Frequently Asked Questions
Everything you need to know about Chemical.AI's retrosynthesis platform, features, and how AI is transforming chemical synthesis.
Product & Platform
-
Chemical.AI is an AI-powered chemistry company founded in 2018, with offices in Toronto, Singapore, Shanghai, and Wuhan. It combines proprietary algorithms, deep chemical expertise, and robotic lab automation to help chemists plan, optimize, and execute chemical synthesis. Chemical.AI serves 100+ pharma, biotech, and CRO partners worldwide and designs over 300,000 synthetic routes annually through its ChemAIRS® platform.
-
ChemAIRS® is Chemical.AI's retrosynthesis planning platform, trained on millions of reactions. It delivers ranked, cost-scored synthesis routes for any target molecule in minutes. Beyond retrosynthesis, ChemAIRS® includes 8 modules: Retrosynthetic Analysis, Forward Synthesis, Synthesizability Assessment (SA Score), Impurity Prediction, Condition Optimisation, Bayesian Optimisation, Process Chemistry, and Internal Data Integration.
-
ChemAIRS® is built for four main user groups. Drug discovery teams use it to explore thousands of pathways and reduce route planning from days to hours. Medicinal chemists use it for diverse, creative route design with real-time cost, yield, and condition prediction. Process development and scale-up teams use it to design cost-efficient, scalable routes from the start. Computational chemists use it to rank virtual libraries by practical synthesizability.
-
ChemAIRS® has been consistently ranked number 1 in idea feasibility and diversity in an independent evaluation conducted by a top chemistry synthesis CRO, where 9 leading CASP tools were evaluated across 60 diverse target molecules and scored by expert synthetic chemists. It is trusted and adopted by the majority of top 10 pharmaceutical companies, CROs, and CDMOs.
-
ChemAIRS® is available via subscription through any modern web browser. Chemical.AI also offers full local deployment for organizations with strict data security or compliance requirements. To get started, visit chemical.ai or contact the team at contact@chemical.ai.
-
Yes. You can try ChemAIRS® directly on the Chemical.AI website. Visit chemical.ai and click "Try ChemAIRS" to get started.
-
ChemAIRS® uses AES-256 encryption and supports full local deployment. It is 21 CFR Part 11 ready, making it suitable for regulated pharmaceutical environments. For organizations that require on-premise deployment, all data stays within your own environment. ChemAIRS® also connects to your existing lab systems via ELN integration, typically set up within days.
-
ChemAIRS® reduces synthesis planning time by approximately 90%. Tasks that traditionally take days are completed in minutes - literature search goes from 3-5 days to 30 seconds, route brainstorming from 2-3 days to 2-4 minutes, cost and reagent checking from 1-2 days to instant, and team review and ELN integration from 2-4 days to real time.
Usage
-
When a retrosynthesis search returns no results, there are several approaches to try. First, increase the risk level in your search parameters - by default ChemAIRS® searches at a low risk level, focusing on well-established chemistry. Switching to a higher risk level allows the algorithm to explore more creative and novel routes. You can also manually break the molecule into smaller fragments using the Manual Search function, or run the search in the Process Chemistry module, which allocates more computational resources and is better suited for complex or challenging targets. If you are still not finding results, contact the Chemical.AI team - they can review your specific molecule and help troubleshoot, or identify whether a gap in the database needs to be addressed.
-
ChemAIRS® ranks routes using a difficulty score - a weighted combination of the number of linear steps and how closely each proposed reaction resembles known, precedented chemistry. The closer a route is to well-established chemistry, the lower the difficulty score. Routes can also be ranked with consideration of your internal ELN data when local deployment is in place, with scores adjusted to reflect real project conditions. ChemAIRS® delivers 10 to 50 prioritized routes per search, and in an internal case study, its top 3 routes aligned with the decisions of expert chemists in 80% of 16 synthetic projects.
-
Yes. Impurity prediction is the process of identifying potential byproducts that may form during a chemical reaction before it is carried out in the lab. In drug development, discovering impurities late - especially during scale-up - can be extremely costly. ChemAIRS®'s Impurity Prediction module allows you to model a single-step reaction before running it. You input the reactants, conditions, and any known contaminants in the raw materials, including trace impurities from a previous step. Each predicted impurity is accompanied by a confidence score from 0 to 100, and ChemAIRS® shows the proposed reaction mechanism mapped to a real reference reaction for every prediction. You can also upload a proton NMR spectrum and overlay it with predicted NMR spectra to confirm whether a structure matches before running more expensive analyses.
-
The SA Score, or Synthesizability Assessment Score, is a metric used to evaluate how practical a molecule is to synthesize. It helps chemists and computational teams prioritize which compounds from a virtual library are realistic to make in the lab, before investing time and resources. In ChemAIRS®, the SA Score is calculated based on retrosynthesis rules rather than chemical similarity - which makes it distinct from other tools that can overestimate or underestimate difficulty. The score runs from 0 to 5. A score of 0 means the compound is commercially available. The score increases as the synthesis becomes longer and more complex. ChemAIRS® validated its SA Score against the assessments of a team of medicinal chemists at Merck across over 13,000 molecules, with close alignment. It is designed for high-throughput screening of large virtual and real compound libraries.
-
No. An SA Score of 5 does not mean the molecule cannot be synthesized. It means the algorithm did not find a straightforward route within the time available for the SA Score calculation. Any compound with a score of 5 can be pushed directly into the Retrosynthesis module for a deeper analysis - routes are often found. SA Score is a prioritization tool, not a yes-or-no gate. It helps teams move from a long list of candidate targets to a short list of realistic first priorities.
-
Yes. Internal Data Integration is one of the 8 core modules in ChemAIRS®. The platform integrates your in-house reaction data to personalize and improve route recommendations. With local deployment, your internal ELN data, building block libraries, and custom vendor catalogs can all be connected - typically within days. The algorithm reads ELN data without requiring human curation, and learnings are retained locally over time through adaptive learning, meaning the platform continues to improve the more your team uses it.
-
Yes. From any route in ChemAIRS®, you can export it as a PDF or Word file with a full step-by-step breakdown. You can also generate a Compound List - a CSV file of every building block, reagent, and solvent required for the synthesis - to cross-reference with your inventory or pass to procurement. Routes can be shared with colleagues or supervisors with one click, as long as they have a ChemAIRS® login. You can also bookmark routes and leave comments directly within the platform.
-
Yes. ChemAIRS® handles stereochemistry in retrosynthesis. For simple chiral molecules with one or a few unrelated chiral centers, ChemAIRS® guides users on how the chirality can be constructed and provides relevant literature references. For molecules with multiple nearby chiral centers, ChemAIRS® focuses on relative configuration and provides supporting references. The platform has also recently added chiral separation and chiral auxiliaries functions, both of which address absolute chiral configurations. A dedicated chirality module is currently in development for more advanced use cases in process chemistry.
Literature & Data
-
ChemAIRS® is trained on a reaction database of over 61 million reactions, combining data from patents including USPTO and EPO, open-source published literature, and Chemical.AI's own proprietary curated datasets. This diverse foundation supports both reliable coverage of known chemistry and strong predictive capability for novel molecules. The platform uses a hybrid approach combining AI and curated rules - unlike purely rule-based tools or purely data-mined tools - which allows it to propose routes that are both grounded in real chemistry and genuinely creative. When local deployment is in place, your internal ELN and building block data can also be integrated to make the model tailored to your organization.
-
Yes. For each reaction step, ChemAIRS® proposes conditions including temperature, solvent, and catalyst, and links directly to the original literature reference. If the default conditions are not suitable, the Condition Search tool gives a full overview of all available literature-backed conditions for that transformation, filterable by pressure, scale, reaction class, and risk items. For process chemistry specifically, conditions demonstrated at 100-gram scale or greater, or sourced from OPRD journals, are specifically flagged to support scale-up decisions.
-
There are several possible reasons. ChemAIRS® only includes building blocks that can ship within two weeks, so routes requiring materials with longer lead times may not appear. A published route may also be deprioritized if it scores higher in difficulty, cost, or number of steps compared to other routes the algorithm identified. Some steps in the published route may have been flagged as uncommon or higher risk. It is also possible the publication is recent and has not yet been incorporated into the database. It is worth noting that ChemAIRS® is designed as a synthesis planning co-pilot, not a literature search tool - it analyzes every molecule as novel and generates the most feasible routes, making it complementary to dedicated database tools like SciFinder or Reaxys. If a specific published route is important to include, ChemAIRS® has a manual search and route import function that allows you to add it directly.
-
The ChemAIRS® software is updated approximately every three months. The AI model is retrained twice a year. UI fixes and bug patches are applied as needed. When local deployment is in place, your internal ELN data continuously contributes to improving route recommendations over time through adaptive learning.
Getting Started
-
There are three ways to input a target molecule into ChemAIRS®. You can draw it directly using the built-in molecule editor, paste a SMILES code copied from ChemDraw or another editor, or use the AI Vision feature to take a screenshot of a molecule from a paper or any other source and let the platform recognize the structure automatically. Once imported, you can use the 2D button to clean up the structure before running the search.
-
Both modules generate synthetic routes but are optimized for different goals. Retrosynthesis is designed for discovery chemists and focuses on identifying the fastest and most feasible synthetic routes, without significant concern for bulk material availability or large-scale cost. Process Chemistry allocates more computational resources - searches can take up to 4 hours - and prioritizes novelty, diversity, and scalability of routes, with a preference for building blocks available in bulk quantities. It also flags conditions demonstrated at 100-gram scale or greater, or sourced from OPRD journals, to support scale-up decisions. If Retrosynthesis does not generate results for a challenging molecule, running the search in Process Chemistry is recommended for additional ideas.
-
FGI stands for Functional Group Interconversion - a strategy used in retrosynthetic analysis where one functional group is transformed into another to make a strategic bond disconnection possible. It is used when a direct disconnection of the target molecule is not immediately feasible, and a functional group transformation is needed first to open up a cleaner synthetic route. FGI is a fundamental concept in retrosynthesis planning and is one of the strategies ChemAIRS® considers when generating retrosynthetic pathways.
Retrosynthesis
-
Retrosynthesis is a problem-solving strategy in organic chemistry where a chemist works backwards from a complex target molecule, systematically breaking it down into simpler precursor molecules until commercially available starting materials are reached. First formalized by Nobel laureate E.J. Corey in the 1960s, retrosynthetic analysis is the foundation of modern synthesis planning. It allows chemists to map out a logical, step-by-step route to any target molecule before setting foot in the lab. AI-powered platforms like ChemAIRS® automate this process, analyzing thousands of possible retrosynthetic pathways in minutes and ranking them by feasibility, cost, and risk.
-
AI-driven retrosynthesis uses machine learning and rule-based models to automate the retrosynthetic process. Instead of relying on a single chemist's intuition and years of experience, AI retrosynthesis platforms analyze thousands of possible bond disconnections, propose reagents and conditions with links to literature references, and rank routes by feasibility, cost, and risk. ChemAIRS® uses a hybrid approach combining AI and curated rules, which allows it to propose both established routes grounded in published chemistry and novel, chemically plausible pathways that have never been published. This makes it particularly valuable for novel molecules where no published synthesis exists.
-
Computer-Aided Synthesis Planning, or CASP, refers to software that uses algorithms and chemical databases to assist chemists in designing synthetic routes. CASP tools reduce the time and effort required for manual literature searching and route brainstorming, helping chemists identify feasible, cost-effective pathways faster. ChemAIRS® is consistently ranked number 1 among leading CASP tools in independent evaluations for idea feasibility and diversity, trusted and adopted by the majority of top 10 pharmaceutical companies, CROs, and CDMOs.
-
Retrosynthesis works backwards from a target molecule to identify simpler starting materials - it answers the question "how do we make this?" Forward synthesis works in the opposite direction, starting from available building blocks or a core scaffold and generating what products or analogues can be made from them - it answers the question "what could we make?" Both approaches are important in drug discovery and medicinal chemistry. ChemAIRS® supports both within a single platform. The Forward Synthesis module helps teams generate focused analogue libraries under defined chemistry constraints, using the building blocks they actually have access to.