2025 Hyper Recent •CC0 1.0 Universal

This work is dedicated to the public domain. No rights reserved.

Access Preprint From Server
March 7th, 2025
Version: 1
Insilico Medicine
bioinformatics
biorxiv

DORA AI Scientist: Multi-agent Virtual Research Team for Scientific Exploration Discovery and Automated Report Generation

Naumov, V.Open in Google Scholar•Zagirova, D.Open in Google Scholar•Lin, S.Open in Google Scholar•Xie, Y.Open in Google Scholar•Gou, W.Open in Google Scholar•Urban, A.Open in Google Scholar•Tikhonova, N.Open in Google Scholar•Alawi, K.Open in Google Scholar•Durymanov, M.Open in Google Scholar•Galkin, F.Open in Google Scholaret al.

Modern goal-oriented scientific research process involves hierarchical teams of researchers of diverse backgrounds performing generalist and domain-specific tasks. Many of these tasks include hypothesis generation, literature review, data collection, cleanup, processing and analysis, experimental design, virtual and physical experiments, research report and academic paper writing, reference management, bibliography and quality control. Most of these tasks can be performed automatically or in a co-pilot mode by the generative reinforcement learning systems. In this paper, we introduce a versatile multi-agent scientific exploration and draft outline research assistant (DORA), which provides multiple templates and workflows for automated or semi-automated research studies and report generation. Under user guidance, it employs hierarchical teams of AI agents based on the plug-and-play generalist and domain-specific large language models (LLMs) exploiting a variety of specialized research tools and open data repositories and generates high-quality research outputs publication drafts with maximally-accurate references. DORA is designed to minimize the time and effort required for manuscript preparation, thereby enabling researchers to devote more attention to high-value discovery tasks. The system is constantly evolving with user feedback with regular feature and resource updates. The platform is available at https://dora.insilico.com

Similar Papers

biorxiv
Fri Mar 07 2025
Peptide generative design with weakly order-dependent autoregressive language model and lifelong learning
Bioactive peptides have become strong candidates for a variety of clinical therapies due to their diverse advantages, which promotes the development of deep generative models for peptide design. Considering that existing methods cannot effectively deal with the conformational flexibility of peptides and are difficult to capture accurate residue-to-residue interaction dependencies, we propose a uni...
Nie, Z.
•
Li, D.
•
Liu, Y.
•
Xu, F.
...•
Chen, J.
biorxiv
Fri Mar 07 2025
CIA: a Clustering Independent Annotation method to investigate cell identities in scRNA-seq data
Single-cell RNA sequencing (scRNA-seq) has revolutionized our understanding of the transcriptional landscape of complex tissues, enabling the discovery of novel cell types and biological functions. However, the identification and classification of cells from scRNA-seq datasets remain significant challenges. To address this, we developed a new computational tool called CIA (Clustering Independent A...
Ferrari, I.
•
Battistella, M.
•
Vincenti, F.
•
Gobbini, A.
...•
Galeota, E.
biorxiv
Fri Mar 07 2025
Structural annotation of full-scan MS data: A unified solution for LC-MS and MS imaging analyses
Public liquid chromatography-mass spectrometry (LC-MS) and MS imaging metabolomics data repositories contain millions of files, with over 40% of them consisting solely of MS1 (full-scan) information, creating a significant gap in data reuse potential due to limited annotation capabilities. Here, we present ms1-id, an open-source Python package providing a unified solution for structural annotation...
Xing, S.
•
Charron-Lamoureux, V.
•
Ekelöf, M.
•
El Abiead, Y.
...•
Dorrestein, P. C.
biorxiv
Fri Mar 07 2025
Protein stability prediction with dual-view ensemble learning from single sequence
Predicting the protein stability changes upon mutations is one of the effective ways to improve the efficiency of protein engineering. Here, we propose a dual-view ensemble learning-based framework, DVE-stability, for protein stability prediction from single sequence. DVE-stability integrates the global and local dependencies of mutations to capture the intramolecular interactions from two views t...
Nie, Z.
•
Ma, Y.
•
Liu, Y.
•
Huang, X.
...•
Chen, J.
biorxiv
Fri Mar 07 2025
NTxPred2: A large language model for predicting neurotoxic peptides and neurotoxins
Most of the existing methods including our NTxPred, use a single model to predict both neurotoxic peptides and neurotoxic proteins (neurotoxins). In this study, we developed distinct models for predicting neurotoxic peptides and neurotoxins. Our peptide dataset consists of 877 neurotoxic and 877 non-neurotoxic peptides, while our protein dataset includes 775 neurotoxins and 775 non-neurotoxins. Pr...
Rathore, A. S.
•
Jain, S.
•
Choudhury, S.
•
Raghava, G. P. S.
biorxiv
Fri Mar 07 2025
Exploring the structural diversity and evolution of the D1 subunit of photosystem II using AlphaFold and Foldtree
While our knowledge of photosystem II has expanded to time-resolved atomic details, the diversity of experimental structures of the enzyme remains limited. Recent advances in protein structure prediction with AlphaFold offer a promising approach to fill this gap in structural diversity in non-model systems. This study used AlphaFold to predict the structures of the D1 protein, the core subunit of ...
Kim, T. D.
•
Pretorius, D.
•
Murray, J. W.
•
Cardona, T.
biorxiv
Fri Mar 07 2025
Harnessing A Unified Multi-modal SequenceModeling to unveil Protein-DNA Interdependency
The interdependent orchestration of proteins, coding DNA sequences (CDS), and adjacent regulatory DNA elements underpins biological functionality, where evolutionary constraints shape codon usage, transcriptional regulation, and structural stability. We present ProDMM, a multimodal framework that deciphers these systemic relationships through unified sequence modeling. Integrating a context-aware ...
Li, M.
•
Ren, Y.
•
Ye, P.
•
Cheng, J.
...•
Tan, P.
biorxiv
Fri Mar 07 2025
scRL: Utilizing Reinforcement Learning to Evaluate Fate Decisions in Single-Cell Data
The rapid development of single-cell sequencing offers an unparalleled opportunity to delineate the heterogeneity of individual cells. However, current methods struggle to pinpoint the states of cell fate decisions. In this study, we introduce a novel approach called Single-cell Reinforcement Learning (scRL), which integrates reinforcement learning into single-cell data analysis using an actor-cri...
Fu, Z.
•
Chen, C.
•
Wang, S.
•
Wang, J.
•
Chen, S.
biorxiv
Fri Mar 07 2025
BioFuse: An Embedding Fusion Framework for Biomedical Foundation Models
The biomedical field has witnessed a surge in pre-trained foundation models excelling in specific sub-domains such as radiology and histopathology. While integrating these models promises a more comprehensive understanding of biomedical data, it poses challenges in model compatibility and feature fusion. We present BioFuse, a novel open-source framework designed to generate optimised biomedical em...
Hossain, M. N.
•
Harris-Birtill, D.