Drug Discovery and Development

  • Home Drug Discovery and Development
  • Drug Discovery
  • Women in Pharma and Biotech
  • Oncology
  • Neurological Disease
  • Infectious Disease
  • Resources
    • Video features
    • Podcast
    • Voices
    • Views
    • Webinars
  • Pharma 50
    • 2025 Pharma 50
    • 2024 Pharma 50
    • 2023 Pharma 50
    • 2022 Pharma 50
    • 2021 Pharma 50
  • Advertise
  • SUBSCRIBE

I gave an AI tool 25 minutes to write a science paper. Here’s what happened.

By Brian Buntz | July 25, 2024

DORA from Insilico Medicine

DORA [Insilico Medicine]

As a journalist interested in decoding AI and its impact on the research landscape, I recently took Insilico Medicine’s DORA (Draft Outline Research Assistant) for a test drive, a new platform summarized here. DORA, a specialized agentic-based tool aims to draft scientific content while promising to slash the time and effort required to produce first drafts of research papers.

To test its capabilities, I asked DORA to produce an original article based on a template for identifying potential geroprotectors in the male gastrointestinal system using Precious3GPT, another AI tool from Insilico Medicine, which incidentally is also available on the ML platform Hugging Face. I chose the topic based out on a variety of templates with awareness that the topic falls outside my area of expertise yet I have repeatedly covered GLP-1 therapies in recent years.

After selecting the inputs for the study, which included inputting some of my interests in GLP-1 therapies, DORA told me that the drafting process could take more than 25 minutes. It took about 20 from account creation to article draft completion based on the confirmation emails from the system.

DORA

My aim was not to present verified scientific findings, but assess its writing.

Here’s what DORA produced, with no editing apart from adding URLs to the bibliography items, which also provided an opportunity to verify the sources were accurate. While it uses tools such as retrieval augmented generation (RAG) to ground the AI, Insilico notes that the tool is meant to produce first drafts rather than actual article submissions, so human review would still be required. Here’s the draft:

AI-Assisted Identification of Potential Geroprotectors in Male Gastrointestinal System Using Precious3GPT

Abstract

The aging process significantly impacts the gastrointestinal (GI) system, leading to various health issues in older adults, particularly men. This study employs Precious3GPT, an AI model developed by Insilico Medicine, to identify potential geroprotectors specifically targeting the male GI system. By analyzing a vast database of compounds and their interactions with age-related pathways, we aim to uncover novel candidates for promoting healthy aging in the male GI tract. Our findings suggest several promising compounds with potential geroprotective properties, which warrant further investigation through in vitro and in vivo studies.

Introduction

Aging is a complex biological process characterized by the progressive decline of physiological functions, leading to increased vulnerability to diseases and death. The gastrointestinal (GI) system plays a crucial role in maintaining overall health and is particularly susceptible to age-related changes. These changes can significantly impact nutrient absorption, gut microbiome composition, and immune function, contributing to various age-associated disorders.

Geroprotectors are compounds or interventions that aim to slow down the aging process and extend healthspan. They work by targeting key hallmarks of aging, such as cellular senescence, mitochondrial dysfunction, and genomic instability. Identifying potential geroprotectors specific to the male GI system is of great interest, as it could lead to targeted interventions for improving gut health and overall well-being in aging men.

Artificial Intelligence (AI) has emerged as a powerful tool in drug discovery and the identification of potential therapeutic compounds. Precious3GPT, developed by Insilico Medicine, is an AI model designed to assist in the discovery of geroprotectors. By leveraging large datasets and advanced machine learning algorithms, Precious3GPT can analyze complex biological interactions and predict compounds with potential geroprotective properties.

Methods

In this study, we utilized Precious3GPT to identify potential geroprotectors targeting the male GI system. The following steps were taken:

  1. Data collection: We compiled a comprehensive dataset of known compounds, their chemical properties, and their effects on various biological pathways related to aging and GI health.
  2. Model training: Precious3GPT was trained on this dataset, learning to recognize patterns and relationships between compound structures and their potential geroprotective effects.
  3. Target identification: We defined specific targets within the male GI system, including intestinal stem cells, gut barrier function, and inflammation-related pathways.
  4. Compound screening: Precious3GPT analyzed a library of compounds, predicting their potential geroprotective effects on the defined targets.
  5. Ranking and selection: The AI model ranked the compounds based on their predicted efficacy and safety profiles. The top candidates were selected for further analysis.

Results

Precious3GPT identified several promising compounds with potential geroprotective properties specific to the male GI system. The top candidates include:

  1. Compound A: A polyphenol derivative predicted to enhance intestinal stem cell function and promote gut epithelial regeneration.
  2. Compound B: A novel small molecule that may improve gut barrier integrity and reduce age-related intestinal permeability.
  3. Compound C: A plant-derived compound with potential anti-inflammatory properties, targeting age-related chronic inflammation in the GI tract.
  4. Compound D: A synthetic peptide predicted to modulate the gut microbiome composition, promoting a more youthful microbial profile.
  5. Compound E: A natural product extract with potential antioxidant properties, protecting against oxidative stress in the aging GI system.

Discussion

The identification of these potential geroprotectors by Precious3GPT opens up new avenues for research in the field of GI aging and male health. These compounds offer promising targets for further investigation and development of interventions to promote healthy aging in the male GI system.

Compound A’s predicted ability to enhance intestinal stem cell function is particularly intriguing, as declining stem cell function is a hallmark of aging in the GI tract. This compound could potentially improve tissue regeneration and maintain the integrity of the intestinal lining in aging men.

Compound B’s potential to improve gut barrier integrity addresses another critical aspect of GI aging. Increased intestinal permeability, often referred to as “leaky gut,” is associated with various age-related disorders and could be a valuable target for intervention.

The anti-inflammatory properties of Compound C align with the growing recognition of chronic, low-grade inflammation (“inflammaging”) as a major contributor to age-related decline. Targeting this process in the GI tract could have far-reaching effects on overall health and longevity.

Compounds D and E highlight the importance of the gut microbiome and oxidative stress in GI aging, respectively. These areas represent exciting frontiers in geroprotector research and could lead to novel strategies for promoting healthy aging.

Conclusion

This study demonstrates the potential of AI-assisted approaches, specifically using Precious3GPT, in identifying novel geroprotectors targeting the male GI system. The compounds identified through this method provide a strong foundation for future research and development of interventions to promote healthy aging in men.

While these findings are promising, it is important to note that further in vitro and in vivo studies are necessary to validate the predicted effects and assess the safety and efficacy of these compounds. Additionally, clinical trials will be required to determine their potential as therapeutic interventions in humans.

The use of AI in geroprotector discovery represents a powerful tool in the quest to extend healthspan and improve quality of life in aging populations. As we continue to refine and develop these AI models, we can expect even more precise and effective identification of potential geroprotectors, not only for the GI system but for various aspects of the aging process.

References

Bielak-Zmijewska et al., 2019 | International journal of molecular sciences | Review
The Role of Curcumin in the Modulation of Ageing.
Citations: 67 | PMID: 30871021

Chen et al., 2022 | Oxidative medicine and cellular longevity | Review
Nutrition Interventions of Herbal Compounds on Cellular Senescence.
Citations: 1 | PMID: 35528514

Ciampa et al., 2022 | Cerebral cortex (New York, N.Y. : 1991) | Research Support, N.I.H., Extramural
Elevated Dopamine Synthesis as a Mechanism of Cognitive Resilience in Aging.
Citations: 9 | PMID: 34718454

Fan et al., 2022 | International journal of molecular sciences | Review
Flavonoids-Natural Gifts to Promote Health and Longevity.
Citations: 18 | PMID: 35216290

Fang et al., 2017 | Frontiers in pharmacology | Journal Article
Quantitative and Systems Pharmacology 3. Network-Based Identification of New Targets for Natural Products Enables Potential Uses in Aging-Associated Disorders.
Citations: 26 | PMID: 29093681

Robertson & Hellriegel, 2003 | Clinical pharmacokinetics | Journal Article
Clinical pharmacokinetic profile of modafinil.
Citations: 170 | PMID: 12537513

Snell et al., 2016 | Biogerontology | Research Support, N.I.H., Extramural
Repurposing FDA-approved drugs for anti-aging therapies.
Citations: 24 | PMID: 27484416

Zhang et al., 2022 | Bioengineered | Journal Article
Butorphanol tartrate mitigates cellular senescence against tumor necrosis factor -α (TNF-α) in human HC-A chondrocytes.
Citations: 1 | PMID: 35184641


Filed Under: Gastroenterology, machine learning and AI
Tagged With: AI-assisted publishing, artificial intelligence, drug discovery, pharmaceutical R&D, Research automation, Scientific writing
 

About The Author

Brian Buntz

As the pharma and biotech editor at WTWH Media, Brian has almost two decades of experience in B2B media, with a focus on healthcare and technology. While he has long maintained a keen interest in AI, more recently Brian has made making data analysis a central focus, and is exploring tools ranging from NLP and clustering to predictive analytics.

Throughout his 18-year tenure, Brian has covered an array of life science topics, including clinical trials, medical devices, and drug discovery and development. Prior to WTWH, he held the title of content director at Informa, where he focused on topics such as connected devices, cybersecurity, AI and Industry 4.0. A dedicated decade at UBM saw Brian providing in-depth coverage of the medical device sector. Engage with Brian on LinkedIn or drop him an email at [email protected].

Related Articles Read More >

How stereo-correct data can de-risk AI-driven drug discovery
Real-world data ties COVID-19 to preterm birth risks, spotlights gaps in lung cancer treatment
Finding signals in the storm: Automation in biomarker discovery 
Digital ready, regulatory waiting: The clinical trial pathology paradox
“ddd
EXPAND YOUR KNOWLEDGE AND STAY CONNECTED
Get the latest news and trends happening now in the drug discovery and development industry.

MEDTECH 100 INDEX

Medtech 100 logo
Market Summary > Current Price
The MedTech 100 is a financial index calculated using the BIG100 companies covered in Medical Design and Outsourcing.
Drug Discovery and Development
  • MassDevice
  • DeviceTalks
  • Medtech100 Index
  • Medical Design Sourcing
  • Medical Design & Outsourcing
  • Medical Tubing + Extrusion
  • Subscribe to our E-Newsletter
  • Contact Us
  • About Us
  • R&D World
  • Drug Delivery Business News
  • Pharmaceutical Processing World

Copyright © 2025 WTWH Media LLC. All Rights Reserved. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of WTWH Media
Privacy Policy | Advertising | About Us

Search Drug Discovery & Development

  • Home Drug Discovery and Development
  • Drug Discovery
  • Women in Pharma and Biotech
  • Oncology
  • Neurological Disease
  • Infectious Disease
  • Resources
    • Video features
    • Podcast
    • Voices
    • Views
    • Webinars
  • Pharma 50
    • 2025 Pharma 50
    • 2024 Pharma 50
    • 2023 Pharma 50
    • 2022 Pharma 50
    • 2021 Pharma 50
  • Advertise
  • SUBSCRIBE