More Like this

1. SCOT+: A Comprehensive Software Suite for Single-Cell alignment Using Optimal Transport

   https://doi.org/10.1093/bioadv/vbaf314  

   Baker, Colin; Pham, Tuan; Demetci, Pinar; Tran, Quang Huy; Redko, Ievgen; Sandstede, Bjorn; Singh, Ritambhara (December 2025, Bioinformatics Advances)

   Abstract SummaryNew advances in single-cell multi-omics experiments have allowed biologists to examine how various biological factors regulate processes in concert on the cellular level. However, measuring multiple cellular features for a single cell can be quite resource-intensive or impossible with the current technology. By using optimal transport (OT) to align cells and features across disparate datasets produced by separate assays, Single Cell alignment using Optimal Transport + (SCOT+), our unsupervised single-cell alignment software suite, allows biologists to align their data without the need for any correspondence. SCOT+ implements a generic optimal transport solution that can be reduced to multiple different previously studied OT optimization procedures including SCOT, SCOTv2, SCOOTR, and AGW for single cell, each of which provides state-of-the-art single-cell alignment performance. Outside of giving a unified framework to interact with prior formulations, the generality of SCOT+ optimization naturally gives rise to a new OT loss, Unbalanced Augmented Gromov-Wasserstein (UAGW), and a corresponding optimizer. With our user-friendly website and tutorials, this new package will help improve biological analyses by allowing for more accurate downstream analyses on multi-omics single-cell measurements. Implementation and AvailabilityOur algorithm is implemented in Pytorch and available on PyPI and GitHub (https://github.com/scotplus/scotplus). Additionally, we have many tutorials available in a separate GitHub repository (https://github.com/scotplus/book_source) and on our website (https://scotplus.github.io/). 

   more » « less
2. CellMeSH: probabilistic cell-type identification using indexed literature

   https://doi.org/10.1093/bioinformatics/btab834  

   Mao, Shunfu; Zhang, Yue; Seelig, Georg; Kannan, Sreeram (February 2022, Bioinformatics)

   Birol, Inanc (Ed.)

   Abstract MotivationSingle-cell RNA sequencing (scRNA-seq) is widely used for analyzing gene expression in multi-cellular systems and provides unprecedented access to cellular heterogeneity. scRNA-seq experiments aim to identify and quantify all cell types present in a sample. Measured single-cell transcriptomes are grouped by similarity and the resulting clusters are mapped to cell types based on cluster-specific gene expression patterns. While the process of generating clusters has become largely automated, annotation remains a laborious ad hoc effort that requires expert biological knowledge. ResultsHere, we introduce CellMeSH—a new automated approach to identifying cell types for clusters based on prior literature. CellMeSH combines a database of gene–cell-type associations with a probabilistic method for database querying. The database is constructed by automatically linking gene and cell-type information from millions of publications using existing indexed literature resources. Compared to manually constructed databases, CellMeSH is more comprehensive and is easily updated with new data. The probabilistic query method enables reliable information retrieval even though the gene–cell-type associations extracted from the literature are noisy. CellMeSH is also able to optionally utilize prior knowledge about tissues or cells for further annotation improvement. CellMeSH achieves top-one and top-three accuracies on a number of mouse and human datasets that are consistently better than existing approaches. Availability and implementationWeb server at https://uncurl.cs.washington.edu/db_query and API at https://github.com/shunfumao/cellmesh. Supplementary informationSupplementary data are available at Bioinformatics online. 

   more » « less
3. SEraster: a rasterization preprocessing framework for scalable spatial omics data analysis

   https://doi.org/10.1093/bioinformatics/btae412  

   Aihara, Gohta; Clifton, Kalen; Chen, Mayling; Li, Zhuoyan; Atta, Lyla; Miller, Brendan F; Satija, Rahul; Hickey, John W; Fan, Jean (July 2024, Bioinformatics)

   Martelli, Pier Luigi (Ed.)

   Abstract MotivationSpatial omics data demand computational analysis but many analysis tools have computational resource requirements that increase with the number of cells analyzed. This presents scalability challenges as researchers use spatial omics technologies to profile millions of cells. ResultsTo enhance the scalability of spatial omics data analysis, we developed a rasterization preprocessing framework called SEraster that aggregates cellular information into spatial pixels. We apply SEraster to both real and simulated spatial omics data prior to spatial variable gene expression analysis to demonstrate that such preprocessing can reduce computational resource requirements while maintaining high performance, including as compared to other down-sampling approaches. We further integrate SEraster with existing analysis tools to characterize cell-type spatial co-enrichment across length scales. Finally, we apply SEraster to enable analysis of a mouse pup spatial omics dataset with over a million cells to identify tissue-level and cell-type-specific spatially variable genes as well as spatially co-enriched cell types that recapitulate expected organ structures. Availability and implementationSEraster is implemented as an R package on GitHub (https://github.com/JEFworks-Lab/SEraster) with additional tutorials at https://JEF.works/SEraster. 

   more » « less
4. 3D-equivariant graph neural networks for protein model quality assessment

   https://doi.org/10.1093/bioinformatics/btad030  

   Chen, Chen; Chen, Xiao; Morehead, Alex; Wu, Tianqi; Cheng, Jianlin (January 2023, Bioinformatics)

   Cowen, Lenore (Ed.)

   MotivationQuality assessment (QA) of predicted protein tertiary structure models plays an important role in ranking and using them. With the recent development of deep learning end-to-end protein structure prediction techniques for generating highly confident tertiary structures for most proteins, it is important to explore corresponding QA strategies to evaluate and select the structural models predicted by them since these models have better quality and different properties than the models predicted by traditional tertiary structure prediction methods. ResultsWe develop EnQA, a novel graph-based 3D-equivariant neural network method that is equivariant to rotation and translation of 3D objects to estimate the accuracy of protein structural models by leveraging the structural features acquired from the state-of-the-art tertiary structure prediction method—AlphaFold2. We train and test the method on both traditional model datasets (e.g. the datasets of the Critical Assessment of Techniques for Protein Structure Prediction) and a new dataset of high-quality structural models predicted only by AlphaFold2 for the proteins whose experimental structures were released recently. Our approach achieves state-of-the-art performance on protein structural models predicted by both traditional protein structure prediction methods and the latest end-to-end deep learning method—AlphaFold2. It performs even better than the model QA scores provided by AlphaFold2 itself. The results illustrate that the 3D-equivariant graph neural network is a promising approach to the evaluation of protein structural models. Integrating AlphaFold2 features with other complementary sequence and structural features is important for improving protein model QA. Availability and implementationThe source code is available at https://github.com/BioinfoMachineLearning/EnQA. Supplementary informationSupplementary data are available at Bioinformatics online. 

   more » « less
5. PROLONG: penalized regression for outcome guided longitudinal omics analysis with network and group constraints

   https://doi.org/10.1093/bioinformatics/btaf099  

   Broll, Steven; Basu, Sumanta; Lee, Myung Hee; Wells, Martin T (March 2025, Bioinformatics)

   Martelli, Pier Luigi (Ed.)

   Abstract MotivationThere is a growing interest in longitudinal omics data paired with some longitudinal clinical outcome. Given a large set of continuous omics variables and some continuous clinical outcome, each measured for a few subjects at only a few time points, we seek to identify those variables that co-vary over time with the outcome. To motivate this problem we study a dataset with hundreds of urinary metabolites along with Tuberculosis mycobacterial load as our clinical outcome, with the objective of identifying potential biomarkers for disease progression. For such data clinicians usually apply simple linear mixed effects models which often lack power given the low number of replicates and time points. We propose a penalized regression approach on the first differences of the data that extends the lasso + Laplacian method [Li and Li (Network-constrained regularization and variable selection for analysis of genomic data. Bioinformatics 2008;24:1175–82.)] to a longitudinal group lasso + Laplacian approach. Our method, PROLONG, leverages the first differences of the data to increase power by pairing the consecutive time points. The Laplacian penalty incorporates the dependence structure of the variables, and the group lasso penalty induces sparsity while grouping together all contemporaneous and lag terms for each omic variable in the model. ResultsWith an automated selection of model hyper-parameters, PROLONG correctly selects target metabolites with high specificity and sensitivity across a wide range of scenarios. PROLONG selects a set of metabolites from the real data that includes interesting targets identified during EDA. Availability and implementationAn R package implementing described methods called “prolong” is available at https://github.com/stevebroll/prolong. Code snapshot available at 10.5281/zenodo.14804245. 

   more » « less