- Home
- Industry Solutions
- Services
- Support
- About Us
Over the past few years, artificial intelligence (AI) has been widely used in the pharmaceutical industry, because it can handle large volumes of data with enhanced automation. AI is a technology-based system that can interpret and learn from the input data to achieve specific goals. AI can be used effectively in different stages of drug research, including drug design and synthesis, drug screening, pharmacology study, and drug repurposing. Creative Biolabs is recognized as the world leader for providing an advanced AI-assisted platform to support drug discovery and development for worldwide customers.
Fig 1. Role of artificial intelligence (AI) in drug discovery. (Paul, et al., 2021)
Based on nucleotide sequence information, nucleic acid drugs can regulate gene expression to control the cell’s biological functions. Sequence-dependent mechanisms provide a major advantage for the design of nucleic acid drugs. Currently, many RNA interferes (RNAi) drugs such as miRNA, siRNA, and antisense oligonucleotides (ASO) have been developed for gene therapy. In the recent COVID-19 pandemic, the mRNA vaccine was first administered to humans for the treatment of virus infection. With the artificial intelligence-assisted platform, Creative Biolabs can design an effective sequence and provide the optimal modification to improve the stability of nucleic acid drugs.
The drug discovery heavily relies on three-dimensional (3D) structures of target proteins. It is very difficult to design the targeted drugs if the 3D structure of a protein target is unknown. The biological function of a protein is entirely dependent on its inherent three-dimensional structure. There are three major approaches for predicting 3D structures, including homology modeling, protein threading or fold recognition, and Ab initio quantum chemistry methods. The combination of artificial intelligence technology contributed to handling the big data and discovering novel drugs targeting proteins without 3D structure and overcoming the undruggable targets.
Chemical toxicity and adverse effects are key regulatory aspects for a multitude of industries. Traditional in vivo toxicity tests are time-consuming and expensive. Simultaneously, it is subject to ethical limitations. For greater economic and time efficiency, there are growing demands on the authorities to replace animal tests with in silico computational models. In recent years, artificial intelligence based on in silico methodologies has been widely used for the determination of the toxicological properties of chemical compounds in different fields. The introduction of computational methodologies based on AI models has provided an unprecedented predictive capacity for toxicology.
Fig 2. Stages making up in silico toxicology. (Pérez, et al., 2021)
ADMET stands for absorption, distribution, metabolism, excretion, and toxicity. These are the key factors that determine the safety, uptake, elimination, metabolic behavior, and effectiveness of drugs. By the prediction of ADMET properties, scientists can evaluate their drug candidates and select compounds that are likely to yield the desired effects in patients. Building ADMET profiles involves exploring a heterogeneous set of properties, such as compound hepatotoxicity, blood-brain barrier penetration, cytochrome P450 enzyme inhibition, and adverse drug reactions. The growing performance of machine learning algorithms and the increased availability of the ADMET dataset makes it possible to predict the ADMET properties by AI-assisted methods.
Creative Biolabs also provides routine structure and function prediction services including molecular docking, virtual screening, molecular dynamics simulation, and the analysis of quantitative structural activity relationship (QSAR). Molecular docking can predict the preferred orientation of a given molecule when they’re bound to each other to form a stable complex. Virtual screening can use computer tools to automatically evaluate a large library of compounds. Molecular dynamics simulation is a computer simulation technique to study the physical motion of atoms and molecules. QSAR is a machine learning process used to develop meaningful associations between molecular structural features and biological activity.
Currently, researchers used quantum chemical calculations in various fields of physics and chemistry more and more often. Quantum chemical calculations have the ability to predict the behavior of molecules in various cases. Moreover, quantum chemical calculations have also been used to describe reaction mechanisms. Quantum chemistry is the only non-indirect source of information about the structure and energy of transition states, and they cannot be experimentally observed. Creative Biolabs is able to offer AI-assisted molecular structure calculation, molecular properties, and reaction mechanism calculation.
References
