Precious2GPT: the combination of multiomics pretrained transformer and conditional diffusion for artificial multi-omics multi-species multi-tissue sample generation.

Synthetic data generation in omics mimics real-world biological data, providing alternatives for training and evaluation of genomic analysis tools, controlling differential expression, and exploring data architecture. We previously developed Precious1GPT, a multimodal transformer trained on transcriptomic and methylation data, along with metadata, for predicting biological age and identifying dual-purpose therapeutic targets potentially implicated in aging and age-associated diseases. In this study, we introduce Precious2GPT, a multimodal architecture that integrates Conditional Diffusion (CDiffusion) and decoder-only Multi-omics Pretrained Transformer (MoPT) models trained on gene expression and DNA methylation data. Precious2GPT excels in synthetic data generation, outperforming Conditional Generative Adversarial Networks (CGANs), CDiffusion, and MoPT. We demonstrate that Precious2GPT is capable of generating representative synthetic data that captures tissue- and age-specific information from real transcriptomics and methylomics data. Notably, Precious2GPT surpasses other models in age prediction accuracy using the generated data, and it can generate data beyond 120 years of age. Furthermore, we showcase the potential of using this model in identifying gene signatures and potential therapeutic targets in a colorectal cancer case study.

Biomedical generative pre-trained based transformer language model for age-related disease target discovery.

Target discovery is crucial for the development of innovative therapeutics and diagnostics. However, current approaches often face limitations in efficiency, specificity, and scalability, necessitating the exploration of novel strategies for identifying and validating disease-relevant targets. Advances in natural language processing have provided new avenues for predicting potential therapeutic targets for various diseases. Here, we present a novel approach for predicting therapeutic targets using a large language model (LLM). We trained a domain-specific BioGPT model on a large corpus of biomedical literature consisting of grant text and developed a pipeline for generating target prediction. Our study demonstrates that pre-training of the LLM model with task-specific texts improves its performance. Applying the developed pipeline, we retrieved prospective aging and age-related disease targets and showed that these proteins are in correspondence with the database data. Moreover, we propose CCR5 and PTH as potential novel dual-purpose anti-aging and disease targets which were not previously identified as age-related but were highly ranked in our approach. Overall, our work highlights the high potential of transformer models in novel target prediction and provides a roadmap for future integration of AI approaches for addressing the intricate challenges presented in the biomedical field.

Precious1GPT: multimodal transformer-based transfer learning for aging clock development and feature importance analysis for aging and age-related disease target discovery.

Aging is a complex and multifactorial process that increases the risk of various age-related diseases and there are many aging clocks that can accurately predict chronological age, mortality, and health status. These clocks are disconnected and are rarely fit for therapeutic target discovery. In this study, we propose a novel approach to multimodal aging clock we call Precious1GPT utilizing methylation and transcriptomic data for interpretable age prediction and target discovery developed using a transformer-based model and transfer learning for case-control classification. While the accuracy of the multimodal transformer is lower within each individual data type compared to the state of art specialized aging clocks based on methylation or transcriptomic data separately it may have higher practical utility for target discovery. This method provides the ability to discover novel therapeutic targets that hypothetically may be able to reverse or accelerate biological age providing a pathway for therapeutic drug discovery and validation using the aging clock. In addition, we provide a list of promising targets annotated using the PandaOmics industrial target discovery platform.

COVIDomic: A multi-modal cloud-based platform for identification of risk factors associated with COVID-19 severity.

Coronavirus disease 2019 (COVID-19) is an acute infection of the respiratory tract that emerged in December 2019 in Wuhan, China. It was quickly established that both the symptoms and the disease severity may vary from one case to another and several strains of SARS-CoV-2 have been identified. To gain a better understanding of the wide variety of SARS-CoV-2 strains and their associated symptoms, thousands of SARS-CoV-2 genomes have been sequenced in dozens of countries. In this article, we introduce COVIDomic, a multi-omics online platform designed to facilitate the analysis and interpretation of the large amount of health data collected from patients with COVID-19. The COVIDomic platform provides a comprehensive set of bioinformatic tools for the multi-modal metatranscriptomic data analysis of COVID-19 patients to determine the origin of the coronavirus strain and the expected severity of the disease. An integrative analytical workflow, which includes microbial pathogens community analysis, COVID-19 genetic epidemiology and patient stratification, allows to analyze the presence of the most common microbial organisms, their antibiotic resistance, the severity of the infection and the set of the most probable geographical locations from which the studied strain could have originated. The online platform integrates a user friendly interface which allows easy visualization of the results. We envision this tool will not only have immediate implications for management of the ongoing COVID-19 pandemic, but will also improve our readiness to respond to other infectious outbreaks.