Biology subjects

Pati, P.

Publications and source records attributed to Pati, P..

4 recordsLinked to original sources

bioRxiv2023

Multiplexed tumor profiling with generative AI accelerates histopathology workflows and improves clinical predictions

Understanding the spatial heterogeneity of tumors and its links to disease is a cornerstone of cancer biology. Emerging spatial technologies offer unprecedented capabilities towards this goal, but several limitations hinder their clinical adoption. To date, histopathology workflows still heavily depend on hematoxylin & eosin (H&E) and serial immunohistochemistry (IHC) staining, a cumbersome and tissue-exhaustive process that yields unaligned tissue images. We propose the VirtualMultiplexer, a generative AI toolkit that translates real H&E images to matching IHC images for several markers based on contrastive learning. The VirtualMultiplexer learns from unpaired H&E and IHC images and introduces a novel multi-scale loss to ensure consistent and biologically reliable stainings. The virtually multiplexed images enabled training a Graph Transformer that simultaneously learns from the joint spatial distribution of several markers to predict clinically relevant endpoints. Our results indicate that the VirtualMultiplexer achieves rapid, robust and precise generation of virtually multiplexed imaging datasets of high staining quality that are indistinguishable from the real ones. We successfully employed transfer learning to generate realistic virtual stainings across tissue scales, patient cohorts, and cancer types with no need for model fine-tuning. Crucially, the generated images are not only realistic but also clinically relevant, as they greatly improved the prediction of different clinical endpoints across patient cohorts and cancer types, speeding up histopathology workflows and accelerating spatial biology.

bioinformatics↗

bioRxiv2022

ChromFormer: A transformer-based model for 3Dgenome structure prediction

Recent research has shown that the three-dimensional (3D) genome structure is strongly linked to cell function. Modeling the 3D genome structure can not only elucidate vital biological processes, but also reveal structural disruptions linked to disease. In the absence of experimental techniques able to determine 3D chromatin structure, this task is achieved computationally by exploiting chromatin interaction frequencies as measured by high-throughput chromosome conformation capture (Hi-C) data. However, existing methods are unsupervised, and limited by underlying assumptions. In this work, we present a novel framework for 3D chromatin structure prediction from Hi-C data. The framework consists of, a novel synthetic data generation module that simulates realistic structures and corresponding Hi-C matrices, and CO_SCPLOWHROMC_SCPLOWFO_SCPLOWORMERC_SCPLOW, a transformer-based model to predict 3D chromatin structures from standalone Hi-C data, while providing local structural-level confidence estimates. Our solution outperforms existing methods when tested on unseen synthetic data, and achieves comparable results on experimental data for a full eukaryotic genome. The code, data, and models can be accessed at https://github.com/AI4SCR/ChromFormer.

bioinformatics↗

bioRxiv2022

MatchCLOT: Single-Cell Modality Matching with Contrastive Learning and Optimal Transport

Recent advances in single-cell technologies have enabled the simultaneous quantification of multiple biomolecules in the same cell, opening new avenues for understanding cellular complexity and heterogeneity. However, the resulting multimodal single-cell datasets present unique challenges arising from the high dimensionality of the data and the multiple sources of acquisition noise. In this work, we propose MO_SCPLOWATCHC_SCPLOWCLOT, a novel method for single-cell data integration based on ideas borrowed from contrastive learning, optimal transport, and transductive learning. In particular, we use contrastive learning to learn a common representation between two modalities and apply entropic optimal transport as an approximate maximum weight bipartite matching algorithm. Our model obtains state-of-the-art performance in the modality matching task from the NeurIPS 2021 multimodal single-cell data integration challenge, improving the previous best competition score by 28.9%. Our code can be accessed at https://github.com/AI4SCR/MatchCLOT.

bioinformatics↗

bioRxiv2022

Efficacy of Parainfluenza Virus 5 (PIV5)-vectored Intranasal COVID-19 Vaccine as a Single Dose Vaccine and as a Booster against SARS-CoV-2 Variants

Immunization with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccines has greatly reduced coronavirus disease 2019 (COVID-19)-related deaths and hospitalizations, but waning immunity and the emergence of variants capable of immune escape indicate the need for novel SARS-CoV-2 vaccines. An intranasal parainfluenza virus 5 (PIV5)-vectored COVID-19 vaccine CVXGA1 has been proven efficacious in animal models and blocks contact transmission of SARS-CoV-2 in ferrets. CVXGA1 vaccine is currently in human clinical trials in the United States. This work investigates the immunogenicity and efficacy of CVXGA1 and other PIV5-vectored vaccines expressing additional antigen SARS-CoV-2 nucleoprotein (N) or SARS-CoV-2 variant spike (S) proteins of beta, delta, gamma, and omicron variants against homologous and heterologous challenges in hamsters. A single intranasal dose of CVXGA1 induces neutralizing antibodies against SARS-CoV-2 WA1 (ancestral), delta variant, and omicron variant and protects against both homologous and heterologous virus challenges. Compared to mRNA COVID-19 vaccine, neutralizing antibody titers induced by CVXGA1 were well-maintained over time. When administered as a boost following two doses of a mRNA COVID-19 vaccine, PIV5-vectored vaccines expressing the S protein from WA1 (CVXGA1), delta, or omicron variants generate higher levels of cross-reactive neutralizing antibodies compared to three doses of a mRNA vaccine. In addition to the S protein, the N protein provides added protection as assessed by the highest body weight gain post-challenge infection. Our data indicates that PIV5-vectored COVID-19 vaccines, such as CVXGA1, can serve as booster vaccines against emerging variants. ImportanceWith emerging new variants of concern (VOC), SARS-CoV 2 continues to be a major threat to human health. Approved COVID-19 vaccines have been less effective against these emerging VOCs. This work demonstrates the protective efficacy, and strong boosting effect, of a new intranasal viral-vectored vaccine against SARS-CoV-2 variants in hamsters.

microbiology↗