How Adding One Database Changed Everything: The ChEMBL Integration Story

📰 Medium · Data Science

Integrating the ChEMBL database into an AI system improved its performance on infectious diseases, demonstrating the importance of high-quality data in AI development

intermediate Published 21 Apr 2026

Action Steps

Identify gaps in your AI system's performance, particularly in specific domains or datasets
Research and select relevant databases to integrate into your system, such as ChEMBL for biomedical data
Design and implement a data integration pipeline to incorporate the new database
Evaluate the impact of the integrated database on your AI system's performance
Refine and optimize the system as needed to maximize the benefits of the integrated data

Who Needs to Know This

Data scientists and AI engineers can benefit from this story as it highlights the impact of data integration on AI system performance, and how a single database can make a significant difference

Key Insight

💡 High-quality data is crucial for AI system performance, and integrating relevant databases can significantly improve results

Key Takeaways

Integrating the ChEMBL database into an AI system improved its performance on infectious diseases, demonstrating the importance of high-quality data in AI development

Full Article

Title: How Adding One Database Changed Everything: The ChEMBL Integration Story

URL Source: https://kelyn-njeri.medium.com/how-adding-one-database-changed-everything-the-chembl-integration-story-c35ffcaf2a4b?source=rss------data_science-5

Published Time: 2026-04-21T12:01:02Z

Markdown Content:
# How Adding One Database Changed Everything: The ChEMBL Integration Story | by Kelyn Njeri | Apr, 2026 | Medium

[Sitemap](https://kelyn-njeri.medium.com/sitemap/sitemap.xml)

[Open in app](https://play.google.com/store/apps/details?id=com.medium.reader&referrer=utm_source%3DmobileNavBar&source=post_page---top_nav_layout_nav-----------------------------------------)

Sign up

[Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fkelyn-njeri.medium.com%2Fhow-adding-one-database-changed-everything-the-chembl-integration-story-c35ffcaf2a4b&source=post_page---top_nav_layout_nav-----------------------global_nav------------------)

[](https://medium.com/?source=post_page---top_nav_layout_nav-----------------------------------------)

Get app

[Write](https://medium.com/m/signin?operation=register&redirect=https%3A%2F%2Fmedium.com%2Fnew-story&source=---top_nav_layout_nav-----------------------new_post_topnav------------------)

[Search](https://medium.com/search?source=post_page---top_nav_layout_nav-----------------------------------------)

Sign up

[Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fkelyn-njeri.medium.com%2Fhow-adding-one-database-changed-everything-the-chembl-integration-story-c35ffcaf2a4b&source=post_page---top_nav_layout_nav-----------------------global_nav------------------)

![Image 1](https://miro.medium.com/v2/resize:fill:64:64/1*dmbNkD5D-u45r44go_cf0g.png)

Member-only story

# How Adding One Database Changed Everything: The ChEMBL Integration Story

[![Image 2: Kelyn Njeri](https://miro.medium.com/v2/resize:fill:64:64/1*8lAANczgQJHEXJMGAbbUCQ.jpeg)](https://kelyn-njeri.medium.com/?source=post_page---byline--c35ffcaf2a4b---------------------------------------)

[Kelyn Njeri](https://kelyn-njeri.medium.com/?source=post_page---byline--c35ffcaf2a4b---------------------------------------)

Follow

3 min read

·

1 hour ago

[](https://medium.com/m/signin?actionUrl=https%3A%2F%2Fmedium.com%2F_%2Fvote%2Fp%2Fc35ffcaf2a4b&operation=register&redirect=https%3A%2F%2Fkelyn-njeri.medium.com%2Fhow-adding-one-database-changed-everything-the-chembl-integration-story-c35ffcaf2a4b&user=Kelyn+Njeri&userId=8084afd94c4b&source=---header_actions--c35ffcaf2a4b---------------------clap_footer------------------)

[](https://medium.com/m/signin?actionUrl=https%3A%2F%2Fmedium.com%2F_%2Fbookmark%2Fp%2Fc35ffcaf2a4b&operation=register&redirect=https%3A%2F%2Fkelyn-njeri.medium.com%2Fhow-adding-one-database-changed-everything-the-chembl-integration-story-c35ffcaf2a4b&source=---header_actions--c35ffcaf2a4b---------------------bookmark_footer------------------)

[Listen](https://medium.com/m/signin?actionUrl=https%3A%2F%2Fmedium.com%2Fplans%3Fdimension%3Dpost_audio_button%26postId%3Dc35ffcaf2a4b&operation=register&redirect=https%3A%2F%2Fkelyn-njeri.medium.com%2Fhow-adding-one-database-changed-everything-the-chembl-integration-story-c35ffcaf2a4b&source=---header_actions--c35ffcaf2a4b---------------------post_audio_button------------------)

Share

Press enter or click to view image in full size

![Image 3](https://miro.medium.com/v2/resize:fit:700/0*qc7DZa6yc2wwruKb)

Photo by [Vedrana Filipović](https://unsplash.com/@vedranafilipovic?utm_source=medium&utm_medium=referral) on [Unsplash](https://unsplash.com/?utm_source=medium&utm_medium=referral)

Sometimes the biggest improvement in an AI system comes not from a better algorithm, but from better data.

NeoRx v1 used seven biomedical databases to build disease knowledge graphs. It worked well on cancer and metabolic diseases. It completely failed on infectious diseases — Grade F for both malaria and Ebola, Grade C for HIV.

NeoRx v2 added one database:

Read full article → ← Back to Reads

How Adding One Database Changed Everything: The ChEMBL Integration Story

Key Takeaways

Full Article

Related Videos