Topological Data Analysis (TDA) methods to evaluate our previously introduced algorithm called RRTMC, that uses a combination of Rapidly-exploring Random Trees algorithm and Monte Carlo criteria to explore these pathways. TDA is used to identify the intermediate conformations that are generated the most by RRTMC and examine how close they are to existing known intermediate conformations. We concluded that the intermediate conformations generated by RRTMC are close to existing experimental data and that TDA can be a helpful tool to analyze protein conformation sampling methods.

bioinformatics↗

bioRxiv2021

Integrating Rigidity Analysis into the Exploration of Protein Conformational Pathways using RRT* and MC

To understand how proteins function on a cellular level, it is of paramount importance to understand their structures and dynamics, including the conformational changes they undergo to carry out their function. For the aforementioned reasons, the study of large conformational changes in proteins has been an interest to researchers for years. However, since some proteins experience rapid and transient conformational changes, it is hard to experimentally capture the intermediate structures. Additionally, computational brute force methods are computationally intractable, which makes it impossible to find these pathways which require a search in a high-dimensional, complex space. In our previous work, we implemented a hybrid algorithm that combines Monte-Carlo (MC) sampling and RRT*, a version of the Rapidly Exploring Random Trees (RRT) robotics-based method, to make the conformational exploration more accurate and efficient, and produce smooth conformational pathways. In this work, we integrated the rigidity analysis of proteins into our algorithm to guide the search to explore flexible regions. We demonstrate that rigidity analysis dramatically reduces the run time and accelerates convergence.

bioinformatics↗

bioRxiv2019

Patch-DCA: Improved Protein Interface Prediction by utilizing Structural Information and Clustering DCA scores

Over the past decade there have been impressive advances in determining the 3D structures of protein complexes. However, there are still many complexes with unknown structures, even when the structures of the individual proteins are known. The advent of protein sequence information provides an opportunity to leverage evolutionary information to enhance the accuracy of protein-protein interface prediction. To this end, several statistical and machine learning methods have been proposed. In particular, direct coupling analysis has recently emerged as a promising approach for identification of protein contact maps from sequential information. However, the ability of these methods to detect protein-protein inter-residue contacts remains relatively limited.\n\nIn this work, we propose a method to integrate sequential and co-evolution information with structural and functional information to increase the performance of protein-protein interface prediction. Further, we present a post-processing clustering method that improves the average relative F1 score by 70 % and 24 % and the precision by 80 % and 36 % in comparison with two state-of-the-art methods PSICOV and GREMLIN.

bioinformatics↗