PandaOmics Manual

ChatPandaGPT

ChatPandaGPT integrates a Large Language Model (LLM) and chat functionality to provide information and answer questions related to molecular biology, therapeutic target discovery, and pharmaceutical development. With a chatbot-like interface, the LLM allows it to give more personalized and relevant responses to each user based on specific needs and interests. ChatPandaGPT is aware of general biological data and has been augmented with specific information from the PandaOmics Knowledge Graph, ensuring accuracy in each response.

The user can interact with ChatPandaGPT by selecting one of the predefined questions like "What are the potential risks and benefits of targeting gene X?". Alternatively, users can formulate their own queries and receive relevant answers. ChatPandaGPT can be found on the Publications tab of the following pages: Gene, Disease, Gene-Disease Association. Please refer to the ChatPandaGPT manual section for more detailed information.

Automatically Generated Gene-Disease Report

Drug target assessment must include diverse considerations related to biology, chemistry, technology, and business. While there is no single set of questions that are comprehensive for every context, there are a few that very commonly arise. Is there a strong, mechanistic link between the target and the disease? Is it feasible to design and manufacture a drug against this target? What properties would a drug against this target need to have to be competitive in the market, and would it make sense in our company's portfolio?

PandaOmics 4.0 introduces a groundbreaking and revolutionary approach to creating Gene-Disease reports in the context of drug target investigation. By combining omics data from an internal database with the power of Large Language Models (LLMs), PandaOmics now enables users to automatically create a detailed report encompassing all available pieces of evidence for gene-disease associations. This new approach plays a pivotal role in the PandaOmics workflow, providing critical steps when users are on the quest for their targets and diseases of interest.

Indication Prioritization

In version 4.0 of PandaOmics, users can quantitatively prioritize diseases for a given target with a variety of configurable multi-omics-based and text-based scores. Top-ranked diseases can be viewed as candidates in the context of indication expansion for existing drugs or identifying novel indications for promising targets. Indications can be categorized based on either pathology groups (such as oncology or infection) or by organ systems (such as the respiratory or digestive system) for convenience. Indication prioritization functionality can be found on the Indication Prioritization tab of any Gene page.

Genetics-related Enhancements

The latest release of PandaOmics brings a wealth of genetics-related enhancements to our platform. In response to the ever-growing importance of genetics in drug discovery and biomedical research, we've introduced a dedicated Genetics tab, providing a streamlined interface for in-depth genetic exploration. This tab allows users to access gene- and variant-level information from several genetic databases and can be found on any Disease page.

Other enhancements include allowing users to visualize genes carrying relevant genetic variants on the Knowledge Graph. We also improved genetics-related scores for the ranking of potential therapeutic targets in oncology and other therapeutic areas. These advancements aim to significantly enhance genetic research capabilities within PandaOmics, facilitating more informed decision-making and a deeper understanding of the role of genetics in disease mechanisms.

Knowledge Graph Improvements

In PandaOmics 3.0 we introduced the Knowledge Graph, a result of automated analyses of scientific publications, which allows users to visualize the relationships between genes, diseases, chemical compounds, and biological processes. By delving into Knowledge Graph, researchers can gain insights into the molecular underpinnings of diseases and the known roles of genes and compounds in the disease context. This resource assists in making informed decisions about prospective drug targets and biomarkers.

In this release, we bring significant enhancements to the Knowledge Graph. Our database has been updated to include the latest publications available up to Sep 2023. The Knowledge Graph now offers the capability to visually identify whether a gene harbors genetic variants known to be linked to a particular disease. Additionally, we have improved the user interface by introducing new designs for the legend and graph layout selector. The Knowledge Graph is accessible on the Publications tab of the Meta-Analysis, Gene, Disease, and Gene-Disease Association pages.

Methylation Data Upload

PandaOmics 4.0 introduces the capability for users to upload custom, gene-level methylomics datasets. These datasets can undergo processing through a standard PandaOmics data analysis pipeline, thus greatly enhancing support for multi-omics data analysis. The inclusion of the custom methylome upload feature seamlessly integrates user-proprietary data into PandaOmics Target ID results. PandaOmics accommodates the upload of both M-values and B-values, and it automatically converts B-values to M-values when necessary. Additionally, during the regularly scheduled updates for the PandaOmics platform, the methylation microarray processing for public datasets has been expanded to support both Illumina 850k and 935k platforms. New datasets based on these platforms are now collected from GEO monthly in addition to the 450k datasets supported in earlier versions. These updates significantly enrich the methylomics analyses within the platform.

Database Update

In PandaOmics 4.0, we have incorporated over 300 manually curated disease-specific Meta-Analyses, with a particular focus on cancer, rare and genetic diseases, as well as inflammatory and infectious diseases. Pre-calculated Target ID scores and Compound ID scores are available on their respective tabs within each Disease page. We ensure the regular updates of the pre-calculated Disease pages weekly.

Over 2,000 high-quality omics datasets covering 71,000 samples have been added to the platform and are readily available for target discovery analyses. In this release, we have placed a special focus on methylation data support. More than 500 datasets for three platforms (450k, 850k, and 935k) were added to the database. Also, several proteomics datasets across 40+ diseases have been added, covering more than 2,000 samples. Overall this improvement has led to a ten-fold increase in the number of pre-calculated multi-omics disease projects available to the user compared to PandaOmics 3.0.

Other Improvements

This release introduces significant improvements in search capabilities across the user interface. Specifically, we've enhanced pathway search functionality by enabling searches across various meta-data fields, including pathway name, description, keywords, and pathway content such as gene names. In addition, when querying for genes within the Target ID or Expression Analysis sections, users will receive results irrespective of the current filtering criteria. The Publications tab supports a comprehensive search approach, encompassing publication titles, abstracts, author surnames, and keywords. Furthermore, we've removed the constraint that previously limited the display to the top 500 publications associated with Genes or Diseases, offering a more extensive view of relevant publications.

The druggability filters (Small molecules, Antibodies, Safety, and Novelty) on both the Meta-Analysis and Disease pages can now be customized to accommodate any combination of values. Furthermore, we've enhanced the functionality of Meta-Analysis, allowing users to add or reattach comparisons and modify the therapeutic area for previously conducted Meta-analyses, creating an editable copy for greater flexibility. Additionally, navigation within the Pharma.AI platform is now more seamless, with direct links to Chemistry42 and InClinico conveniently located in the upper left corner of every PandaOmics screen. Finally, the Expression Analysis page for each Meta-Analysis now includes the option to export differential analysis results in a comma-separated text file, providing greater utility for your research needs.

You can download the printer-friendly PandaOmics 4.0 Brochure in PDF.