Biology subjects

Beavers, D.

Publications and source records attributed to Beavers, D..

5 recordsLinked to original sources

bioRxiv2025

Application of Large Language Models for Annotating Genes into Reactome Pathways

Reactome is the most comprehensive, open source, open access biological pathway knowledgebase, widely used in the research community. To ensure the highest quality of its content, human pathway data in Reactome is manually curated. However, manual curation is labor-intensive, time-consuming, and increasingly difficult to keep up with the ever-growing biomedical literature. Large language model (LLM)-driven artificial intelligence (AI) technologies are transforming many fields, including bioinformatics resource development. Applying LLM/AI technologies in Reactome may offer a powerful way to scale curation and consolidate pathway-related data into a single resource. This manuscript describes the first stage of our attempt to adopt LLM/AI technologies for Reactome manual curation. We developed an LLM workflow that can assist curators in adding new genes to existing pathways and refining the functional annotations of existing ones. The workflow predicts pathways in which genes are likely to function, identifies PubMed-indexed literature that may support these predictions, generates text summaries describing potential molecular mechanisms, and extracts functional relationships among biological entities from full-text PDF papers. To validate the workflow output, we used a computational approach based on semantic similarity between LLM workflow-generated summaries and Reactome manual annotations. The results show significant enrichment of high-similarity matches. Manual evaluation of 19 genes indicated that more than half of the outputs are useful for supporting curation. Based on these results, we developed an enhanced workflow that incorporates protein-protein interaction data, facilitating Reactomes reaction-based annotation. In summary, our initial adoption of LLM/AI technologies produced encouraging results and provides a practical framework for integrating AI-assisted methods into Reactomes curation pipeline. The strategies described here may be broadly applicable to community knowledgebases in general.

bioinformatics↗

bioRxiv2025

MiroSCOPE: An AI-driven digital pathology platform for annotating functional tissue units

Cancer tissue analysis in digital pathology is typically conducted across different spatial scales, ranging from high-resolution cell-level modeling to lower-resolution tile-based assessments. However, these perspectives often overlook the structural organization of functional tissue units (FTUs), the small, repeating structures which are crucial to tissue function and key factors during pathological assessment. The incorporation of FTU information is hindered by the need for detailed manual annotations, which are costly and time-consuming to obtain. While artificial intelligence (AI)-based solutions hold great promise to accelerate this process, there is currently no comprehensive workflow for building the large, annotated cohorts required. To remove these roadblocks and advance the development of more interpretable approaches, we developed MiroSCOPE, an end-to-end AI-assisted platform for annotating FTUs at scale, built on QuPath. MiroSCOPE integrates a fine-tunable multiclass segmentation model and curation-specific usability features to enable a human-in-the-loop system that accelerates AI annotation by a pathologist. The system is used to efficiently annotate over 71,900 FTUs on 184 prostate cancer hematoxylin and eosin (H&E)-stained tissue samples and demonstrates ready translation to breast cancer. Furthermore, we publicly release a dataset named Miro-120, consisting of 120 prostate cancer H&E with 30,568 annotations, which can be used by the community as a high-quality resource for FTU-level machine learning aims. In summary, MiroSCOPE provides an adaptable AI-driven platform for annotating functional tissue units, facilitating the use of structural information in digital pathology analyses.

bioinformatics↗

bioRxiv2023

Pathway-based, reaction-specific annotation of disease variants for elucidation of molecular phenotypes

Disease variant annotation in the context of biological reactions and pathways can provide a standardized overview of molecular phenotypes of pathogenic mutations that is amenable to computational mining and mathematical modeling. Reactome, an open source, manually curated, peer-reviewed database of human biological pathways, provides annotations for over 4000 disease variants of close to 400 genes in the context of [~]800 disease reactions constituting [~]400 disease pathways. Functional annotation of disease variants proceeds from normal gene functions, through disease variants whose divergence from normal molecular behaviors has been experimentally verified, to extrapolation from molecular phenotypes of characterized variants to variants of unknown significance using criteria of the American College of Medical Genetics and Genomics (ACMG). Reactomes pathway-based, reaction-specific disease variant dataset and data model provide a platform to infer pathway output impacts of numerous human disease variants and model organism orthologs, complementing computational predictions of variant pathogenicity.

systems biology↗

bioRxiv2023

Illuminating Dark Proteins using Reactome Pathways

Limited knowledge about a substantial portion of protein coding genes, known as "dark" proteins, hinders our understanding of their functions and potential therapeutic applications. To address this, we leveraged Reactome, the most comprehensive, open source, open-access pathway knowledgebase, to contextualize dark proteins within biological pathways. By integrating multiple resources and employing a random forest classifier trained on 106 protein/gene pairwise features, we predicted functional interactions between dark proteins and Reactome-annotated proteins. We then developed three scores to measure the interactions between dark proteins and Reactome pathways, utilizing enrichment analysis and fuzzy logic simulations. Correlation analysis of these scores with an independent single-cell RNA sequencing dataset provided supporting evidence for this approach. Furthermore, systematic natural language processing (NLP) analysis of over 22 million PubMed abstracts and manual checking of the literature associated with 20 randomly selected dark proteins reinforced the predicted interactions between proteins and pathways. To enhance the visualization and exploration of dark proteins within Reactome pathways, we developed the Reactome IDG portal, deployed at https://idg.reactome.org, a web application featuring tissue-specific protein and gene expression overlay, as well as drug interactions. Our integrated computational approach, together with the user-friendly web platform, offers a valuable resource for uncovering potential biological functions and therapeutic implications of dark proteins.

bioinformatics↗

bioRxiv2022

UNSUPERVISED HARMONIZATION OF BRAIN MRI USING 3D CYCLE GANS AND ITS EFFECT ON BRAIN AGE PREDICTION

Deep learning methods trained on brain MRI data from one scanner or imaging protocol can fail catastrophically when tested on data from other sites or protocols - a problem known as domain shift. To address this, here we propose a domain adaptation method that trains a 3D CycleGAN (cycle-consistent generative adversarial network) to harmonize brain MRI data from 5 diverse sources (ADNI, WHIMS, OASIS, AIBL, and UK Biobank; total N=4,941 MRIs, age range: 46-96 years). The approach uses 2 generators and 2 discriminators to generate an image harmonized to a specific target dataset given an image from the source domain distribution and vice versa. We train the CycleGAN to jointly optimize an adversarial loss and cyclic consistency. We use a patch-based discriminator and impose identity loss to further regularize model training. To test the benefit of the harmonization, we show that brain age estimation - a common benchmarking task - is more accurate in GAN-harmonized versus raw data. t-SNE maps show the improved distributional overlap of the harmonized data in the latent space.

neuroscience↗