Connect with us

Technology

Aureka Releases OpenDDE, an Open-Source Drug Discovery Engine Designed to Accelerate AI-Driven Therapeutic Discovery

Published

6 days ago

on

All-atom biomolecular foundation model uses co-folding as the entry point to a scalable drug discovery engine; the release marks a concrete step toward advancing open scientific AI for future biomedical research that benefit patients. 

LAGUNA HILLS, Calif. and SHANGHAI, July 6, 2026 /PRNewswire/ — Aureka, an AI TechBio company building infrastructure for AI-driven biologics discovery, today announced the release of Open Drug Discovery Engine (OpenDDE), an open-source, all-atom biomolecular foundation model designed to serve as the structural reasoning core of next-generation drug discovery systems.

OpenDDE uses biomolecular co-folding as the entry point to model interactions across proteins, nucleic acids, small-molecule ligands, and other biomolecular components. Rather than treating structure prediction as an isolated endpoint, OpenDDE is designed as a shared structural reasoning layer for sequence–structure–function modeling, enabling complex structure prediction today while laying the foundation for de novo design, affinity estimation, structure-conditioned optimization, and closed-loop discovery workflows. Across in silico benchmarks, OpenDDE shows competitive co-folding performance and narrows the gap with reported IsoDDE-level results, while offering an open and reproducible framework for the broader drug discovery community.

“OpenDDE begins with open, all-atom co-folding and structural reasoning. On selected in silico benchmarks, it shows competitive performance that narrows the gap with reported IsoDDE-level results. We view this release as an early foundation toward a broader drug discovery engine: a system that can progressively connect structure prediction, molecular design, affinity estimation, and experimental feedback to support more informed exploration of disease- and target-relevant molecular space.”

—Will Hua from Aureka AI Research

Three Technical Contributions Behind OpenDDE

Atomic latent reasoning over biomolecular tokens. OpenDDE introduces latent reasoning for biomolecular modeling by refining representations of local geometry, chemical context, and cross-molecular interfaces before all-atom structure generation.A folding-centered foundation for an extensible drug-discovery engine. OpenDDE currently focuses on complex structure prediction, but its unified architecture is designed to support de novo molecular design, affinity prediction, and other structure-conditioned modules.Scaling laws and data distillation. Aureka studies scaling directions along model-parameter, data, inference, and training axes, pointing to practical routes for continued improvement in biomolecular foundation models.

Open Benchmark Performance in Antibody-Antigen Co-Folding

In Aureka’s technical report, OpenDDE demonstrates strong antibody-antigen co-folding performance across three benchmarks. Under top-ranked selection, OpenDDE reaches 51.0% success on PXMeter-AB, 70.0% on FoldBench-AB, and 66.4% on the newly curated 2026ARK-AB benchmark. Under oracle selection, the corresponding success rates rise to 65.9%, 81.9%, and 80.1%, indicating strong latent sampling capacity and a clear opportunity for further gains through confidence calibration and candidate ranking.

The results are particularly relevant for therapeutic discovery because antibody-antigen interfaces are difficult, flexible, and chemically diverse. Aureka reports that OpenDDE improves not only low-threshold recovery but also medium- and high-quality DockQ regimes, suggesting stronger modeling of binding geometry rather than merely producing marginally acceptable complexes.

Biomolecular Foundation Models Are Entering the Scaling Era

OpenDDE has approximately 655 million trainable parameters. Aureka reports that the model required approximately 414,000 GPU-hours for training, equivalent to roughly 54 years on a single computing unit. This scale reflects a broader shift in AI for Biology: the frontier is no longer only an algorithm problem, but an infrastructure problem requiring compute, data pipelines, engineering, evaluation, and long-running training windows.

Aureka’s analysis identifies clear scaling trends for biomolecular foundation models, suggesting that larger effective training corpora, larger models, more capable inference-time sampling, and post-training improvements can systematically translate into stronger biological reasoning and structure prediction. For Aureka, this is a signal that biomolecular AI is beginning to enter a scaling regime analogous to the one that transformed large language models.

An Open Release for the Global Scientific Community

OpenDDE is released to make frontier biomolecular modeling more accessible to researchers, startups, academic laboratories, and multinational corporations. Aureka is releasing training code, inference pipelines, checkpoints, and benchmarks under the Apache-2.0 license, with the goal of enabling independent validation, community-driven extension, and global collaboration.

The release is available at:

GitHub: https://github.com/aurekaresearch/OpenDDEHugging Face: https://huggingface.co/aurekaresearch/OpenDDEWebsite: https://aurekaresearch.github.io/OpenDDE-Website/

Building TechBio Infrastructures

OpenDDE is an initial foundation for that future. Today, it serves structure prediction, antibody-antigen modeling, and drug discovery research. Over time, Aureka will extend the system toward de novo design, affinity estimation, conformational ensemble modeling, structure-conditioned optimization, experimental feedback, and broader scientific world modeling.

Aureka is also pairing this computational foundation with a high-throughput automated wet-lab platform to build a dry-wet closed-loop discovery system. By integrating autonomous antibody-design agents with high-throughput single-cell functional screening and automated yeast evolution, Aureka aims to create a high-throughput, high-content experimental data flywheel for functional antibody discovery. This platform allows AI agents to propose candidates, test them through automated experimental workflows, absorb functional and phenotypic feedback, and iteratively improve their design strategies.

Together, Aureka’s TechBio infrastructures are designed to support the next generation of antibody discovery across complex modalities such as epitope-specific antibodies, multispecific antibodies, internalizing antibodies, and pH-switch antibodies, with the long-term goal of developing differentiated First-in-Class and Best-in-Class therapeutic pipelines.

About Aureka

Aureka is an AI TechBio company developing infrastructure for AI-driven biology and therapeutic discovery. The company integrates large-scale compute, biomolecular foundation models, high-throughput wet-lab systems, and data flywheel capabilities to accelerate discovery in complex biological systems. Aureka’s mission is to improve human health by digitalizing and democratizing therapeutic discovery.

Forward-Looking Statements

This press release contains forward-looking statements regarding Aureka, OpenDDE, future research directions, product plans, and potential applications. These statements are based on current expectations and assumptions and are subject to risks and uncertainties, including technical, experimental, regulatory, commercial, and market factors. OpenDDE’s current release focuses primarily on biomolecular structure modeling and co-folding. Downstream capabilities such as molecular design, affinity prediction, conformational ensemble modeling, active learning, experimental feedback, and clinical translation require further research, validation, and development. Aureka does not guarantee the discovery, approval, or commercialization of any specific therapeutic candidate.

View original content to download multimedia:https://www.prnewswire.com/news-releases/aureka-releases-opendde-an-open-source-drug-discovery-engine-designed-to-accelerate-ai-driven-therapeutic-discovery-302818833.html

SOURCE Aureka

Related Topics:
Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Technology

EV All Day Launches Instant Battery-Health Check for Used Electric Cars

Published

11 hours ago

on

July 12, 2026

By

A used electric car’s most valuable part, its battery, is also the one thing no advert, V5C or history check will show you. EV All Day’s new £9.99 check changes that, giving buyers an instant, independent estimate of battery health, real-world range and remaining warranty before they ever view the car.

BRISTOL, England, July 12, 2026 /PRNewswire-PRWeb/ — EV All Day, a UK-based vehicle verification service, has launched to give used electric vehicle (EV) buyers and sellers the check that matters most for a battery-powered car: an independent read on the condition of its battery, before they buy.

The battery can be up to 40% of an EV’s value and thousands of pounds to replace, but nothing makes a seller prove its condition. For £9.99, we give buyers that proof before they travel to view.

While UK consumers can readily check any vehicle for outstanding finance, theft and write-off status, the single biggest factor in an electric car’s value and reliability, the health of its battery, has remained effectively invisible to buyers. Standard history checks were built for petrol and diesel cars and say nothing about battery condition, and a seller is under no obligation to evidence it.

EV All Day closes that gap. For £9.99, the service delivers an instant digital report estimating a used EV’s battery health, real-world range now versus when new, and how much battery warranty remains, from nothing more than a registration and the current mileage.

The Missing Check in Used EV Buying

On a petrol car, buyers judge condition on mileage and service history. On an electric car, the number that really decides value is one they can’t see. The battery can account for up to 40% of an EV’s value and costs anywhere from £5,000 to £15,000-plus to replace, yet its condition never appears on the advert, the V5C or the MOT.

Because batteries degrade gradually with age, mileage and charging habits, mileage alone is a poor guide: a well-treated 80,000-mile car can hold a healthier battery than a hard-charged 30,000-mile one. Until now, buyers have had no independent way to tell the difference before travelling to view a car.

“On a petrol car you check the mileage and the service history. On an electric car, the number that decides value is one you simply can’t see: the health of the battery. And no seller is obliged to show it to you,” said Simon Brown, founder of EV All Day.

“For £9.99 and about thirty seconds, we give buyers an honest estimate of that battery’s health, its real-world range and how much warranty is left, straight from the listing, before they ever travel to a viewing. It’s the check that’s been missing from used EV buying.”

What an EV All Day Check Shows

Every £9.99 report is built around an EV-specialist battery and range core, powered by ClearWatt, and cross-checked against official DVSA MOT and mileage records.

The report may include:

An estimated battery-health reading and range retention versus when newA battery-health grade (such as A+) where a manufacturer test record existsExpected real-world range now, shown side by side with the official WLTP figureRemaining battery warranty in miles and months, with an Active or Expired badgeUsable and total battery capacity (kWh)Charging, running cost, efficiency and full specification, where that data is held (powered by EV Database)Full MOT and mileage history from the DVSA, which also feeds the range estimate

The service is offered through two entry points to suit how buyers search: an EV Battery Health Check that leads with the battery reading, and a fuller Used EV Check that adds charging, running-cost and specification detail. Both are the same £9.99 report.

Crucially, EV All Day is honest about what the reading is: an estimate built from aggregated real-world data plus the specific car’s age and mileage, with a manufacturer grade shown where a test record exists, not an OBD-measured State of Health. It is the read buyers can get from a listing, before they ever contact the seller.

Coming Soon: A Full EV History Check

A comprehensive EV history check, bringing battery condition, charging and running costs, and full vehicle provenance together in a single report, is scheduled to follow, giving used EV buyers everything they need in one place.

Reducing Risk in a Fast-Growing Market

As more electric cars reach their second and third owners, so does the risk of undisclosed battery degradation. A tired battery can look identical to a healthy one on a forecourt, and dashboard range figures alone can mislead. Heavy, frequent rapid charging can roughly double the rate of battery wear, meaning two seemingly identical cars can hold very different batteries.

By providing an independent estimate of battery health and range, EV All Day helps buyers verify a used EV’s real condition rather than relying on seller claims, and helps sellers with a healthy battery evidence it to support their asking price. UK market research suggests buyers pay several hundred pounds more for a used EV with evidenced battery health, and that such cars sell noticeably faster.

Designed for Buyers, Sellers and the Trade

EV All Day is designed for use by:

Used EV buyers, screening listings and verifying battery health before travelling to viewPrivate sellers, evidencing a healthy battery and remaining warranty to support asking pricesDealers and traders, appraising electric vehicles quickly and consistentlyEV owners, understanding their car’s battery condition over time

The service is intended to complement existing vehicle history checks rather than replace them.

How the Service Works

Using EV All Day involves three steps:

Enter a UK registration number and current mileage, with no VIN required. The car is confirmed as an eligible EV before any payment is taken, and mileage is pre-filled from the latest MOT.Complete a single secure card payment of £9.99 through Stripe, with no subscription and no account.Receive the report in seconds, delivered three ways: instantly on screen, as a downloadable PDF, and as a copy by email.

If a report cannot be generated because data is unavailable for the vehicle, the customer is refunded in full, automatically. Coverage spans the mainstream UK electric market, including Tesla, Nissan, Kia, Hyundai, Volkswagen, BMW, MG and Jaguar, among many others.

The Switch to Electric Is Accelerating

The launch comes as electric vehicles take an ever-larger share of the UK market, with registrations climbing year on year and new petrol and diesel car sales due to end in 2030. As more of these vehicles reach the used market, buying with confidence increasingly means knowing each battery’s real condition, not just its mileage.

Availability

EV All Day is available now at evallday.com. Reports are delivered instantly where data is available, with an automatic full refund where a report cannot be generated.

About EV All Day

EV All Day is a UK-based vehicle verification service focused exclusively on electric vehicles. Operated by EV All Day Ltd and based in Chepstow, the platform combines EV-specialist battery and range data from ClearWatt with vehicle specification data from EV Database and official MOT and mileage records from the DVSA, helping buyers, sellers and the trade judge a used EV’s true condition. Reports cost £9.99, with an automatic full refund where a report cannot be generated.

Media Contact

Simon Brown, EV All Day, 44 01632 961111, hello@evallday.com, https://evallday.com/

View original content to download multimedia:https://www.prweb.com/releases/ev-all-day-launches-instant-battery-health-check-for-used-electric-cars-302823331.html

SOURCE EV All Day

Continue Reading

Technology

AlgoLaser Launches DIY KIT MK3: Start, Just That Simple–A Smarter Way to Laser Engrave

Published

1 day ago

on

July 11, 2026

By

SHENZHEN, China, July 11, 2026 /PRNewswire/ — AlgoLaser, a global leader in smart laser engraving technology, today officially launched its latest desktop laser engraver: the DIY KIT MK3. For years, complex assembly, cumbersome operation, and steep learning curves have kept many creators from exploring laser engraving. The DIY KIT MK3 eliminates these barriers. Built around the core promise to ‘Start, Just That Simple,’ it features optimized structural engineering, an intuitive AlgoOS-powered HD touchscreen, and significantly boosted laser performance. From unboxing to final creation, the DIY KIT MK3 seamlessly streamlines the entire process while delivering exceptional value.

Streamlined Assembly for Immediate Use

The DIY KIT MK3 introduces an innovative Structrix Frame, featuring precision alignment slots and cable management. Arriving 95% pre-assembled, the machine can be fully set up in just five simple steps in under 10 minutes. This completely eliminates traditional frustrations like belt tensioning, repeated alignments, and messy wiring.

Intelligent, Computer-Free Operation

Powered by the proprietary AlgoOS, the built-in HD touchscreen enables fully offline, standalone operation. It boasts smart parameter recommendations, drag-and-drop positioning, and direct image processing. Combined with over 400 ready-to-use projects and creative tools like AlgoType and AlgoSketch, the system allows beginners to start creating instantly—no computer or technical expertise required.

Enhanced Power and Speed for Higher Productivity

Equipped with new 8W, 15W, and 20W laser modules, the DIY KIT MK3 delivers up to a 60% power increase over its predecessor. Robust structural and material upgrades fully harness this power, ensuring stable, high-precision engraving at speeds up to 15,000 mm/min. Additionally, the spacious 400×400mm workspace and an efficient repetitive processing mode make intricate designs and small-batch production highly practical, empowering users to easily monetize their craft.

Modular Design for Long-Term Flexibility

The DIY KIT MK3’s modular architecture supports seamless laser module upgrades and effortless integration with accessories like rotary attachments. This flexibility adapts to diverse needs—from scaling an Etsy business to exploring family DIY projects. Furthermore, with an optional Class 1 safety enclosure and multiple built-in monitoring systems, the DIY KIT MK3 provides peace of mind, making it safe for both commercial studios and home environments.

Availability

The DIY KIT MK3 is now available for pre-order exclusively on the official website, algolaser.com. From July 11–31, customers can order during the Super Early Bird window and enjoy exclusive perks, including free gifts and bonus points. It will then launch globally on Amazon and other major platforms starting August 1.

Order now to secure early access before the worldwide launch.

About AlgoLaser

AlgoLaser is a global provider of smart laser engraving solutions, dedicated to empowering makers, educators, and everyday creators around the world. By pairing high-performance hardware with the intuitive AlgoOS operating system, AlgoLaser breaks down technical barriers to make professional-quality creation as simple as everyday printing. The company is committed to helping users of all skill levels effortlessly transform creative ideas into reality, making laser technology easier, safer, and accessible enough for every household. For more information, visit www.algolaser.com.

View original content to download multimedia:https://www.prnewswire.com/news-releases/algolaser-launches-diy-kit-mk3-start-just-that-simplea-smarter-way-to-laser-engrave-302822637.html

SOURCE AlgoLaser

Continue Reading

Technology

DRAI Health Introduces SpaceXAI-Powered Personalized Voice Interaction in heyDRAI

Published

2 days ago

on

July 11, 2026

By

New capability delivers more natural, adaptive, and human-centered voice-guided healthcare experiences

LOS ANGELES, July 11, 2026 /PRNewswire-PRWeb/ — DRAI Health today announced the launch of a new personalized voice interaction capability within heyDRAI, its AI-powered healthcare platform. Powered by advanced SpaceXAI technology, this innovation enables more natural, expressive, and context-aware voice-guided healthcare interactions, further advancing DRAI Health’s mission to deliver truly patient-centric digital care.

“By integrating SpaceXAI technology into heyDRAI, we are enabling a more natural, adaptive, and emotionally intelligent interface that enhances how patients interact with healthcare information.” said Gor Galstyan, CTO of DRAI Health.

The new capability transforms AI-guided consultations from static, text-based exchanges into dynamic, conversational experiences tailored to each individual user. Patients can select from a range of voice styles—such as calm and reassuring, clear and clinical, or energetic and motivational—allowing interactions to align with their personal preferences and emotional needs.

Unlike conventional text-to-speech systems that simply vocalize scripted content, heyDRAI’s SpaceXAI-powered voice interaction is designed to understand conversational context, adjust tone dynamically, and deliver responses in a more human-like manner. This creates a more engaging and intuitive experience that helps patients feel more comfortable, attentive, and connected throughout their healthcare journey.

Each user’s preferred voice profile is retained across interactions, ensuring continuity and personalization over time, while maintaining flexibility for users to modify their preferences as needed.

Technology Differentiation Through SpaceXAI Integration

The integration of SpaceXAI technology enables a new class of voice interaction that goes beyond traditional AI voice systems by incorporating:

Context-aware response generation rather than static script delivery

Adaptive tone modulation based on conversational flow and user engagement

Improved reasoning and coherence in multi-step healthcare interactions

More natural conversational pacing, reducing cognitive load for users

These capabilities are particularly important in healthcare, where clarity, empathy, and precision directly impact patient understanding and engagement.

Leadership Commentary

“Healthcare conversations are deeply personal. Our goal is to make interactions with AI feel less transactional and more human,” said Gor Galstyan, CTO of DRAI Health. “By integrating SpaceXAI technology into heyDRAI, we are enabling a more natural, adaptive, and emotionally intelligent interface that enhances how patients interact with healthcare information.”

Enhancing the Patient-Centric Healthcare Experience

The introduction of personalized voice interaction represents a significant step forward in DRAI Health’s broader vision to create a continuous, patient-centered healthcare experience spanning:

Wellness and preventive care

Symptom assessment and early intervention

Acute and chronic condition support

Post-acute recovery and ongoing monitoring

By embedding advanced voice interaction into the consultation flow, heyDRAI improves accessibility for a wide range of users, including those who prefer voice-first interaction or may have difficulty engaging with traditional text-based interfaces.

Looking Ahead

The personalized voice capability is now available within heyDRAI and will continue to evolve with additional features, including deeper personalization, multilingual support, and enhanced clinical interaction workflows.

About DRAI Health

DRAI Health is developing AI-powered healthcare technologies designed to transform how patients, providers, and health systems interact with medical information. Through platforms such as heyDRAI, the company focuses on intelligent intake, guided consultation, patient engagement, and clinical decision support.

DRAI Health’s mission is to make healthcare more accessible, personalized, and human-centered, leveraging advanced artificial intelligence combined with real-world clinical insight.

For more information, visit www.draihealth.com.

Media Contact

Kelsey Whiddon, DRAI Health, Inc., 1 818.621.1441, marketing@draihealth.com, https://www.draihealth.com/

View original content to download multimedia:https://www.prweb.com/releases/drai-health-introduces-spacexai-powered-personalized-voice-interaction-in-heydrai-302822689.html

SOURCE DRAI Health, Inc.

Continue Reading

Trending