Tevogen Marks Major Milestone in Its AI Initiative to Enhance Efficacy of T Cell–Based Therapies with 100x PredicTcell™ Beta Data Expansion
Tevogen (NASDAQ:TVGN) announced significant advancements in its PredicTcell™ AI platform for T cell-based therapies. The beta version has expanded its training dataset to ~1.4 million records and total dataset to over 6.7 billion records, marking a 100-fold increase.
The platform, developed with Microsoft and Databricks, builds upon the alpha version which achieved 92-97% recall levels and 38-43% precision. The beta version analyzes over 10.7 billion data points, including 6.5 billion virology, 4.2 billion genomic, and 416 million oncology datapoints, while expanding training features from 22 to 27.
This advancement could potentially enable T-cell therapies to bind to their targets with unprecedented accuracy, promising increased clinical success rates, shorter development timelines, and improved patient access to life-saving therapies.
Tevogen (NASDAQ:TVGN) ha annunciato notevoli progressi nella sua piattaforma PredicTcell™ AI per le terapie a base di cellule T. La versione beta ha ampliato il set di dati di addestramento a circa 1,4 milioni di record e l'insieme totale a oltre 6,7 miliardi di record, segnando un incremento di 100 volte.
La piattaforma, sviluppata insieme a Microsoft e Databricks, si basa sulla versione alpha che ha ottenuto livelli di recall tra 92-97% e precision tra 38-43%. La versione beta analizza oltre 10,7 miliardi di dati, tra cui 6,5 miliardi di dati virologici, 4,2 miliardi di dati genomici e 416 milioni di dati oncologici, espandendo inoltre le caratteristiche di addestramento da 22 a 27.
Questo progresso potrebbe consentire alle terapie T-cell di legarsi ai propri bersagli con una precisione senza precedenti, aprendo la strada a maggiori tassi di successo clinico, a tempi di sviluppo più brevi e a un miglior accesso dei pazienti a terapie salvavita.
Tevogen (NASDAQ:TVGN) anunció avances significativos en su plataforma PredicTcell™ AI para terapias basadas en células T. La versión beta ha ampliado su conjunto de datos de entrenamiento a aproximadamente 1,4 millones de registros y el conjunto total a más de 6,7 mil millones de registros, un aumento de 100 veces.
La plataforma, desarrollada junto a Microsoft y Databricks, se apoya en la versión alfa que logró niveles de recall del 92-97% y una precisión del 38-43%. La versión beta analiza más de 10,7 mil millones de puntos de datos, incluyendo 6,5 mil millones de datos virológicos, 4,2 mil millones de datos genómicos y 416 millones de datos oncológicos, al tiempo que expande las características de entrenamiento de 22 a 27.
Este avance podría permitir a las terapias de células T unirse a sus objetivos con una precisión sin precedentes, prometiendo tasas de éxito clínico más altas, plazos de desarrollo más cortos y un mejor acceso de los pacientes a terapias que salvan vidas.
Tevogen(NASDAQ:TVGN)은 T 세포 기반 치료를 위한 PredicTcell™ AI 플랫폼에서 상당한 발전을 발표했다. 베타 버전은 학습 데이터 세트를 약 140만 건으로 확장했고 전체 데이터 세트는 67억 건을 넘겨 100배 증가했다.
이 플랫폼은 Microsoft와 Databricks와 함께 개발되었으며, 알파 버전은 재현율(recall)이 92-97%, 정밀도(precision)가 38-43%를 달성했다. 베타 버전은 107억 개가 넘는 데이터 포인트를 분석하며, 이 중 65억 개는 바이러스학 데이터, 4,200,000,000개의 게놈 데이터, 4억1600만 개의 종양 데이터 포인트를 포함하고, 학습 피처를 22개에서 27개로 확장했다.
이 발전은 T 세포 치료제가 표적에 이전에 없던 정확도로 결합할 수 있게 하여 임상 성공률을 높이고 개발 기간을 단축하며 환자들이 생명을 구하는 치료에 더 쉽게 접근할 수 있게 할 수 있다.
Tevogen (NASDAQ:TVGN) a annoncé des avancées significatives dans sa plateforme PredicTcell™ AI pour les thérapies à base de cellules T. La version bêta a élargi son ensemble de données d'entraînement à environ 1,4 million d'enregistrements et l'ensemble total à plus de 6,7 milliards d'enregistrements, soit une augmentation de 100 fois.
La plateforme, développée avec Microsoft et Databricks, s'appuie sur la version alpha qui a atteint des niveaux de rappel (recall) de 92-97% et une précision de 38-43%. La version bêta analyse plus de 10,7 milliards de points de données, dont 6,5 milliards de données virologiques, 4,2 milliards de données génomiques et 416 millions de données oncologiques, tout en élargissant les caractéristiques d'entraînement de 22 à 27.
Cette avancée pourrait permettre aux thérapies par cellules T de se lier à leurs cibles avec une précision sans précédent, promettant des taux de réussite clinique plus élevés, des délais de développement plus courts et un meilleur accès des patients à des thérapies vitales.
Tevogen (NASDAQ:TVGN) kündigte bedeutende Fortschritte bei seiner PredicTcell™ AI-Plattform für T-Zell-Therapien an. Die Beta-Version hat ihren Trainingsdatensatz auf ca. 1,4 Millionen Datensätze erweitert und den Gesamtdatensatz auf über 6,7 Milliarden Datensätze, was einer 100-fachen Steigerung entspricht.
Die Plattform, entwickelt mit Microsoft und Databricks, baut auf die Alpha-Version auf, die eine Recall-Rate von 92-97% und eine Präzision von 38-43% erreichte. Die Beta-Version analysiert über 10,7 Milliarden Datenpunkte, darunter 6,5 Milliarden Virologie-Daten, 4,2 Milliarden Genomik-Daten und 416 Millionen Onkologie-Datenpunkte, während die Trainingsmerkmale von 22 auf 27 erweitert werden.
Diese Entwicklung könnte T-Zell-Therapien ermöglichen, ihre Ziele mit beispielloser Genauigkeit zu binden, und verspricht höhere klinische Erfolgsraten, kürzere Entwicklungszeiten und besseren Zugang zu lebensrettenden Therapien.
أعلنت Tevogen (بورصة ناسداك: TVGN) عن تقدمات مهمة في منصتها PredicTcell™ AI لعلاجات الخلايا T. النسخة التجريبية (بيتا) وسّعت مجموعة بيانات التدريب إلى حوالي 1.4 مليون سجل وإلى أكثر من 6.7 مليار سجل كإجمالي، بزيادة قدرها 100 مرة.
تم تطوير المنصة بالتعاون مع مايكروسوفت وDatabricks، وتستند إلى النسخة الألفا التي حققت معدلات الاستدعاء (recall) بين 92-97% والدقة (precision) بين 38-43%. تحلل النسخة بيتا أكثر من 10.7 مليار نقطة بيانات، بما في ذلك 6.5 مليار بيانات فيروولوجيا، و4.2 مليار بيانات جينومية، و416 مليون نقطة بيانات أورام، مع توسيع ميزات التدريب من 22 إلى 27.
يمكن أن تمكّن هذه التطورات علاجات الخلايا T من الارتباط بالأهداف بدقة غير مسبوقة، واعدةً بمعدلات نجاح سريرية أعلى، وجداول تطوير أقصر، وتحسين وصول المرضى إلى علاجات إنقاذ للحياة.
Tevogen（NASDAQ:TVGN）宣布在其 PredicTcell™ AI 平台的 T 细胞治疗方面取得重大进展。β 版本将训练数据集扩展至约 140万条记录，总体数据集超过 67亿条记录，实现了 100 倍的增长。
该平台与 微软和 Databricks 联合开发，基于已经达成 92-97% 的召回率和 38-43% 的精确度的 Alpha 版本。β 版本分析超过 107 亿 个数据点，其中包括 6.5 亿病毒学数据、4.2 亿基因组数据和 4.16 亿肿瘤学数据点，同时将训练特征从 22 提升至 27。
这项进展有望使 T 细胞疗法以前所未有的精确度结合靶点，承诺提高临床成功率、缩短开发时间，并提升患者获得挽救生命治疗的机会。
- Massive dataset expansion to 6.7 billion records, a 100-fold increase from alpha version
- High performance metrics with 92-97% recall levels in alpha version
- Partnership with major tech companies Microsoft and Databricks
- Potential to significantly improve clinical success rates and reduce drug development costs
- Current precision range remains relatively low at 38-43%
- Technology still in beta phase with unproven commercial viability
- Additional capital may be needed to execute business plan
- Faces significant regulatory and development uncertainties
Insights
Tevogen's PredicTcell Beta expands training data 100x, potentially enabling near-perfect T cell binding accuracy that could revolutionize immunotherapy development.
Tevogen's announcement represents a significant technological leap in their PredicTcell™ AI platform development. The company has expanded its training dataset by a factor of 10 to approximately
The technical improvements are substantial. Their alpha version already demonstrated impressive recall levels of
The potential implications cannot be overstated. If PredicTcell delivers on its promise, Tevogen could develop T cell therapies with near-certain binding probability. This would fundamentally transform the economics and efficacy of immunotherapy development by: 1) dramatically raising clinical success rates, 2) shortening development timelines, and 3) reducing costs. The platform leverages Microsoft and Databricks technology infrastructure, suggesting robust computational capabilities needed for handling these massive datasets.
What makes this particularly valuable is that T cell binding certainty addresses the most unpredictable aspect of immunotherapy development. By potentially eliminating this uncertainty, Tevogen could significantly reduce the high failure rates that plague clinical development in this space, fundamentally changing the risk profile for their pipeline across infectious diseases and oncology applications.
- Beta version of PredicTcell™ expands training dataset to ~1.4 million and total dataset to over 6.7 billion records.
- Potential future T cell therapies could reliably bind to their target nearly every time, dramatically raising the probability of success.
WARREN, N.J., Sept. 25, 2025 (GLOBE NEWSWIRE) -- Tevogen (“Tevogen Bio Holdings Inc.” or “Company”) (Nasdaq: TVGN), today announced significant progress in the development of its proprietary PredicTcell™ platform, designed to accelerate precision immunotherapy development and efficacy through advanced machine learning and transformer-based models. The platform is being developed with the support of Microsoft (Nasdaq: MSFT) and Databricks, leveraging their advanced cloud and data technologies to enable scalability and efficiency.
The alpha version of PredicTcell was trained on more than 124,000 records using transformer-based architecture and 91,000 records using traditional machine learning architecture. The alpha version of the model delivered recall levels of ~92–
Informed by insights from Tevogen’s proprietary ExacTcell™ platform and positive Phase 1 trial results, PredicTcell Beta aims for significantly higher precision in identifying virology targets. Key advancements include:
- Expanded the training dataset tenfold to approximately 1.4 million records, while the total dataset has grown more than 100-fold to over 6.7 billion records.
- Analyzed more than 10.7 billion data points to construct the training set consisting of 6.5 billion virology datapoints, 4.2 billion genomic datapoints, and 416 million oncology datapoints.
- Expanded the number of features for training the model from 22 to 27.
By dramatically scaling its data pipelines and fine-tuning its models, Tevogen.AI could move toward an unprecedented position: T-cell therapies that could accurately bind to their intended target nearly every time. Such predictability would be a transformative breakthrough in medicine, with far-reaching implications:
- Clinical success rates dramatically increased.
- Development timelines shortened, reducing drug costs.
- Greater patient access to life-saving therapies across infectious diseases, oncology, and beyond.
“The promise of PredicTcell goes far beyond data,” said Mittul Mehta, CIO and Head of Tevogen.AI. “If our tools continue to deliver as they have so far, Tevogen stands to create T-cell therapies where binding to the target virus or disease isn’t just probable, but nearly guaranteed. That would mean clinical success, faster cures, reduced costs, and ultimately more lives saved.”
“With the right skill and the proper blend of AI and biotechnology, we can scale discoveries in precision medicine once thought impossible. Tevogen’s AI initiative is to raise efficacy standards in T cell–based therapies, cut development costs, and unlock entirely new markets in immunotherapy,” added Ryan Saadi, M.D., M.P.H., Chief Executive Officer of Tevogen Bio.
Forward Looking Statements
This press release contains certain forward-looking statements, including without limitation statements relating to: 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: that Tevogen will need to raise additional capital to execute its business plan, which may not be available on acceptable terms 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; 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 Annual Report on Form 10-K.
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
FAQ
What is Tevogen's PredicTcell™ platform and how does it work?
What are the key performance metrics of Tevogen's PredicTcell™ platform?
How could PredicTcell™ impact T cell therapy development?
Who are Tevogen's key technology partners for PredicTcell™?
What types of data does Tevogen's PredicTcell™ analyze?
