STOCK TITAN

Tevogen.AI Reports Advancements in PredicTcell™ Beta, Demonstrates Improved Precision Metrics and Expands Proprietary AI Infrastructure

Rhea-AI Impact
(Moderate)
Rhea-AI Sentiment
(Neutral)
Tags
AI

Tevogen (Nasdaq: TVGN) reported advances in its Tevogen.AI PredicTcell™ beta, citing improved model metrics and expanded proprietary data and infrastructure on March 13, 2026.

The company reports a database of 655 million peptide sequences, training on 1.8 million data points, recall rising to 92%, and precision to 48%.

Loading...
Loading translation...

Positive

  • Database expanded to 655 million peptide sequences
  • Recall improved from 87% to 92%
  • Precision increased from 40% to 48% (20% relative gain)
  • Model scale trained on 1.8 million data points (~20x more robust)
  • Three production AI agents enable continuous learning and literature monitoring

Negative

  • Model precision remains under 50%, leaving substantial false positives
  • No binding pharmaceutical partnerships announced to advance peptide candidates

Key Figures

Peptide sequences: 655 million Proteins covered: 24 million Total data points: 16 billion +5 more
8 metrics
Peptide sequences 655 million Proprietary database size across disease areas
Proteins covered 24 million Source proteins for peptide sequences
Total data points 16 billion Data points in AI training dataset
Publications analyzed 37 million Scientific articles feeding continuous enrichment
Recall improvement 87% to 92% PredicTcell™ beta testing performance
Precision improvement 40% to 48% PredicTcell™ beta testing performance
Training data points 1.8 million Current PredicTcell™ training set size
Active peptide candidates 14 Monitored by production AI agents

Market Reality Check

Price: $5.38 Vol: Volume 33,152 vs 20-day a...
normal vol
$5.38 Last Close
Volume Volume 33,152 vs 20-day average 31,517 (relative volume 1.05x) shows only modestly elevated trading. normal
Technical Price $6.38 is well below the 200-day MA of $35.01, and sits 91.55% under the 52-week high and 2.61% above the 52-week low.

Peers on Argus

TVGN fell 14.71% while close peers showed smaller mixed moves (e.g., KYTX -1.46%...
2 Up

TVGN fell 14.71% while close peers showed smaller mixed moves (e.g., KYTX -1.46%, CRBU -2.07%, NTHI -4.36%, VTYX +0.07%). Momentum names SLS (+8.75%) and ELTX (+10.92%) moved up, underscoring stock-specific pressure in TVGN rather than a broad sector drop.

Previous AI Reports

5 past events · Latest: Sep 25 (Positive)
Same Type Pattern 5 events
Date Event Sentiment Move Catalyst
Sep 25 PredicTcell data expansion Positive +1.5% PredicTcell beta dataset and features expanded sharply with stronger metrics.
Sep 10 AI conference participation Positive -1.4% CIO featured PredicTcell at Databricks AI event to showcase platform.
Aug 11 AI growth letter Positive +8.8% Stockholder letter highlighted AI expansion, capital position, and partnerships.
Aug 7 AI grant funding Positive -8.8% Non-dilutive $1M grant for Tevogen.AI within larger $10M agreement.
Aug 01 AI strategy letter Positive +1.1% Letter detailed AI expansion, PredicTcell launch, and strategic partnerships.
Pattern Detected

AI-related news has generally been positive but produced mixed share reactions, with three aligned upward moves and two negative divergences.

Recent Company History

Recent AI-tagged releases for Tevogen (TVGN) highlighted growth of the PredicTcell™ platform, expansion of datasets to billions of records, and strategic collaborations with Microsoft and Databricks. Funding of $1 million within a broader $10 million grant and access to a $36 million credit line supported Tevogen.AI’s build-out. Today’s announcement of improved PredicTcell™ precision and expanded infrastructure continues this AI expansion trajectory.

Historical Comparison

+0.2% avg move · Past AI-tag news for TVGN showed modest average moves of 0.24% with mixed direction. A double-digit ...
AI
+0.2%
Average Historical Move AI

Past AI-tag news for TVGN showed modest average moves of 0.24% with mixed direction. A double-digit decline around this PredicTcell™ update stands out versus prior AI headlines.

AI efforts have progressed from launching PredicTcell™, securing dedicated AI funding, and forming Microsoft/Databricks partnerships to repeated data expansions and now higher precision metrics.

Market Pulse Summary

This announcement highlights measurable progress for Tevogen.AI, with PredicTcell™ recall improving ...
Analysis

This announcement highlights measurable progress for Tevogen.AI, with PredicTcell™ recall improving to 92% and precision to 48%, trained on 1.8 million data points. The platform leverages a database of 655 million peptide sequences and analyses from 37 million publications to refine immune-target predictions. Historically, AI-tagged news has produced mixed share reactions, so investors may watch for concrete partnerships and monetization steps tied to these technical gains.

Key Terms

peptide, proteome, ai agents
3 terms
peptide medical
"database of more than 655 million peptide sequences derived from approximately 24 million"
A peptide is a short chain of amino acids — the small building blocks that make up proteins — linked together like a short necklace of beads. Investors care because peptides are used as drugs, diagnostic tools and research reagents: their size and structure can make them easier to manufacture, modify, patent and bring through clinical testing than large proteins, so progress or setbacks in peptide development can directly affect a biotech company's value.
proteome medical
"ultimately predict the proteome for any given combination of protein and HLA type."
The proteome is the complete set of proteins produced by a cell, tissue, or organism at a given time — like a toolbox showing which tools are being used right now. For investors, proteome data matters because it reveals disease mechanisms, potential drug targets, and biomarkers that can drive product value, clinical success, or competitive advantage in biotech and healthcare investments.
ai agents technical
"Tevogen.AI now operates three production AI agents that: Continuously evaluate 14"
AI agents are computer programs designed to perform tasks or make decisions automatically, often by learning from data and adapting to new information. They act like virtual assistants or robots that can handle complex activities without human intervention, which can help businesses and individuals save time and improve efficiency. For investors, AI agents matter because they can enhance decision-making and automate processes that influence markets and financial outcomes.

AI-generated analysis. Not financial advice.

WARREN, N.J., March 13, 2026 (GLOBE NEWSWIRE) -- Tevogen (“Tevogen Bio Holdings Inc.” or “Company”) (Nasdaq: TVGN) today announced performance advancements for its artificial intelligence platform, operated through Tevogen.AI.

Tevogen.AI was built to solve a critical challenge in drug development: identifying biological targets which are most likely to work in patients, before entering costly clinical trials.

Over the past year, the Company has built a proprietary database of more than 655 million peptide sequences derived from approximately 24 million proteins, representing nearly 16 billion data points across multiple disease areas. This database is continuously enriched using analysis of 37 million scientific publications.

Improved Prediction Accuracy

In recent beta testing of its PredicTcell™ model, Tevogen reported:

  • Recall improved from 87% to 92% (the model is finding more of the right targets)
  • Precision improved from 40% to 48% (fewer incorrect predictions)
  • Higher overall accuracy scores
  • Increased true positives and reduced missed targets
  • Dramatically expanded training sample size

These results allow the model to improve in identifying which immune targets are likely to succeed. The current version, trained on 1.8 million data points, is nearly 20 times more robust than the initial model, reflecting rapid scale and learning acceleration.

Drug development today relies heavily on trial-and-error, and by improving target prediction before clinical testing, Tevogen aims to:

  • Reduce time to market
  • Lower development costs
  • Increase probability of clinical success
  • Extend the value of patent-protected products

This development builds on Tevogen.AI’s  published international patent application (WO 2025/129197), which outlines novel machine learning systems for predicting immunologically active peptides, a critical step in developing targeted therapies for cancers and infectious diseases.

Production AI Agents and Continuous Learning

Tevogen.AI now operates three production AI agents that:

  1. Continuously evaluate 14 active peptide candidates
  2. Monitor newly published scientific literature
  3. Integrate wet lab results back into the AI system

This creates a continuous learning loop between AI predictions and biological validation, strengthening future performance.

Next Steps and Partnership Strategy

As predictive accuracy continues to improve, Tevogen intends to explore partnerships with pharmaceutical companies to advance select peptide candidates for production and development.

Mittul Mehta, CIO & Head of Tevogen.AI, stated, “Our goal is to reduce trial-and-error in immunotherapy design and ultimately predict the proteome for any given combination of protein and HLA type. As our prediction quality improves, we believe we can meaningfully increase success rates while lowering development risk. That combination has the potential to create significant long-term value.”

About Tevogen

Tevogen is a socially integrated healthcare enterprise built on the principles of affordability, efficiency, and scientific rigor. The company leverages artificial intelligence and precision T cell therapy platforms, a patient-first and cost-disciplined operating model, and engagements with global technology leaders to support the development of advanced, life-saving therapies across multiple therapeutic areas and scalable solutions for the broader healthcare system.

Tevogen Bio, the company’s lead initiative, has completed a proof-of-concept clinical trial demonstrating the potential of its single-HLA-restricted, genetically unmodified allogeneic T cells. Tevogen Bio’s pipeline spans virology, oncology, and neurology, with programs built on the company’s proprietary ExacTcell™ platform.

Tevogen.AI is designed to transform drug development by accelerating target detection, helping reduce failure rates, and supporting optimized clinical trial design through proprietary predictive technologies. The platform utilizes cloud and data services from leading technology providers, including Microsoft and Databricks, to advance its long-term ambition to predict the proteome for any given protein–HLA combination, enabling rapid and cost-efficient therapeutic discovery.

Tevogen is exploring future strategic initiatives that may include domestic generics, biosimilars, medical devices, and innovative insurance solutions for healthcare providers. Together, these programs reflect Tevogen’s mission to advance sustainable innovation and broaden patient access through a faster, more efficient, and more equitable healthcare model.

Forward Looking Statements

This press release contains certain forward-looking statements, including without limitation statements relating to: the potential transactions and the potential benefits of the transactions; Tevogen’s plans for its research and manufacturing capabilities; expectations regarding future growth; expectations regarding the healthcare and biopharmaceutical industries; and Tevogen’s development of, the potential benefits of, and patient access to its product candidates for the treatment of infectious diseases and cancer. Forward-looking statements can sometimes be identified by words such as “may,” “could,” “would,” “expect,” “anticipate,” “possible,” “potential,” “goal,” “opportunity,” “project,” “believe,” “future,” and similar words and expressions or their opposites. These statements are based on management’s expectations, assumptions, estimates, projections and beliefs as of the date of this press release and are subject to a number of factors that involve known and unknown risks, delays, uncertainties and other factors not under the company’s control that may cause actual results, performance or achievements of the company to be materially different from the results, performance or other expectations expressed or implied by these forward-looking statements.

Factors that could cause actual results, performance, or achievements to differ from those expressed or implied by forward-looking statements include, but are not limited to: risks inherent in diligence and negotiation of the proposed transactions; the risk that the transactions may not be consummated on favorable terms or at all; the risk that the expected benefits of the transactions may not be realized on a timely basis or at all; changes in the markets in which Tevogen competes, including with respect to its competitive landscape, technology evolution, or regulatory changes; changes in domestic and global general economic conditions; the risk that Tevogen may not be able to execute its growth strategies or may experience difficulties in managing its growth and expanding operations; the risk that Tevogen may not be able to develop and maintain effective internal controls; the failure to achieve Tevogen’s commercialization and development plans and identify and realize additional opportunities, which may be affected by, among other things, competition, the ability of Tevogen to grow and manage growth economically and hire and retain key employees; the risk that Tevogen may fail to keep pace with rapid technological developments to provide new and innovative products and services or make substantial investments in unsuccessful new products and services; that Tevogen will need to raise additional capital to fully realize its business plans; risks related to the ability to develop, license or acquire new therapeutics; the risk of regulatory lawsuits or proceedings relating to Tevogen’s business; uncertainties inherent in the execution, cost, and completion of preclinical studies and clinical trials; risks related to regulatory review, approval and commercial development; risks associated with intellectual property protection; Tevogen’s limited operating history; and those factors discussed or incorporated by reference in Tevogen’s most recent Annual Report on Form 10-K and subsequent filings with the SEC.

You should not place undue reliance on forward-looking statements, which speak only as of the date they are made. Tevogen undertakes no obligation to update any forward-looking statements, except as required by applicable law.

Contacts

Tevogen Bio Communications
T: 1 877 TEVOGEN, Ext 701
Communications@Tevogen.com

A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/e46645d4-7bf3-4cb6-91d3-cb7ede5a0064


FAQ

What improvements did Tevogen (TVGN) report for PredicTcell™ on March 13, 2026?

PredicTcell™ showed improved recall and precision in beta testing, with recall at 92% and precision at 48%. According to the company, the model now trains on 1.8 million data points and benefits from a 655 million–sequence peptide database for broader learning.

How large is Tevogen.AI’s proprietary database reported by Tevogen (TVGN)?

Tevogen.AI’s database contains 655 million peptide sequences and about 16 billion data points. According to the company, it integrates data from roughly 24 million proteins and enriches training using 37 million scientific publications.

What does PredicTcell™’s precision increase mean for TVGN drug development?

Higher precision (40% to 48%) suggests fewer incorrect target predictions, potentially reducing wasted preclinical efforts. According to the company, better precision aims to lower development costs and increase probability of clinical success.

What production capabilities did Tevogen (TVGN) describe for Tevogen.AI?

Tevogen.AI now runs three production AI agents that continuously evaluate peptide candidates and monitor literature. According to the company, these agents feed wet‑lab results back into the system to create a continuous learning loop.

Are there confirmed pharma partnerships to develop PredicTcell™ candidates for TVGN?

No binding partnerships were announced; Tevogen said it intends to explore collaborations with pharmaceutical companies. According to the company, future partnerships are planned to advance select peptide candidates toward development.
Tevogen Bio

NASDAQ:TVGN

View TVGN Stock Overview

TVGN Rankings

TVGN Latest News

TVGN Latest SEC Filings

TVGN Stock Data

25.83M
913.91k
Biotechnology
Biological Products, (no Diagnostic Substances)
Link
United States
WARREN