Biology subjects

Halder, A. K.

Publications and source records attributed to Halder, A. K..

3 recordsLinked to original sources

bioRxiv2026

SIP-BERT: A multi-organism deep strategy for predicting self interaction in proteins

Self-interacting proteins (SIPs) are critical to cellular regulation, yet their experimental identification remains challenging due to high costs, inefficiencies, and frequent false positives. Leveraging recent advances in deep language models, we introduce SIP-BERT, a family of lightweight transformer-based models trained on organism-specific self-interaction datasets curated from existing protein-protein interaction databases. We developed three variants: SIP-BERT(H), SIP-BERT(Y), and SIP-BERT(HY) -trained on human, yeast, and combined datasets, respectively. These models significantly outperform existing methods, exceeding baseline accuracies by 18%, 8% and 15% respectively. SIP-BERT models also generalise effectively to under-annotated organisms such as the mouse and the fruit fly, achieving high recall despite minimal labeled data. Furthermore, structural analysis of predicted false positives using PDB-derived alpha-carbon distance maps reveals close spatial residue proximities, suggesting plausible but undocumented self-interactions. These results highlight the potential of SIP-BERT to uncover novel SIPs and expand our understanding of protein self-interaction across diverse species. The dataset and the developed models are available at https://github.com/CMATERJU-BIOINFO/SIP-BERT for academic use only.

bioinformatics↗

bioRxiv2023

FuzzyPPI: Human Proteome at Fuzzy Semantic Space

Large scale protein-protein interaction (PPI) network of an organism provides key insights into its cellular and molecular functionalities, signaling pathways and underlying disease mechanisms. For any organism the total number of unexplored protein interactions significantly outnumbers all known positive and negative interactions. For Human, all known PPI datasets, contain only [~] 5.61 million positive and [~] 0.76 million negative interactions, that together is [~] 3.1% of potential interactions. Moreover, conventional PPI prediction methods produce binary results. At the same time, recent studies show that protein binding affinities may prove to be effective in detecting protein complexes, disease association analysis, signaling network reconstruction, etc. Keeping these in mind, we present a fuzzy semantic scoring function using the Gene Ontology (GO) graphs to assess the binding affinity between any two proteins at an organism level. We have implemented a distributed algorithm in Apache Spark that computes this function and used it to process a Human PPI network of [~] 180 million potential interactions resulting from 18 994 reviewed proteins for which GO annotations are available. The quality of the computed scores has been validated with respect to the available state-of-the-art methods on benchmark data sets. The resulting scores are published with a web-server for non-commercial use at: http://fuzzyppi.mimuw.edu.pl/.

bioinformatics↗

bioRxiv2020

SeqPIP-2020: Sequence based Protein InteractionPrediction Contest

Computational protein-protein interaction (PPI) prediction techniques can contribute greatly in reducing time, cost and false-positive interactions compared to experimental approaches. Sequence is one of the key and primary information of proteins that plays a crucial role in PPI prediction. Several machine learning approaches have been applied to exploit the characteristics of PPI datasets. However, these datasets greatly influence the performance of predicting models. So, care should be taken on both dataset curation as well as design of predictive models. Here, we summarize the results of the SeqPIP competition whose objective was to develop comprehensive PPI predictive models from sequence information with high-quality bias-free interaction datasets. A training set of 2000 positive and 2000 negative interactions with sequences was given to each contestant. The methods were evaluated with three independent high-quality interaction test datasets.

bioinformatics↗