Sameer Ahmad Khan

SpatialDiffusion: Predicting Spatial Transcriptomics with DenoisingDiffusion Probabilistic Models

This paper introduces a denoising diffusion model to predict and interpolate spatial transcriptomics data, enabling generative modeling of tissue slices.

Foundation Models Meet Imbalanced Single-Cell Data When Learning Cell Type Annotations

This study evaluates how single-cell foundation models handle imbalanced cell-type data and finds that scGPT and scBERT outperform Geneformer, with random oversampling improving performance.

LEP-AD: Language Embedding of Proteins and Attention to Drugs predicts drug target interactions

LEP-AD uses a Transformer protein language model to predict drug-target interactions, achieving state-of-the-art results across multiple datasets.

scAEGAN: Unification of Single-Cell Genomics Data by Adversarial Learning of Latent Space Correspondences

scAEGAN unifies single-cell genomics data by adversarial learning of latent space correspondences, outperforming existing methods in integration and prediction tasks.