New AI Pipeline Revolutionizes Molecular Target Identification

When researchers create new molecules whether for agricultural applications, species management, or life-saving medications it is essential to identify their specific targets. A comprehensive understanding of a molecule's interactions, both intended and unintended, is vital for confirming its safety and effectiveness.

Inspired by a cone snail toxin that influences both fish and insects, scientists at the Weizmann Institute have devised an innovative method for identifying molecular targets. By integrating artificial intelligence with conventional research techniques, they established a system capable of predicting which proteins natural toxins will impact, with significant implications for ecological studies and pharmaceutical development.

This research will be showcased at the 69th Biophysical Society Annual Meeting, scheduled for February in Los Angeles.

Izhar Karbat, PhD, and Eitan Reuveny, PhD, both affiliated with the Weizmann Institute, aimed to understand how the cone snail toxin, Conkunitzin-S1 (Cs1), affects fish, which are prey for cone snails.

Cs1 is recognized for its ability to block potassium channels and critical pathways for cellular function and has a strong effect on fruit flies and various insects, but does not affect mammals or other organisms like mollusks. However, the specific targets of Cs1 in fish remained unclear.

Three years ago, we tried our best tools at the time to find the target of the Conkunitzin toxin, and we failed because the tools were not good enough. And then came a big revolution in structural biology driven by artificial intelligence.”

Izhar Karbat, Weizmann Institute

In their most recent effort, he and Reuveny identified the fish potassium channels most susceptible to Cs1 using a two-pronged computational approach.

Initially, they utilized AlphaFold, an advanced AI tool, to forecast how the toxin might interact with various fish potassium channels. Subsequently, they created ET3, a novel AI model designed to examine the movement of water molecules around these channels.

ET3 was trained to detect anomalies in the movement of water molecules surrounding the “selectivity filter” the section of the channel that regulates which ions can pass through. Blocking this filter effectively disables the channel.

By leveraging ET3 to investigate a broad array of fish potassium channels, far exceeding the capabilities of earlier methods, they successfully identified the specific channels targeted by Cs1 and elucidated how it disrupts their normal function.

Essentially, if potassium channels are likened to small doors controlling ion flow in and out of cells, Cs1 functions as a lock that prevents these doors from opening.

Using molecular dynamics and the new AI-driven structural tools we were able to find the small subset of channels in fish which bind our toxins with high affinity and are probably the real target of the cone snail. This new pipeline offers exciting opportunities and prospects with ecological studies, to study real chemical interactions in real ecological systems.”

Izhar Karbat, Weizmann Institute

He also mentioned its potential application in drug development to identify targets based on a drug’s structure or to uncover possible off-target interactions.

For instance, Karbat stated, “If you develop a drug that would activate a channel in the human brain, you would not want the same drug to affect a channel in the human heart and cause a heart attack.”

The power of this pipeline is that we can concentrate on a target, or any molecule that we are interested in, and find its match.”

Eitan Reuveny, Weizmann Institute