Author

Sumaiya Shomaji

University of KansasORCID 0009-0008-9843-2325Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 1 Approach:graph neural network· 1 Organism:human· 1 Assay:protein sequence· 1 Research Focus:protein structure prediction· 1 Approach:transformer / foundation model· 1

Frequent Co-Authors

Arian AshourvaniD· 1 shared Bishnu SarkeriD· 1 shared Devin SetiawaniD· 1 shared Fairuz Shadmani ShishiriD· 1 shared Farzana RahmaniD· 1 shared Joaquín GoñiiD· 1 shared

Activity by Year

2023-2025 · peak 1/yr

Co-Author Collaboration Network

6 top collaborators · 6 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

1 shared paperNeuroscience

Arian AshourvanORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

NeurosciencebioRxivPreprintDec 17, 2025

A Concept-Driven Disentanglement Framework for Interpretable Graph Neural Networks in Structure-Function Coupling

Devin Setiawan, Sumaiya Shomaji, Joaquín Goñi, Arian Ashourvan

This paper introduces a concept-driven disentanglement framework for interpretable GNNs to predict brain functional connectivity from structural connectivity, achieving high accuracy and providing interpretable insights.

DOI 10.64898/2025.12.15.694495

humangraph neural network

𝕏 PostBluesky

BioinformaticsLecture notes in computer sciencePeer-reviewedJan 1, 2023

MetaLLM: Residue-wise Metal ion Prediction UsingDeep Transformer Model

Fairuz Shadmani Shishir, Bishnu Sarker, Farzana Rahman, Sumaiya Shomaji

MetaLLM predicts metal binding sites in proteins using a transformer-based model trained on protein sequences, achieving over 90% precision for common metal ions.

3 citations

protein sequencedeep learning

𝕏 PostBluesky