Ashish Anand

This study compares deep learning models for identifying canonical and non-canonical splice sites across three species, finding that SpliceViNCI performs best, especially with multi-species training.

This paper introduces SpliceViNCI, a model using BLSTM to identify non-canonical splice junctions and visualizes its learned features using integrated gradient and occlusion methods.

The paper introduces new similarity measures based on Gene Ontology to improve confidence scoring of protein interactions and shows they effectively distinguish true from false positives.

This paper introduces two memory-efficient algorithms for reconstructing time-varying gene regulatory networks without assuming smooth time variation, achieving state-of-the-art accuracy on benchmark datasets.

This paper evaluates visualization techniques for interpreting a neural network's learned features in splice junction prediction, finding that perturbation-based methods outperform back-propagation for canonical motifs.

This paper introduces TGS and TGS+ algorithms for reconstructing time-varying gene regulatory networks, showing superior true positive detection but challenges in false positive rejection and memory usage.

SpliceVec uses distributed feature representations to improve splice junction prediction by avoiding manual feature extraction and achieving better classification performance.