D&D Pharmatech’s US subsidiary launches AI genomics platform built on ‘tens of millions of’ single cells

D&D Pharmatech’s U.S. subsidiary, Valted Seq, said Tuesday (local time) that it has launched SCADE, an AI-powered single-cell genomics platform trained on "tens of millions" of in-house brain tissue samples, aiming to streamline biomarker discovery, drug development, and precision medicine.

SCADE—short for Single Cell AI Discovery Engine—is built on a proprietary data engine sourced from post-mortem frozen brain tissue collected via biobank partnerships with Johns Hopkins University and Banner Health Institute.

Using GPU-optimized models trained on this data, the platform enables non-coders, including biologists and clinicians, to analyze single-cell datasets via a user-friendly dashboard.

Valted Seq, a U.S. subsidiary of D&D Pharmatech, developed the AI-powered SCADE platform to analyze single-cell genomic data at scale.

“Analyzing genomics data, let alone from single cells, is incredibly complex. However, with SCADE we are democratizing that process,” said Bardia Nezami, CEO of Valted Seq, in a statement. “It enables robust analysis and interpretation at a scale never before possible expediting the journey toward life-saving breakthroughs.”

Valted Seq says the tool sidesteps the limits of mainstream AI models like ChatGPT or Gemini, which it claims “fail to solve complex genomics problems because of a lack of specific domain knowledge and/or fine-tuning.” In contrast, SCADE incorporates layered, task-specific models tailored to neurology, oncology, microbiology, and immunology applications.

The company also developed a benchmarking framework for AI models in single-cell analysis, focusing on core tasks like cell type annotation. In internal tests, existing models achieved only 25 percent code execution success and 14 percent accuracy, while SCADE delivered 96 percent and 36 percent, respectively, according to Tuesday’s release.

“Our goal is to enable scientists such as biologists and biochemists to perform genomics and bioinformatics without writing computer code,” said Nezami. “We have made this possible by training our AI models on high-quality, homogeneous single cell big data generated in-house consisting of tens of millions of cells.”

The platform’s key features include robotics-driven big data generation, fast multi-dataset processing, a no-code interface for analysis and reporting, and flexible scalability across research and clinical settings. Valted Seq says the system reduces analysis time while boosting accuracy by minimizing false positives and negatives.

“AI-driven platforms like SCADE are no longer just ‘nice to have’; they are rapidly becoming the foundation upon which modern genomic science stands,” said Nezami. “Researchers worldwide are seeking innovative tools that can streamline the interpretation of complex genomics data at a very large scale and help them keep pace with rapid advancements in precision medicine.”

Valted Seq says it has already identified several novel biomarkers and therapeutic targets from its brain database, with preclinical validation underway.