Biology subjects

Maiti, P.

Publications and source records attributed to Maiti, P..

4 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↗

bioRxiv2022

Style Transfer Generative Adversarial Networks to Harmonize Multi-Site MRI to a Single Reference Image to Avoid Over-Correction

Recent work within neuroimaging consortia have aimed to identify reproducible, and often subtle, brain signatures of psychiatric or neurological conditions. To allow for high-powered brain imaging analyses, it is often necessary to pool MR images that were acquired with different protocols across multiple scanners. Current retrospective harmonization techniques have shown promise in removing cross-site image variation. However, most statistical approaches may over-correct for technical, scanning-related, variation as they cannot distinguish between confounded image-acquisition based variability and cross-site population variability. Such statistical methods often require that datasets contain subjects or patient groups with similar clinical or demographic information to isolate the acquisition-based variability. To overcome this limitation, we consider cross-site MRI image harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a single reference image, without knowing their site/scanner labels a priori. We trained our model using data from five large-scale multi-site datasets with varied demographics. Results demonstrated that our style-encoding model can harmonize MR images, and match intensity profiles, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. We highlight the effectiveness of our method for clinical research by comparing extracted cortical and subcortical features, brain-age estimates, and case-control effect sizes before and after the harmonization. We showed that our harmonization removed the cross-site variances, while preserving the anatomical information and clinical meaningful patterns. We further demonstrated that with a diverse training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising novel tool for ongoing collaborative studies. Source code is released in USC-IGC/style_transfer_harmonization (github.com).

neuroscience↗

bioRxiv2021

Style Transfer Using Generative Adversarial Networks for Multi-Site MRI Harmonization

Large data initiatives and high-powered brain imaging analyses require the pooling of MR images acquired across multiple scanners, often using different protocols. Prospective cross-site harmonization often involves the use of a phantom or traveling subjects. However, as more datasets are becoming publicly available, there is a growing need for retrospective harmonization, pooling data from sites not originally coordinated together. Several retrospective harmonization techniques have shown promise in removing cross-site image variation. However, most unsupervised methods cannot distinguish between image-acquisition based variability and cross-site population variability, so they require that datasets contain subjects or patient groups with similar clinical or demographic information. To overcome this limitation, we consider cross-site MRI image harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a reference image directly, without knowing their site/scanner labels a priori. We trained our model using data from five large-scale multi-site datasets with varied demographics. Results demonstrated that our styleencoding model can harmonize MR images, and match intensity profiles, successfully, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. Moreover, we further demonstrated that if we included diverse enough images into the training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising novel tool for ongoing collaborative studies.

neuroscience↗

bioRxiv2019

Diffusion Tensor Imaging connectivity analysis: detecting structural alterations and their underlying substrates for Optic Ataxia in correlations with \"How\" stream Visual Pathways

Optic ataxia is a neurological condition that shows clinical manifestations of disturbances in visual guided hand movements on reaching for a target object. Previous studies failed to provide substantial evidences for the neural structural pathway damaged by this condition. Therefore, this study was aimed to identify the neural structural connectivity between \"Visual cortex with Superior Parietal Lobule\" and to correlate its functional importance, using \"Diffusion Imaging fiber Tractography. The fibers were traced, and we confirmed its extension from \"Visual cortex (Brodmanns Areas 18 and 19) to Superior Parietal Lobule (Brodmanns Area 7)\". This new observation gives an insight to understand the structural existence and functional correlations between \"Visual cortex with Superior Parietal Lobule\" which is involved in targeting the grasping hand movements towards a visually perceived object, called visuo-motor coordination pathway or \"how\" stream pathways in visual perception. The observational analysis used thirty-two healthy adults, ultra-high b-value, diffusion MRI datasets from an Open access research platform. The datasets range between 20-49 years, in both sexes, with mean age of 31.1 years. The confirmatory observational analysis process includes, datasets acquisition, pre-processing, processing, reconstruction, fiber tractography and analysis using software tools. All the datasets confirmed that the fiber structural extension between, Visual cortex to superior parietal lobe in both the sexes may be responsible for the visual spatial recognition of objects. These new fiber connectivity evidences justify the structural relevance of visual spatial recognition impairments, such as optic ataxia.

neuroscience↗