Overview¶
Welcome to the MQS Toolstack documentation for learning about modern calculation pipelines utilizing quantum chemistry and machine learning models.
The modular algorithms have been compiled for high performance CPUs, GPUs and QPUs and can be chained together in a flexible way to solve a wide range of use-case applications.
We provide integrated tools to apply the algorithms in a user-friendly way and leverage a combination of code oriented programming (SDK) and dashboard interfaces to let you gain control and an easy overview of results, datasets and settings.
-
MQS Dashboard
MQS Cebule Engine
JupyterLab
Kubeflow
-
High Performance Computing (HPC)
Object Storage
Git Version Control
Container Registry
-
Software Development Kit (SDK)
API Endpoints
SDK Functions & Arguments
-
PubchemQC
QMugs
-
DFT, Semi-empirical Methods & Tight-binding Models
DFT, PW-DFT
PM6, PM7
GFNx-xTB
-
COSMO (CPCM)
PCM (DPCM)
IEFPCM
-
Born-Oppenheimer MD (BOMD)
Car-Parrinello MD (CPMD)
Path Integral MD (PIMD)
-
Machine Learning (ML) & Artificial Intelligence (AI)
Graph Neural Network (GNN) Library
Generative Adversarial Network (GAN)
-
Fermion-Qubit Mapping & Measurement Method
Tensor Networks & Variational Quantum Algorithms
-
OPC-UA + MQTT based Real-time Data Capturing & Storage Framework
Robotics Lab Interface
Bayesian Design of Experiments & Closed-loop Optimization
Examples / Use-cases¶
Cebule Engine
How to run a COSMO calculation
Database & HOMO-LUMO Gap
Anion, cation, S0, D0, T0, Q0 states look-up
Get HOMO-LUMO gap data from the PubchemQC PM6 and QMugs data set
HOMO-LUMO Gap, Poly-chlorinated Biphenyls (PCBs) & Toxicity
DelFTa Model prediction performance comparison for PCB molecules against PM6 data
GNN performance compared to DelFTa for PCB molecules
Kubeflow
Fine-tuning a model via Kubeflow for toxicity predictions of PCB molecules
Prediction of toxicity of PCB molecules with trained model via Kubeflow
The MQS Toolstack allows you to tackle demanding problems within pharma, life science, chemistry and materials research.
Use-case Domain → | Formulation Development & Product Design | Upscaling & Process Simulations | Materials Design |
---|---|---|---|
Properties → | Solubility, Stability, Toxicity, Viscosity | Vapour-Liquid Equilibrium (VLE) | HOMO-LUMO Gap, Ground & Excited States |
Binding Analysis | Liquid-Liquid Equilibrium (LLE) | Seebeck Coefficient | |
Solid-Liquid Equilibrium (SLE) | Solubility, Phase Stability | ||
Use-case Examples → | (Bio)Pharma Solubility in Multi-compound Mixtures | Crystallizer Design for Purification Processes | OLED Materials |
Toxicity Checks in Pharma & Chemical Product Development | Solvents Analysis for CO2 Capture & CO2 Utilization Processes | Energy Storage Materials | |
Human, Animal and Environmental Safety | Liquid-Liquid Chromatographic Separation | High-Entropy Alloys | |
Beauty Care Product Design | Property data for Computational Fluid Dynamics (CFD) | Catalyst Design | |
Integrated Drug Discovery & Formulation Analysis | Anti-corrosion and Functional Coatings |
Feedback and questions¶
Do not hesitate to send us feedback, if you have any questions or if you find mistakes in the text, code snippets, equations, or any other flaw.
Please let us know through the support field in the MQS Dashboard or via contact (at) mqs [dot] dk.
Some notes on this documentation¶
-
Sometimes the mathematical equations in this documentation show up as LaTex equations. One can reload the page and then the equations should be rendered properly.
-
The table of content (ToC) is shown in desktop view on the right. When reading the documentation on a phone screen and navigating to a specific chapter, you will be able to see the table of contents by again opening the navigation menu and a symbol should show up next to the current opened chapter. This symbol opens up the ToC.