How AI Discovered 3,500 Mental Wellness Compounds in 5 Months — What Took Traditional Labs Years

Nanyang Biologics' Vecura platform, powered by NVIDIA GPU infrastructure, is rewriting the rules of natural ingredient discovery.

‍

The wellness industry has a dirty secret: most of the "natural" ingredients in your stress-relief supplements and focus-enhancing drinks come from a remarkably small, decades-old playbook. Caffeine. Theanine. GABA analogs. These legacy compounds have been recycled across thousands of products with limited mechanistic clarity and even less differentiation.

‍

Meanwhile, the World Health Organization reports that more than 970 million people worldwide live with mental disorders, and post-pandemic demand for mood-regulating and stress-relieving products has never been higher. The gap between what consumers need and what science has delivered is widening.

‍

Nanyang Biologics (NYB), a Singapore-based AI-native biotechnology company spun out of Nanyang Technological University, set out to close that gap; not with incremental improvements, but with a fundamentally different approach to discovery.

‍

Project X: From 700,000 Compounds to Market-Ready Leads

When a global consumer health conglomerate approached NYB with a challenge, discover plant-derived compounds for emotional balance, focus, and stress resilience, the team turned to their proprietary Vecura platform and its specialized DTIGN engine for drug-target interaction prediction.

‍

The results were striking.

‍

Starting from a natural compound library of over 700,000 molecules sourced from Southeast Asia's diverse ecosystems — plants, fungi, animals, and insects — the team identified 3,500 compounds with high bioactivity and low toxicity across 156 key neuromodulatory receptors and transporters. These targets span the serotonergic, dopaminergic, glutamatergic, and GABAergic pathways most commonly associated with mood, cognition, stress response, and neuroplasticity.

‍

The entire journey from target definition to lead recommendation took five months. By comparison, conventional high-throughput screening (HTS) typically yields hit rates below 1% — often as low as 0.01–0.1% — requires multi-day campaigns to process more than 100,000 samples, and costs $0.10–$1.50 per compound screened.

‍

NYB's AI-driven pipeline delivered a 64× higher hit rate, 7× broader compound coverage than known databases, and 6× faster discovery and validation cycles than traditional methods.

‍

The Engine Behind the Results: Vecura and LigoSPACE

At the heart of NYB's capability is Vecura, a modular discovery platform that integrates over 200 AI models into a single, no-code interface spanning the full small molecule discovery pipeline: from target identification and hit screening to lead optimization and preclinical validation design.

‍

What makes Vecura distinctive is not just breadth but depth. The platform's proprietary AI engine, DTIGN (now evolved into LigoSPACE, or DTIGN 2.0), uses interaction-based 3D graph neural networks to predict compound-target interactions with a level of spatial awareness that most competing approaches miss entirely.

‍

Where conventional models rely on ligand-based 2D representations, LigoSPACE models the spatial emptiness around ligands; the vacant space in binding pockets that determines whether a drug can successfully inhibit a target or will be displaced by endogenous substrates. It integrates multiple binding pockets through a unified geometric representation, combining techniques called GeoREC and Union-Pocket to capture protein-ligand interaction geometry with high fidelity.

‍

The numbers speak for themselves: LigoSPACE delivers an 18.39% improvement in bioactivity prediction (Pearson correlation), a 9.93% improvement in accuracy (RMSE), and a 19.09% improvement in ligand ranking (Kendall tau) over baseline models. The work has been published in IEEE and presented at NeurIPS; rigorous peer-reviewed validation that sets NYB apart from platforms making claims without published benchmarks.

‍

Powered by NVIDIA: The Computational Backbone

Discovery at this scale; screening 100,000 compounds per target across dozens of neurological targets, demands serious computational firepower. NYB's pipeline runs on NVIDIA GPU infrastructure, a strategic partnership that enables the massive parallelized computation required for 3D graph neural network inference at production scale.

‍

On a 16-GPU configuration, NYB's DTIGN engine processes 100,000 compounds per target; a 10× throughput advantage over the 10,000-compound capacity of traditional HTS setups. This isn't just about speed; it's about the ability to explore chemical space comprehensively rather than sampling a tiny fraction of it.

‍

NVIDIA's GPU architecture is particularly well-suited to the geometric deep learning at the core of LigoSPACE, where modeling the 3D spatial relationships between protein structures and small molecules requires the kind of tensor computation that GPUs were built to accelerate. NYB's strategic programs with NVIDIA, alongside infrastructure partners Equinix and HPE, provide the computational foundation that makes screening a library of 1 million natural compounds practically feasible rather than theoretically possible.

‍

Vecurate: The Data Moat

Technology alone doesn't create defensibility, data does. NYB's compound library, Vecurate, is the world's largest digitized collection of natural compounds, containing over 1 million molecules sourced from more than 50,000 tropical species with ethnobotanical context, classified across more than 100 curated families by structure and bioactivity.

‍

This library draws from underexplored plants, microbes, and marine organisms across Southeast Asia, a region of extraordinary biodiversity that remains largely uncharacterized by Western pharmaceutical research. In fact, 99% of nature's chemistry remains uncharacterized globally, and only about 20% of known plant species have been screened for bioactivity. Vecurate is purpose-built for seamless integration with LigoSPACE, creating a flywheel where each discovery campaign enriches the dataset for future ones.

‍

For Project X, this data advantage translated directly into outcomes: the library contained 7× more compounds relevant to the mental wellness targets than what is commonly known to academia and industry.

‍

From Prediction to Product: The Full Pipeline

What separates NYB from pure computational platforms is the end-to-end nature of the workflow. Project X didn't stop at AI prediction. The pipeline moved through seven distinct phases, each with concrete deliverables and timelines:

‍

Market intelligence analysis of 120,000+ SKUs and 15,000+ consumer reviews identified unmet needs and mapped 38 whitespace ingredient clusters across APAC and EU markets completed in a single day. Target identification prioritized serotonin, dopamine, GABA, and glutamate pathways, drawing from 12,000+ publications to identify 156 neuromodulatory targets in one week. Ingredient selection screened 700,000+ natural compounds and selected 3,500 bioactives with greater than 85% confidence another week. Formulation strategy simulated 250+ combinations for safety, synergy, and delivery, selecting 6 formulations with over 90% predicted bioavailability. Wet lab validation of 15 lead compounds was executed at the NYB-NTU joint laboratory using both in vitro cellular assays and in vivo behavioral models.

‍

Claim substantiation and regulatory compliance, targeting GRAS, EFSA, and ASEAN frameworks are currently in progress, with early-stage composition filings already prepared.

‍

This is the shift Vecura enables: biological confidence established upstream, where risk is lowest and impact is highest, so that everything downstream; formulation, manufacturing, regulatory, commercial — accelerates. NYB estimates a 70% reduction in time to formulation compared to traditional methods.

‍

Broader Implications

Project X is a proof point, but the implications extend well beyond mental wellness. The same framework of target definition, AI-driven screening, and iterative validation applies equally to sleep, cognition, metabolic balance, skin health, and functional food development. NYB currently has active pilot engagements spanning pharmaceuticals, consumer health, cosmeceuticals, food and nutrition, and animal health across the globe.

‍

For the consumer health industry specifically, this represents a paradigm shift. Instead of relying on historical usage or generic extraction, the approach that has kept the industry recycling the same handful of ingredients for decades, companies can now pursue ingredient innovation grounded in molecular evidence and AI precision, with proprietary IP protection built in from the start.

‍

The competitive landscape tells the story. In NYB's own assessment of AI integration depth versus application domain reach, they occupy a unique position: full-stack AI capability (from discovery through validation) combined with multi-sector coverage. Most AI drug discovery platforms — Recursion, Insilico Medicine, Exscientia, Atomwise — focus narrowly on pharmaceuticals with varying degrees of AI integration. Natural ingredient players like Brightseed and Enveda operate with moderate AI depth but limited domain reach. NYB bridges both dimensions.

‍

What Comes Next

As regulatory, safety, and consumer expectations continue to rise, the bar for wellness ingredients is moving beyond "generally recognized as safe" toward "mechanistically validated and differentiated." The companies that will win in this environment are those that can discover novel bioactives faster, validate them more rigorously, and protect them with defensible IP.

‍

NYB's combination of LigoSPACE (running on NVIDIA GPU infrastructure), the Vecurate compound library, the Vecura orchestration platform, and the NTU wet lab validation pipeline creates exactly the kind of integrated capability that this new era demands.

‍

Project X proved it works. The question for the rest of the industry is how long they can afford to keep screening the old way.

‍

Nanyang Biologics (NYB) is an AI-native biotechnology company headquartered in Singapore, founded in 2019 as a spin-off from Nanyang Technological University. The company's Vecura platform powers end-to-end molecular discovery across pharmaceuticals, consumer health, cosmeceuticals, and food innovation. NYB is a winner of SuperAI Genesis 2025 and maintains strategic partnerships with NVIDIA, Equinix, and HPE.