DP Technology is a company that specializes in the development of computer-aided manufacturing (CAM) software solutions. Their products are designed to improve manufacturing processes by automating toolpath generation and optimizing CNC machine performance.

DP Technology

DP Technology, Ltd. is an AI research and development company aspiring to solve the biggest problems in science. DP Technology is founded on the fact that our current scientific tools and computing methods have not been adequate in deepening our understanding of the microscopic world. Specifically, they have failed in predicting the behavior of complex systems at multi-scale levels. This has resulted in prolonged stagnation in the development of new materials, new drugs, new semiconductor frameworks, and beyond. 

We believe artificial intelligence has the potential of solving these imminent global challenges and the best way to do it is by combining the best practices of AI, scientific computing, and cloud HPC, designing innovative algorithms and software, and connecting cutting-edge technologies with real challenges in industry.

At DP, we believe in the power of open source. DP is the critical contributor to DeepModeling, the largest open source AI for Sciences (AI4S) community in the world. Leading researchers from Princeton, UC Berkeley and others have embraced DeepModeling and have achieved breakthroughs published in journals like Nature, Science, PRL and more. Our technology is also adopted by top companies in developing the next genenration energy storage system, cancer curing drugs and new semiconductor frameworks.

DPTechnology

"AI for Science" illustrated: a 4-minute animation.

https://lnkd.in/g7DZgaXs

DP Technology is proud to introduce Uni-MOF, a cutting-edge framework designed to predict gas adsorption in metal-organic frameworks (MOFs) with unprecedented accuracy and efficiency. Together with collaborators at Tsinghua University and University of California, Riverside, our paper is now live on Nature Communications with open access https://lnkd.in/gkWXvPDP

Metal-organic frameworks, known for their unique porous structures and customizable chemical compositions, have emerged as frontrunners in the race to develop advanced materials for critical applications such as carbon capture, gas storage, and purification. These materials' ability to selectively adsorb gases makes them invaluable in addressing some of today's most pressing environmental and energy challenges, including greenhouse gas reduction and sustainable energy solutions.

What sets Uni-MOF apart is its ability to learn from an extensive database of over 631,000 MOF and COF structures, enabling it to predict adsorption capacities under various conditions (temperatur/pressure/gas) using a single model. This not only enhances the framework's predictive accuracy (R2>0.98) but also its applicability to a broad spectrum of properties beyond gas adsorption, including energy storage and catalysis.

Uni-MOF is built on our Uni-Mol 3D Molecular Representation Learning framework. Since launching, Uni-Mol has been adopted in peer-reviewed researchs in an impressive range of fields, incl. 
-- QSAR & ADMET (ICLR'23 https://lnkd.in/gGV5Cw6D), 
-- new OLED material properties prediction at near-DFT level (AOM'23 https://lnkd.in/gTShd9iW), 
-- Single-step retrosynthesis (JACS Au'24 https://lnkd.in/gft-VPPD), 
-- MOF, and beyond.

Please reach out at info@dp.tech if you would like to work with us on developing Uni-Mol for your need.

Uni-Dock v1.1: Open-sourced High Performance Molecular Docking Software

Uni-Dock, a high-performance molecular docking software developed by DPTechnology, has made significant strides in drug discovery. Originally published as a cover article in the JCTC journal in June 2023 and later open-sourced under the LGPL license in August 2023, Uni-Dock has garnered attention from both academic and industrial sectors. Its integration into various software platforms and application in early drug discovery projects highlight its utility in AI for Science methods. The new 1.1 version features significantly enhanced performance, new ultra-large virtual screening competence, practical toolkits, benchmarks, CI/CD and improved open-source collaboration model.

Highlights of Uni-Dock v1.1:

1. Enhanced Performance: The latest v1.1 version of Uni-Dock, released in February 2024, includes numerous new features contributed by developers from DP and NVIDIA, further improving the efficiency of molecular docking and virtual screening. The single-molecule docking speed has been significantly increased to 2.773s per ligand (up 194%) in fast mode. For virtual screening, the speed has been boosted to 0.062s per ligand (up 150%) in fast mode.

2. Optimized GPU Kernel for Ultra-large Virtual Screening: Virtual screening has also seen significant enhancements through GPU kernel adjustments, Warp-level parallel optimization for the Monte Carlo simulation, and optimized task scheduling strategies. These improvements have led to a substantial increase in screening speed, making it possible to complete a large-scale virtual screening of 100 million molecules in just 8.3 hours with a 100 consumer-grade GPU cluster.

3. Uni-Dock Tools: The release of Uni-Dock Tools provides users with a better experience and excellent use cases. This package integrates practical tools such as proteinprep for receptor protein preparation and ligandprep for ligand molecule preparation, complementing the pre-processing methods in the Uni-Dock workflow. It also includes the unidock-pipeline for automated execution of protein and ligand preparation.

4. Benchmarks, CI/CD and Open-Source Collaboration: Uni-Dock v1.1 introduces the Uni-Dock Benchmarks for performance evaluation and refines the CI/CD pipeline, laying the groundwork for broader open-source collaboration. Uni-Dock's open-source collaborative model has become more defined and standardized with each software iteration, embracing the open-source community and user feedback for continuous optimization and progress.

Get Uni-Dock v1.1! The code for Uni-Dock v1.1 is available on GitHub at the following repository: https://lnkd.in/gxG7_7NW

Introducing Uni-IFD (Induced Fit Docking) on Hermite® Drug Design Platform.

In molecular docking studies, rigid or semi-flexible docking methods are commonly used. However, in real biochemical processes, there is often conformational changes in both ligand and receptor protein when they bind to each other. These changes lead to alterations in the conformations of amino acids surrounding the pocket, allowing for better adaptation to the ligand's shape and binding mode. Therefore, Induced Fit Docking (IFD) is needed for a more accurate prediction of drug-target binding. Uni-IFD is designed to meet this need.

Recently, Uni-IFD is used in a Cell Reports Medicine paper https://lnkd.in/eJDwbzGk. The paper investigated the anti-tumor immunotherapy effects of the marine natural small molecule Benzosceptrin C. Uni-IFD performed induced fit docking of all conformations of Benzosceptrin C with selected active sites and accurately predicted and validated the binding modes observed. 

Try Uni-IFD at hermite.dp.tech or email us at info@dp.tech.

Introducing Uni-FEP on Hermite® Drug Design Platform.

Uni-FEP leverages free energy perturbation theory, molecular dynamics, and advanced sampling algorithms to accurately and efficiently gauge the binding affinity between proteins and ligands. This approach streamlines the lead compound optimization process, significantly reduce time and expenses typically associated with experimental phases, and facilitates optimization at an industrial scale. Uni-FEP is

1) Accurate: Free energy calculations achieving chemical accuracy (±1 kcal/mol), with indus- try-leading average correlation coefficients on publicly available case studies; 

2) Fast: Finish affinity prediction and screening of thousands of candidate compounds within a single day, leveraging our robust cloud computing resources; and

3) Easy to use: User-friendly interface, automated computation, one-click task submission, support- ing flexible application scenarios and multiple deployment methods. 

Email us at info@dp.tech for trial.


msh id	TECH:DP
symbol	-
name	DP Technology
homepage url	https://dp.tech
country	CN
sector	Technology
industry	Software Development
market	PRIVATE
employee count	58
crunchbase url	https://www.crunchbase.com/organization/dp-technology
linkedin url	https://www.linkedin.com/company/dptechnology
founders	-

market cap	-
enterprise value	-
stage	-
raised capital	-
valuation	-

monthly webtraffic	-
monthly webtraffic growth	-
growth score 14	60.6
growth score 28	60.98
growth score 90	59.33
growth score 365	55.3

revenue ltm	-
gross profit ltm	-
ebitda ltm	-
net income ltm	-
revenue ntm	-
gross profit ntm	-
ebitda ntm	-
net income ntm	-

growth cost and expenses	-
growth cost of revenue	-
growth depreciation and amortization	-
growth ebitda	-
growth ebitda ratio	-
growth eps	-
growth eps diluted	-
growth general and administrative expenses	-
growth gross profit	-
growth gross profit ratio	-

TECH:DP

DP Technology

Company Information

Market Metrics

Web & Growth Metrics

LTM & NTM Metrics

Growth & Performance Metrics

Operating Metrics

Balance Sheet Metrics

Financial Metrics (2022-2026)

cost and expenses	-
cost of revenue	-
depreciation and amortization	-
ebitda	-
ebitda ratio	-
eps	-
eps diluted	-
operating expenses	-
operating income	-
operating income ratio	-

accounts receivables	-
capital expenditure	-
cash at beginning of period	-
cash at end of period	-
inventory	-
working capital ttm	-

	2022	2023	2024	2025	2026
Revenue Metrics
Revenue	-	-	-	-	-
Revenue Growth	-	-	-	-	-
Revenue Multiple	-	-	-	-	-
Profit Metrics
Gross Profit	-	-	-	-	-
Gross Profit Growth	-	-	-	-	-
Gross Profit Multiple	-	-	-	-	-
EBITDA Metrics
EBITDA	-	-	-	-	-
EBITDA Growth	-	-	-	-	-
EBITDA Multiple	-	-	-	-	-
Net Income Metrics
Net Income	-	-	-	-	-
Net Income Growth	-	-	-	-	-
Net Income Multiple	-	-	-	-	-