Biology subjects

Kouril, M.

Publications and source records attributed to Kouril, M..

6 recordsLinked to original sources

bioRxiv2026

A Conversational Multi-Agent AI System for Integrated Multi-Omics Analysis and Biomedical Discovery

Single-cell and spatial omics offer unprecedented opportunities to decipher the mechanisms of disease, however, this process requires teams of experts, iterative trial-and-error and reasoning across modalities. Here we present LungChat (https://chat.lungmap.net), a conversational system for integrated multi-omics analysis and biomedical discovery, deployed as a hierarchical multi-agent architecture in which a supervisor decomposes natural-language questions into parallel, tool-grounded tasks spanning single-cell and spatial analyses, literature and clinical-trial synthesis, and drug repurposing. To predict new therapeutics, LungChat implements Direction-Aware Repurposing and Targeting (DART) to distinguish perturbations that reverse disease transcriptional programs from those that reinforce them, at the cell-type level, for safety prediction. Controlled architecture ablations showed that hierarchical orchestration improved grounded abstention and token efficiency and preserved strong performance on complex multi-step tasks. In pulmonary disease case studies, LungChat independently prioritized saracatinib for IPF through drug-connectivity screening, followed by DART-based cell-type analysis; the same compound has been evaluated in the STOP-IPF clinical trial (NCT04598919). The system also recovered fluticasone propionate, an established COPD therapy, through a single orchestrated analysis. This tissue-agnostic system provides a blueprint for verifiable agentic AI systems that support reproducible scientific discovery.

bioinformatics↗

bioRxiv2022

Guided construction of single cell reference for human and mouse lung

Accurate cell type identification is a key and rate-limiting step in single cell data analysis. Single cell references with comprehensive cell types, reproducible and functional validated cell identities, and common nomenclatures are much needed by the research community to optimize automated cell type annotation and facilitate data integration, sharing, and collaboration. In the present study, we developed a novel computational pipeline to utilize the LungMAP CellCards as a dictionary to consolidate single-cell transcriptomic datasets of 104 human lungs and 17 mouse lung samples and constructed "LungMAP CellRef" and "LungMAP CellRef Seed" for both normal human and mouse lungs. "CellRef Seed" has an equivalent prediction power and produces consistent cell annotation as does "CellRef" but improves computational efficiency and simplifies its utilization for fast automated cell type annotation and online visualization. This atlas set incorporates 48 human and 40 mouse well-defined lung cell types catalogued from diverse anatomic locations and developmental time points. Using independent datasets, we demonstrated the utility of our CellRefs for automated cell type annotation analysis of both normal and disease lungs. User-friendly web interfaces were developed to support easy access and maximal utilization of the LungMAP CellRefs. LungMAP CellRefs are freely available to the pulmonary research community through fast interactive web interfaces to facilitate hypothesis generation, research discovery, and identification of cell type alterations in disease conditions.

bioinformatics↗

bioRxiv2021

LungMAP Portal Ecosystem: Systems-Level Exploration of the Lung

An improved understanding of the human lung necessitates advanced systems models informed by an ever-increasing repertoire of molecular omics, cellular, imaging and pathological datasets. To centralize and standardize information across broad lung research efforts we expanded the LungMAP.net website into a gateway portal. This portal connects a broad-spectrum of research networks, bulk and single-cell multi-omics data and a diverse collection of image data that span mammalian lung development and disease. The data are standardized across species and technologies using harmonized data and metadata models that leverage recent advances including those from the Human Cell Atlas, diverse ontologies, and the LungMAP CellCards initiative. To cultivate future discoveries, we have aggregated a diverse collection of single-cell atlases for multiple species (human, rhesus, mouse), to enable consistent queries across technologies, cohorts, age, disease and drug treatment. These atlases are provided as independent and integrated queriable datasets, with an emphasis on dynamic visualization, figure generation and reference-based classification of user-provided datasets (Azimuth). As this resource grows, we intend to increase the breadth of available interactive interfaces, data portals and datasets from LungMAP and external research efforts.

systems biology↗

bioRxiv2020

Accelerating Drug Discovery and Repurposingby Combining Transcriptional Signature Connectivity with Docking

The development of targeted treatment options for precision medicine is hampered by a slow and costly process of drug screening. While small molecule docking simulations are often applied in conjunction with cheminformatic methods to reduce the number of candidate molecules to be tested experimentally, the current approaches suffer from high false positive rates and are computationally expensive. Here, we present a novel in silico approach for drug discovery and repurposing, dubbed connectivity enhanced Structure Activity Relationship (ceSAR) that improves on current methods by combining docking and virtual screening approaches with pharmacogenomics and transcriptional signature connectivity analysis. ceSAR builds on the landmark LINCS library of transcriptional signatures of over 20,000 drug-like molecules and ~5,000 gene knock-downs (KDs) to connect small molecules and their potential targets. For a set of candidate molecules and specific target gene, candidate molecules are first ranked by chemical similarity to their concordant LINCS analogs that share signature similarity with a knock-down of the target gene. An efficient method for chemical similarity search, optimized for sparse binary fingerprints of chemical moieties, is used to enable fast searches for large libraries of small molecules. A small subset of candidate compounds identified in the first step is then re-scored by combining signature connectivity with docking simulations. On a set of 20 DUD-E benchmark targets with LINCS KDs, the consensus approach reduces significantly false positive rates, improving the median precision 3-fold over docking methods at the extreme library reduction. We conclude that signature connectivity and docking provide complementary signals, offering an avenue to improve the accuracy of virtual screening while reducing run times by multiple orders of magnitude.

bioinformatics↗

bioRxiv2019

Connecting omics signatures of diseases, drugs, and mechanisms of actions with iLINCS

There are only a few platforms that integrate multiple omics data types, bioinformatics tools, and interfaces for integrative analyses and visualization that do not require programming skills. Among these, iLINCS is unique in scope and versatility of the data provided and the analytics facilitated. iLINCS (http://ilincs.org) is an integrative web-based platform for analysis of omics data and signatures of cellular perturbations. The platform facilitates analysis of user-submitted omics signatures of diseases and cellular perturbations in the context of a large compendium of pre-computed signatures (>200,000), as well as mining and re-analysis of the large collection of omics datasets (>12,000), pre-computed signatures, and their connections. Analytics workflows driven by user-friendly interfaces enable users with only conceptual understanding of the analysis strategy to execute sophisticated analyses of omics signatures, such as systems biology analyses and interpretation of signatures, mechanism of action analysis, and signature-driven drug repositioning. In summary, iLINCS workflows integrate vast omics data resources and a range of analytics and interactive visualization tools into a comprehensive platform for analysis of omics signatures.

bioinformatics↗

bioRxiv2018

GREIN: An interactive web platform for re-analyzing GEO RNA-seq data

The vast amount of RNA-seq data deposited in Gene Expression Omnibus (GEO) and Sequence Read Archive (SRA) is still a grossly underutilized resource for biomedical research. To remove technical roadblocks for reusing these data, we have developed a web-application GREIN (GEO RNA-seq Experiments Interactive Navigator) which provides user-friendly interfaces to manipulate and analyze GEO RNA-seq data. GREIN is powered by the back-end computational pipeline for uniform processing of RNA-seq data and the large number (>6,500) of already processed datasets. The front-end user interfaces provide a wealth of user-analytics options including sub-setting and downloading processed data, interactive visualization, statistical power analyses, construction of differential gene expression signatures and their comprehensive functional characterization, and connectivity analysis with LINCS L1000 data. The combination of the massive amount of back-end data and front-end analytics options driven by user-friendly interfaces makes GREIN a unique open-source resource for re-using GEO RNA-seq data. GREIN is accessible at: https://shiny.ilincs.org/grein, the source code at: https://github.com/uc-bd2k/grein, and the Docker container at: https://hub.docker.com/r/ucbd2k/grein.

bioinformatics↗