Biology subjects

Chandrashekar, P. B.

Publications and source records attributed to Chandrashekar, P. B..

3 recordsLinked to original sources

bioRxiv2025

Inferring virtual cell environments using multi-agent reinforcement learning

1Single cells interact continuously to form a cell environment that drives key biological processes. Cells and cell environments are highly dynamic across time and space, fundamentally governed by molecular mechanisms, such as gene expression. Recent sequencing techniques measure single-cell-level gene expression under specific conditions, either temporally or spatially. Using these datasets, emerging works, such as virtual cells, can learn biologically useful representations of individual cells. However, these representations are typically static and overlook the underlying cell environment and its dynamics. To address this, we developed CellTRIP, a multi-agent reinforcement learning method that infers a virtual cell environment to simulate the cell dynamics and interactions underlying given single-cell data. Specifically, cells are modeled as individual agents with dynamic interactions, which can be learned through self-attention mechanisms via reinforcement learning. CellTRIP also applies novel truncated reward boot-strapping and adaptive input rescaling to stabilize training. We can in-silico manipulate any combination of cells and genes in our learned virtual cell environment, predict spatial and/or temporal cell changes, and prioritize corresponding genes at the single-cell level. We applied and benchmarked CellTRIP on various simulated and real gene expression datasets, including recapitulating cellular dynamic processes simulated by gene regulatory networks and stochastic models, imputing spatial organization of mouse cortical cells, predicting developmental gene expression changes after drug treatment in cancer cells, and spatiotemporal reconstruction of Drosophila embryonic development, demonstrating its outperformance and broad applicability. Interactive manipulation of those virtual cell environments, including in-silico perturbation, can prioritize spatial and developmental genes for single-cell-level changes, enabling the generation of new insights into cell dynamics over time and space. CellTRIP is open source as a general tool and available at github.com/daifengwanglab/CellTRIP.

bioinformatics↗

bioRxiv2023

DeepCORE: An interpretable multi-view deep neural network model to detect co-operative regulatory elements

Gene transcription is an essential process involved in all aspects of cellular functions with significant impact on biological traits and diseases. This process is tightly regulated by multiple elements that co-operate to jointly modulate the transcription levels of target genes. To decipher the complicated regulatory network, we present a novel multi-view attention-based deep neural network that models the relationship between genetic, epigenetic, and transcriptional patterns and identifies co-operative regulatory elements (COREs). We applied this new method, named DeepCORE, to predict transcriptomes in 25 different cell lines, which outperformed the state-of-the-art algorithms. Furthermore, DeepCORE translates the attention values embedded in the neural network into interpretable information, including locations of putative regulatory elements and their correlations, which collectively implies COREs. These COREs are significantly enriched with known promoters and enhancers. Novel regulatory elements discovered by DeepCORE showed epigenetic signatures consistent with the status of histone modification marks.

bioinformatics↗

bioRxiv2022

DeepGAMI: Deep biologically guided auxiliary learning for multimodal integration and imputation to improve phenotype prediction

Genotype-phenotype association is found in many biological systems, such as brain-related diseases and behavioral traits. Despite the recent improvement in the prediction of phenotypes from genotypes, they can be further improved and explainability of these predictions remains challenging, primarily due to complex underlying molecular and cellular mechanisms. Emerging multimodal data enables studying such mechanisms at different scales from genotype to phenotypes involving intermediate phenotypes like gene expression. However, due to the black-box nature of many machine learning techniques, it is challenging to integrate these multi-modalities and interpret the biological insights in prediction, especially when some modality is missing. Biological knowledge has recently been incorporated into machine learning modeling to help understand the reasoning behind the choices made by these models. To this end, we developed DeepGAMI, an interpretable deep learning model to improve genotype-phenotype prediction from multimodal data. DeepGAMI uses prior biological knowledge to define the neural network architecture. Notably, it embeds an auxiliary-learning layer for cross-modal imputation while training the model from multimodal data. Using this pre-trained layer, we can impute latent features of additional modalities and thus enable predicting phenotypes from a single modality only. Finally, the model uses integrated gradient to prioritize multimodal features and links for phenotypes. We applied DeepGAMI to multiple emerging multimodal datasets: (1) population-level genotype and bulk-tissue gene expression data for predicting schizophrenia, (2) population-level genotype and gene expression data for predicting clinical phenotypes in Alzheimers Disease, (3) gene expression and electrophysiological data of single neuronal cells in the mouse visual cortex, and (4) cell-type gene expression and genotype data for predicting schizophrenia. We found that DeepGAMI outperforms existing state-of-the-art methods and provides a profound understanding of gene regulatory mechanisms from genotype to phenotype, especially at cellular resolution. DeepGAMI is an open-source tool and is available at https://github.com/daifengwanglab/DeepGAMI.

bioinformatics↗