Scientific Tools
Vicena gives your AI research agent access to 24 specialized tools built on 26 scientific libraries, databases, and models spanning literature search, lab simulation, computational chemistry, and cloud computing.
The agent selects the right tool for each step of your research. You can also pin specific tools or let the agent decide autonomously. Try them free.
Looking for chemistry specifically? See our dedicated page on AI for real chemistry — protocol audit, reaction prediction, and quantum chemistry with PySCF.
We are constantly working to improve and expand Vicena for your research and engineering work. Tell us what you need.
Research & Discovery
4 toolsSearch scientific literature, patents, and the web. The AI agent iterates with refined queries across multiple databases until it has comprehensive, cited results.
Literature Review
Deep research agent for scientific papers
Searches PubMed, arXiv, and Google Scholar in parallel. The agent evaluates results, reformulates queries for better coverage, and cross-references findings across sources. Every result is linked to its original paper with DOIs, authors, and publication dates.
How it works
The agent generates multiple search queries from your question, runs them in parallel across PubMed, arXiv, and Google Scholar, then evaluates coverage gaps. It iterates up to 10 times, refining queries until results are comprehensive. Each paper is returned with DOI, authors, journal, and a relevance summary.
Input
A natural language research question or topic. Be as specific as you would in a database search. You can include constraints like date ranges, organisms, or techniques.
Output
A structured list of papers with titles, authors, journal, year, DOIs, and a relevance summary for each. Papers are grouped by subtopic when the query is broad.
Limitations
Searches open-access metadata and abstracts. Full-text analysis depends on open-access availability. Very new preprints (last 24h) may not be indexed yet.
Tips
Use this for broad research questions and trend analysis. For extracting specific experimental procedures, use Protocol Extraction instead. For patents, use Prior Art Search.
Example prompts
- › Find recent papers on CRISPR delivery mechanisms in solid tumors
- › What is the state of the art in perovskite solar cell stability?
- › Review the literature on metal-organic frameworks for CO2 capture
Prior Art Search
Deep search for patents and prior art
Searches global patent databases including Google Patents for prior art, assignees, and inventive history. Filters by inventor, date range, and jurisdiction. Use it to check freedom to operate or find prior art for your method.
How it works
Queries Google Patents covering 120+ million patent documents from the USPTO, EPO, and WIPO. The agent refines search terms across patent classifications, filters by date and assignee, and cross-references cited and citing patents to map the inventive landscape.
Input
A natural language description of the invention or technology. You can include specific assignees, date ranges, or patent classification codes.
Output
A list of patents with titles, patent numbers, assignees, filing dates, and a summary of each patent's claims. Includes citation links.
Limitations
Covers patents indexed by Google Patents. Some recently filed applications may have an indexing delay. Does not provide legal opinions on patentability.
Tips
Use this for patent landscape analysis and freedom-to-operate checks. For scientific papers, use Literature Review instead.
Example prompts
- › Find patents on electrochemical CO2 reduction catalysts filed after 2020
- › Search prior art for a biodegradable polymer stent with drug elution
- › What patents does BASF hold on lithium-sulfur battery electrolytes?
Protocol Extraction
Search and extract experimental protocols
Finds step-by-step experimental protocols from scientific papers. Extracts every variable (temperatures, concentrations, durations, reagents) independently from each source and assigns confidence scores so you know which values are well-supported.
How it works
Searches for papers matching your experiment, then reads each paper to extract the methods section. Variables (temperatures, concentrations, durations, reagents) are extracted independently from each source and cross-referenced. Each value gets a confidence score based on how many sources agree.
Input
A description of the experiment or synthesis you want a protocol for. The more specific you are about the technique, organism, or compound, the better the results.
Output
A step-by-step protocol with reagents, quantities, temperatures, durations, and equipment. Each variable includes a confidence score and the source papers it was extracted from.
Limitations
Protocols are extracted from published methods sections. Proprietary or unpublished methods are not available. Confidence scores reflect source agreement, not absolute correctness.
Tips
Use this when you need a specific recipe or procedure. For broad research questions, use Literature Review. You can feed the extracted protocol into the Protocol Simulator to validate it.
Example prompts
- › Extract the protocol for synthesizing gold nanoparticles via citrate reduction
- › How is Western blot performed for detecting phosphorylated ERK?
- › Find the experimental procedure for Suzuki coupling of aryl bromides
Web Research
Deep research agent for the open web
Searches the general web for technical specifications, equipment manuals, chemical pricing, safety data sheets, and anything not found in papers or patents. Uses adaptive query refinement for comprehensive results.
How it works
Performs multi-round web searches with adaptive query refinement. The agent evaluates each batch of results, identifies information gaps, and generates new queries until the answer is comprehensive. Extracts and cites specific pages.
Input
Any question about equipment, pricing, suppliers, technical specifications, or practical lab information that is not covered by scientific papers or patents.
Output
A structured answer with extracted facts, prices, or specifications. Each piece of information is cited with its source URL.
Limitations
Results depend on what is publicly available on the web. Paywalled content, internal company documents, and very recent pages may not be accessible.
Tips
Use this for practical lab questions: equipment specs, reagent pricing, supplier comparisons, SDS sheets. For scientific literature, use Literature Review.
Example prompts
- › What is the price range of 99.9% pure titanium dioxide from lab suppliers?
- › Find the operating manual for a Bruker 400 MHz NMR spectrometer
- › Compare specifications of benchtop centrifuges rated for 15,000 RPM
Lab Simulation & Validation
7 toolsSimulate your protocol in a virtual lab before going to the bench. The AI validates each step against thermodynamic, kinetic, and chemical constraints.
Protocol Audit
Safety, yield, and feasibility check
Reviews your synthesis protocol and flags physical impossibilities and safety risks before you go to the bench. Checks conservation of mass, yield limits, reagent-vessel compatibility, and GHS hazards. When a check has no rule for your compound, the audit says so honestly instead of implying safety.
How it works
The agent decomposes your protocol and runs deterministic checks on each step: yield validation (reactant MW vs product MW via RDKit), atom balance (conservation of mass from SMILES), chemical compatibility (curated rules + SMARTS-based classification, e.g. HF+glass, alkali+protic, chlorinated+polycarbonate), and boiling point lookup from the Thermo library. Safety data is pulled live from PubChem. Every finding cites its source. Tools return facts, not verdicts — the LLM synthesizes the final judgment.
Input
A synthesis protocol with reagents, quantities, temperatures, vessels, and claimed yields. Natural language or extracted from a paper.
Output
A report flagging impossibilities (yield > 100%, atoms from nowhere), incompatibilities (with cited rules), GHS hazards, and coverage gaps where the audit could not verify and you must apply your own judgment.
Limitations
~20 hardcoded compatibility rules (more coming via RHEACT/CAMEO). Thermo library covers ~70,000 compounds; unusual or proprietary molecules may hit coverage gaps. The audit complements your expertise, it does not replace it.
Tips
Use Protocol Extraction to pull a protocol from a paper, audit it here for physical issues, then run the Protocol Simulator for full physics validation.
Example prompts
- › Check if 6.2g of naproxen methyl ester from 5g naproxen is physically possible
- › Is it safe to reflux ethyl acetate with NaOH in a glass flask at 90°C?
- › Audit this Fischer esterification: refluxing 30 mL acetic acid with 50 mL ethanol and 2 mL conc. H2SO4 in a round-bottom flask at 85°C for 2 hours, expecting 40 g of ethyl acetate
Protocol Simulator
Physics-grounded protocol validation
Takes your complete protocol and executes each step in a virtual environment that models real-world physics and chemistry. Checks energy balances, reaction rates, and reagent compatibility at every stage, producing a feasibility report.
How it works
Each protocol step is decomposed into physical and chemical operations. Reagent properties are retrieved from PubChem, stoichiometry is balanced via ChemPy, thermodynamic feasibility is checked against the Thermo library (DIPPR correlations), and molecular structures are validated with RDKit. The simulator flags incompatible reagents, unsafe temperature rises, and infeasible reaction conditions.
Input
A step-by-step protocol with reagents, quantities, temperatures, and durations. Can be pasted from a paper or described in natural language.
Output
A feasibility report with pass/fail per step, flagging safety risks (thermal runaway, solvent boiling), stoichiometric errors, and reagent incompatibilities.
Limitations
Validates against known thermodynamic and chemical data. Cannot simulate novel reactions with no literature data. Does not model equipment-specific constraints (e.g. stirring speed, vessel geometry).
Tips
Use Protocol Extraction first to get a protocol from papers, then feed it into the Protocol Simulator to validate it before going to the bench.
Example prompts
- › Simulate this nanoparticle synthesis protocol and check for safety issues
- › Validate my esterification protocol: 50 mL ethanol, 30 mL acetic acid, 2 mL H2SO4, reflux 2h
- › Can I run this polymerization at 180C in DMSO without boiling the solvent?
ThermoMath Engine
Physics and stoichiometry calculations
Calculates balanced chemical equations, limiting reactants, theoretical yields, and handles vapor pressure and Ideal Gas Law calculations. The foundation for all quantitative chemistry in the platform.
How it works
Balances chemical equations symbolically using ChemPy, identifies limiting reagents from input masses, and computes theoretical yields. Vapor pressures are calculated from Antoine equation parameters in the Thermo library. Ideal Gas Law calculations handle non-standard conditions.
Input
A chemical equation (can be unbalanced) with optional reagent masses in grams. Or a compound name with temperature for vapor pressure calculations.
Output
Balanced equation, limiting reagent, theoretical yield in grams and moles, or vapor pressure in the requested units.
Limitations
Requires known compounds in the Thermo/ChemPy databases. Cannot handle reaction mixtures with unknown intermediates.
Tips
Use this for quick stoichiometric calculations. For thermal safety analysis, use Reaction Energetics. For reaction timing, use Reaction Kinetics.
Example prompts
- › Balance the combustion of propane and calculate the yield from 50g
- › What is the vapor pressure of ethanol at 60C?
- › How many grams of NaCl do I get from 10g NaOH and excess HCl?
Reaction Energetics
Virtual calorimeter and thermal safety
Calculates reaction enthalpy and the resulting adiabatic temperature rise. Detects thermal runaway risks, solvent boiling hazards, and exothermic safety concerns before you run the reaction.
How it works
Computes reaction enthalpy from standard formation enthalpies (Thermo database, 70,000+ compounds). Calculates adiabatic temperature rise using heat capacities of the reaction mixture. Compares the predicted temperature against solvent boiling points and known decomposition thresholds to flag runaway or boiling risks.
Input
A chemical reaction with reagent names or formulas. Optionally include quantities and solvent for adiabatic temperature rise calculations.
Output
Reaction enthalpy (kJ/mol), adiabatic temperature rise, and safety flags (exothermic warning, boiling risk, runaway risk).
Limitations
Relies on standard formation enthalpy data. Compounds not in the Thermo database cannot be analyzed. Does not model heat dissipation or cooling.
Tips
Use this before running any exothermic reaction. If the adiabatic temperature rise exceeds the solvent boiling point, you need active cooling or slower addition.
Example prompts
- › Is the neutralization of concentrated H2SO4 with NaOH safe in a 500 mL flask?
- › Calculate the adiabatic temperature rise for nitration of toluene
- › Will my Grignard reaction overheat if I add the reagent too fast?
Reaction Kinetics
Rate constants, half-lives, and timing
Estimates how long a reaction takes and how temperature affects speed. Uses the Arrhenius equation and integrated rate laws to calculate rate constants, half-lives, and time-to-completion.
How it works
Uses the Arrhenius equation (k = A * exp(-Ea/RT)) to compute or adjust rate constants at different temperatures. Applies integrated rate laws for zero, first, and second-order reactions to calculate half-lives and time to reach a target conversion.
Input
Activation energy (Ea), pre-exponential factor (A), reaction order, and temperature. Or provide a known rate at one temperature to predict rates at another.
Output
Rate constant at the specified temperature, half-life, and estimated time to reach a target conversion percentage.
Limitations
Requires known kinetic parameters (Ea and A). For reactions where these are unknown, the tool can estimate from two data points at different temperatures.
Tips
Use this to plan reaction timing and temperature optimization. Combine with Reaction Energetics to check both speed and safety at your chosen temperature.
Example prompts
- › How long does a first-order reaction with Ea=85 kJ/mol take at 60C vs 80C?
- › Estimate the half-life of aspirin hydrolysis at room temperature
- › If my reaction is 50% complete in 2 hours at 25C, how fast is it at 40C?
Solubility Predictor
Solvent compatibility and dissolution
Predicts whether a compound dissolves in a given solvent using polarity matching via LogP. Ranks common lab solvents by compatibility. Use before choosing a reaction or workup solvent.
How it works
Calculates the octanol-water partition coefficient (LogP) of the solute using RDKit descriptors. Compares it against the polarity profile of common lab solvents (water, ethanol, DCM, hexane, DMSO, etc.) to rank solvents by predicted compatibility. Retrieves additional solubility data from PubChem when available.
Input
A compound name, SMILES, or CAS number. Optionally specify a solvent to check, or ask for a ranked list of common solvents.
Output
A compatibility prediction (soluble/insoluble/partial) with a ranked list of solvents from best to worst match.
Limitations
Based on LogP polarity matching, which is a heuristic. Does not account for specific solute-solvent interactions, pH effects, or temperature dependence.
Tips
Use this before choosing a reaction solvent or planning a liquid-liquid extraction. For safety data on solvents, combine with the Safety Summary tool.
Example prompts
- › Will ibuprofen dissolve in water or do I need an organic solvent?
- › Rank solvents for dissolving polyethylene glycol 6000
- › Is caffeine more soluble in ethanol or dichloromethane?
Spectroscopy Predictor
Predicted IR, NMR, and MS fingerprints
Predicts the expected spectral fingerprint (IR, NMR, MS) of a compound by identifying its functional groups. Verify whether your reaction produced the correct product or determine what peaks to look for.
How it works
Parses the molecular structure with RDKit and scans it against a library of SMARTS patterns to identify functional groups. Maps each group to its characteristic spectral signatures: IR absorption bands (cm-1), expected 1H/13C NMR chemical shift ranges, and mass fragmentation patterns. Returns a predicted fingerprint you can compare against your experimental spectrum.
Input
A compound name, SMILES string, or CAS number. You can also describe a reaction product and ask what peaks to expect.
Output
Predicted IR bands (cm-1 with assignment), expected NMR chemical shifts (ppm ranges per proton environment), and major mass spec fragments (m/z).
Limitations
Predictions are based on functional group identification, not full quantum mechanical calculations. Fine structure splitting in NMR and exact fragmentation patterns may differ from experiment.
Tips
Use this to verify reaction products: compare the predicted fingerprint against your measured spectrum. For full computational spectra, use the Science Computer with PySCF.
Example prompts
- › What IR peaks should I expect from the product of Fischer esterification?
- › Predict the NMR spectrum of aspirin
- › I see a peak at 1720 cm-1 in my IR spectrum. What functional group is that?
Computational Chemistry
10 toolsAnalyze molecular structures, predict reactions, calculate properties, and assess safety. Powered by RDKit, PubChem, and neural reaction models.
Chemical Analyzer
Properties and hazards lookup
Retrieves physical properties and safety data for chemicals from PubChem. Returns boiling points, molecular weights, GHS hazard classifications, and reactive group information.
How it works
Queries the PubChem REST API (116 million compounds) by name, CAS number, or SMILES. Returns physical constants (melting point, boiling point, density, molecular weight), GHS hazard pictograms, H-statements, and reactive group classifications.
Example prompts
- › What are the physical properties and hazards of dimethyl sulfoxide?
- › Look up the boiling point and GHS classification of acetonitrile
- › Is sodium azide classified as explosive?
Reaction Predictor
Neural network reaction prediction
Predicts products of complex chemical reactions using a trained neural network. Optimized for multi-step and pharmaceutical reactions like Suzuki coupling, Heck reactions, and Sonogashira coupling. ~93% accuracy on complex patent reactions.
How it works
Converts reactants to SMILES notation and feeds them through a Molecular Transformer, a sequence-to-sequence neural network trained on 1.2 million patent reactions. The model treats reactions as translations between molecular languages. Predicted products are validated for chemical validity using RDKit before being returned.
Input
Reactant names, SMILES strings, or a natural language description of the reaction. You can specify catalysts and conditions.
Output
Predicted product(s) as SMILES with names and a confidence indicator. The product is validated for chemical correctness.
Limitations
Optimized for organic synthesis. Less reliable for inorganic, enzymatic, or radical reactions. Accuracy is ~93% on complex patent-style reactions, lower on unusual chemistries.
Tips
Use this for complex, multi-step reactions. For simple textbook reactions (acid-base, esterification), use Simple Reactions instead for higher accuracy.
Example prompts
- › Predict the product of Suzuki coupling between phenylboronic acid and 4-bromoanisole
- › What do I get when I react aniline with acetic anhydride?
- › Predict the product of a Heck reaction with styrene and iodobenzene
Retrosynthesis
Work backwards from target molecule
Suggests reactants needed to synthesize a target molecule. Proposes synthetic routes by working backwards from your desired product, identifying feasible starting materials and reaction conditions.
How it works
Takes a target molecule in SMILES format and runs it through the Molecular Transformer in reverse mode. The model proposes disconnections and suggests commercially available starting materials. Multiple synthetic routes are ranked by feasibility.
Input
A target molecule as a name, SMILES string, or drawn structure.
Output
One or more proposed synthetic routes with starting materials and reaction types. Routes are ranked by feasibility.
Limitations
Works best for drug-like organic molecules. Very large molecules (polymers) or inorganic compounds may produce unreliable suggestions.
Tips
Use this when you know what you want to make but not how to make it. Combine with the Reaction Predictor to validate each proposed step.
Example prompts
- › How can I synthesize ibuprofen from simple starting materials?
- › Suggest a retrosynthetic route to paracetamol
- › What reactants do I need to make 4-nitroaniline?
Simple Reactions
Textbook reaction predictions
Predicts products of common textbook reactions: esterification, acid-base neutralization, SN2 substitution, hydrolysis, and oxidation/reduction of simple substrates.
How it works
Uses rule-based reaction templates implemented in RDKit for well-characterized reaction types. Unlike the neural predictor, this is deterministic and optimized for simple, well-understood transformations where accuracy is near 100%.
Input
Reactant names or formulas and the reaction type (e.g. "esterification", "neutralization", "SN2").
Output
The predicted product with a balanced equation.
Limitations
Only covers well-known textbook reaction types. For complex or novel reactions, use the Reaction Predictor.
Tips
Use this for common organic and inorganic reactions where accuracy matters more than novelty. The rule-based approach is deterministic, so identical inputs always give identical outputs.
Example prompts
- › What is the product of ethanol and acetic acid with an acid catalyst?
- › Predict the product of SN2 reaction between NaBr and 1-chlorobutane
- › What happens when you mix HCl and NaOH?
Functional Group Identifier
SMARTS substructure matching
Identifies functional groups present in a molecule from its SMILES representation. Uses SMARTS pattern matching to scan for common organic functional groups.
How it works
Parses the input molecule with RDKit and runs it against a curated library of SMARTS patterns covering 60+ functional groups: alcohols, amines, carbonyls, halogens, heterocycles, and more. Reports all matches with their positions in the molecule.
Input
A molecule name, SMILES string, or CAS number.
Output
A list of all functional groups found in the molecule, with their names and positions.
Limitations
Identifies standard organic functional groups. Unusual or very complex heterocyclic motifs may not be covered.
Tips
Use this to understand an unfamiliar molecule before running other tools. Knowing the functional groups helps predict reactivity, solubility, and spectral features.
Example prompts
- › What functional groups are present in aspirin?
- › Identify the functional groups in glucose
- › Does this SMILES contain any amine groups? CC(=O)Nc1ccc(O)cc1
Molecular Descriptors
Drug-likeness and Lipinski analysis
Calculates molecular descriptors and checks Lipinski's Rule of Five for drug-likeness. Returns LogP, molecular weight, hydrogen bond donors/acceptors, and polar surface area.
How it works
Computes 2D molecular descriptors using RDKit: LogP (Wildman-Crippen), molecular weight, number of hydrogen bond donors and acceptors, topological polar surface area, and rotatable bond count. Evaluates Lipinski's Rule of Five and Veber's rules to assess oral bioavailability.
Input
A molecule name, SMILES string, or CAS number.
Output
A table of descriptors (LogP, MW, HBD, HBA, TPSA, rotatable bonds) and a pass/fail assessment against Lipinski and Veber rules.
Limitations
Evaluates drug-likeness based on physicochemical properties only. Does not predict biological activity, toxicity, or metabolic stability.
Tips
Use this early in drug design to filter candidates. Molecules that fail Lipinski's rules are unlikely to be orally bioavailable.
Example prompts
- › Does caffeine pass Lipinski's Rule of Five?
- › Calculate the LogP and polar surface area of metformin
- › Is this molecule drug-like? CC(=O)Oc1ccccc1C(=O)O
Molecular Similarity
Tanimoto fingerprint comparison
Calculates structural similarity between two molecules using Morgan fingerprints and Tanimoto coefficient. Returns a score between 0 (completely different) and 1 (identical).
How it works
Generates Morgan circular fingerprints (radius 2, 2048 bits) for each molecule using RDKit. Computes the Tanimoto coefficient (intersection over union of bit vectors) to quantify structural similarity. This is the same method used in pharmaceutical virtual screening.
Input
Two molecule names, SMILES strings, or CAS numbers to compare.
Output
A Tanimoto similarity score between 0.0 (completely different) and 1.0 (identical), with a qualitative assessment.
Limitations
Measures 2D structural similarity only. Molecules with similar shapes but different connectivity (3D similarity) are not captured.
Tips
Scores above 0.85 generally indicate very similar molecules. Use this to find structural analogs or check if two molecules are variants of the same scaffold.
Example prompts
- › How similar are ibuprofen and naproxen?
- › Compare the structures of caffeine and theobromine
- › Is aspirin structurally similar to salicylic acid?
Safety Summary
GHS hazard information
Retrieves GHS safety information from PubChem for any chemical. Returns hazard statements, signal words, and pictogram descriptions. Accepts chemical names, SMILES, or CAS numbers.
How it works
Queries PubChem's GHS classification data. Returns the signal word (Danger/Warning), all H-statements (hazard), P-statements (precaution), and pictogram codes. Accepts input as chemical name, SMILES, or CAS number.
Input
A chemical name, SMILES string, or CAS number.
Output
Signal word (Danger/Warning), GHS pictograms, hazard statements (H-codes), and precautionary statements (P-codes).
Limitations
Returns the GHS classification from PubChem. Compounds not registered in PubChem will not have data. Does not assess mixture hazards.
Tips
Always check safety before handling a new reagent. Combine with the Solubility Predictor to assess both compatibility and safety of your chosen solvents.
Example prompts
- › What are the safety hazards of hydrofluoric acid?
- › Is methanol toxic? What precautions do I need?
- › Give me the GHS classification for sodium cyanide
Molecule Converters
Name, SMILES, and CAS conversion
Converts between molecule representations: common names to SMILES, SMILES to names, and molecules to CAS registry numbers. Uses PubChem as the reference database.
How it works
Resolves chemical identifiers through PubChem's standardization pipeline. Converts between IUPAC names, common names, CAS registry numbers, and SMILES/InChI representations. Handles synonyms and trade names.
Input
A molecule in any format: common name, IUPAC name, CAS number, or SMILES string.
Output
The molecule in the requested format (SMILES, name, or CAS), with the PubChem CID for reference.
Limitations
Relies on PubChem's compound registry. Very new or proprietary compounds may not be found.
Tips
Use this to translate between formats when other tools require SMILES input. Most chemistry tools in Vicena also accept names directly, but SMILES is unambiguous.
Example prompts
- › What is the SMILES for ibuprofen?
- › Convert CAS 50-78-2 to a chemical name
- › What is the CAS number for dimethylformamide?
Quantum Chemistry
DFT, Hartree-Fock, and post-HF calculations
Runs first-principles electronic structure calculations on your molecule. The agent writes a PySCF notebook, executes it on your cloud computer, and returns energies, orbitals, and geometries. Supports DFT, Hartree-Fock, and post-HF methods like MP2.
How it works
The agent selects an appropriate method and basis set (e.g. B3LYP/6-31G* for DFT), builds a PySCF input using ASE for geometry, and runs the calculation in your persistent JupyterLab environment. Results are parsed back into the conversation with tables and plots.
Input
A molecule (name or SMILES) and the property you want to compute: energy, optimized geometry, HOMO-LUMO gap, IR spectrum, partial charges, etc.
Output
A notebook with the calculation, numerical results, and any plotted data (orbitals, geometries, spectra). Files persist in your cloud environment.
Limitations
CPU-only environment: small-to-medium molecules only (~30 heavy atoms). No periodic DFT or correlated methods beyond MP2. For large systems, use semi-empirical methods instead.
Tips
Combine with Molecular Descriptors for quick ballpark values before running a full quantum calculation. For reaction energetics that don't require first principles, use Reaction Energetics (much faster).
Example prompts
- › Optimize the geometry of caffeine with DFT and show the HOMO-LUMO gap
- › Run a Hartree-Fock calculation on water at STO-3G and show the orbital energies
- › Compute the dipole moment of ammonia using B3LYP/6-31G*
Science Computer
3 toolsA persistent cloud computer with JupyterLab where you and the AI agent collaborate in real notebooks. Write code, run simulations, and visualize results together.
Compute Lab
Isolated Linux container for code execution
Run shell commands in an isolated Linux environment. Install packages, manipulate files, and execute scripts. Pre-installed with the full scientific Python stack including RDKit, PySCF, ASE, and more. The environment persists across conversations so your work is never lost.
How it works
Each user gets a dedicated Linux container with persistent storage. The agent runs shell commands directly and reads the output. Packages installed via pip or apt persist across sessions. The container is isolated from other users.
Input
Natural language instructions for what you want to run, install, or compute. You can also paste shell commands directly.
Output
The command output (stdout/stderr) displayed inline in chat. Files created are saved to your persistent storage.
Limitations
CPU-only environment (no GPU). Long-running computations may time out after 2 minutes per command. Network access is available for downloading packages and data.
Tips
Use this for quick one-off commands. For iterative computation with plots and tables, use Jupyter Notebooks instead.
Example prompts
- › Install openbabel and convert this SDF file to SMILES
- › Run a Python script that reads my CSV and plots the dose-response curve
- › Download the PDB structure 1UBQ and extract the alpha carbons
Jupyter Notebooks
Collaborative AI-powered notebooks
The agent builds Jupyter notebooks cell by cell: writes code, checks output, fixes errors, and refines. With 30+ scientific packages pre-installed, you can run real computations immediately.
How it works
Runs a full JupyterLab instance in your persistent cloud environment. The AI agent writes and executes notebook cells, reads outputs (including plots and tables), debugs errors, and iterates. You see every step live and can edit alongside the agent.
Input
A description of what you want to compute, analyze, or visualize. You can reference uploaded files or previous notebook results.
Output
A Jupyter notebook with code cells, outputs, plots, and tables. The notebook is saved to your persistent storage and can be re-opened later.
Limitations
CPU-only environment. Very large datasets (>1 GB) or GPU-dependent ML training are not supported. 30+ packages are pre-installed; others can be installed on demand.
Tips
This is the most powerful tool for custom computation. Use it when you need plots, iterative analysis, or multi-step calculations that go beyond what the built-in tools offer.
Example prompts
- › Build a notebook that calculates the molecular orbitals of benzene using PySCF
- › Create a notebook analyzing my XRD data and identifying crystal phases
- › Plot the Michaelis-Menten kinetics for these enzyme assay results
File System
Persistent cloud file management
Read, write, and manage files in your persistent cloud environment. Upload data, save results, and organize your work across sessions. Supports all common file formats.
How it works
Provides full filesystem access within your persistent container. The agent can read, write, move, delete, and search files. Uploaded data and generated results persist across conversations.
Input
Natural language instructions for file operations, or specific file paths to read or write.
Output
File contents, directory listings, or confirmation of write/move/delete operations.
Limitations
Files are stored in your personal container. Storage is persistent but not unlimited. Very large files (>100 MB) may take longer to process.
Tips
Use this to manage data between conversations. Upload a CSV, have the agent analyze it in a notebook, then save the results for next time.
Example prompts
- › Read the CSV I uploaded and summarize the columns
- › Save these simulation results as a JSON file
- › List all the notebooks I created last week
Science Stack
26 databases, libraries & modelsThe databases, libraries, and models that power Vicena's tools. All are available in the Science Computer for direct use in your notebooks.
by National Library of Medicine (NIH)
The US National Library of Medicine database with over 36 million biomedical citations. The primary source for life sciences and biomedical literature worldwide.
by Cornell University
Cornell University's open-access repository hosting over 2.4 million preprints in physics, mathematics, computer science, and quantitative biology. Covers cutting-edge research before peer review.
by Google
Google's academic search engine indexing the full text of scholarly literature across publishers, disciplines, and formats. Covers papers, theses, books, and conference proceedings.
by Google
Google's patent search covering over 120 million patent documents from 100+ patent offices worldwide, including the USPTO, EPO, and WIPO.
by National Center for Biotechnology Information (NIH)
The world's largest open chemistry database, maintained by the NIH. Contains data on 116 million compounds including structures, properties, biological activities, safety information, and patent references.
by Greg Landrum and contributors
The industry-standard open-source cheminformatics toolkit used by Pfizer, Novartis, and Merck. Handles molecular representation, substructure search, fingerprinting, and property calculation.
by Bjoern Dahlgren
A Python library for physical chemistry. Solves stoichiometry, balances equations, computes equilibrium constants, and models chemical kinetics from first principles.
by Caleb Bell and contributors
An open-source thermodynamic properties library covering 70,000+ chemicals. Calculates vapor pressure, heat capacity, enthalpy, and phase equilibria using validated correlations from the DIPPR database.
by Qiming Sun et al.
A quantum chemistry package for Hartree-Fock, DFT, and post-Hartree-Fock calculations. Used in academic research for electronic structure simulations of molecules and materials.
by Technical University of Denmark
The Atomic Simulation Environment, a set of tools for setting up, running, and analyzing atomistic simulations. Interfaces with dozens of quantum chemistry and molecular dynamics codes.
by NumPy community
The fundamental package for numerical computing in Python. Provides N-dimensional arrays, linear algebra, Fourier transforms, and random number generators. The foundation of nearly all scientific Python.
by SciPy community
Built on NumPy, SciPy adds optimization, integration, interpolation, signal processing, and statistical functions. The go-to library for scientific and engineering computation.
by Wes McKinney and contributors
The standard library for data manipulation in Python. DataFrames make it easy to clean, transform, and analyze tabular data from experiments, simulations, and databases.
by John D. Hunter and contributors
The most widely used plotting library in science. Produces publication-quality figures, histograms, spectra, and scatter plots. Used in thousands of peer-reviewed papers every year.
by Plotly Technologies Inc.
An interactive visualization library for 3D plots, dashboards, and dynamic charts. Particularly useful for exploring molecular structures, reaction landscapes, and multi-dimensional data.
by Meta AI (FAIR)
Meta's open-source deep learning framework, the most popular in academic research. Powers neural networks for reaction prediction, molecular property estimation, and scientific data analysis.
by Hugging Face
Hugging Face's library providing access to thousands of pre-trained models for NLP, computer vision, and scientific applications. Used for text analysis of papers and chemical language models.
by SymPy community
A symbolic mathematics library for Python. Solves equations algebraically, computes integrals and derivatives, and simplifies expressions. Useful for deriving analytical solutions to scientific problems.
by INRIA and contributors
The most widely used machine learning library in Python. Provides classification, regression, clustering, and dimensionality reduction algorithms for analyzing scientific datasets.
by Intel, Willow Garage, and contributors
The standard computer vision library with tools for image processing, feature detection, and analysis. Used in microscopy, materials characterization, and automated lab image analysis.
by Caleb Bell
A Python library for fluid mechanics calculations. Computes pressure drops, pipe friction factors, and hydraulic properties for chemical engineering and process design.
by Project Jupyter
The open-source interactive development environment used by millions of scientists. Originally developed at UC Berkeley, Jupyter is the standard for reproducible computational research across all scientific disciplines.
Molecular Transformer
Modelby Philippe Schwaller et al. (IBM Research / EPFL)
A sequence-to-sequence neural network that treats chemical reactions as translations between molecular languages (SMILES). Trained on millions of patent reactions, it predicts products with ~93% accuracy on complex organic synthesis.
Morgan fingerprints
Modelby H. L. Morgan (1965), extended by RDKit
A circular fingerprinting algorithm that encodes the local chemical environment around each atom. Widely used in drug discovery for virtual screening and similarity searching because it captures both topology and atom types.
SMARTS
Standardby Daylight Chemical Information Systems
A pattern language for describing molecular substructures. Used to identify functional groups, pharmacophores, and reactive sites by matching atoms and bonds in molecular graphs.
Arrhenius equation
Modelby Svante Arrhenius (1889)
The foundational model in chemical kinetics describing how reaction rate constants depend on temperature. Developed by Svante Arrhenius in 1889, it remains the standard for predicting reaction speed.
Ready to try?
Describe your research problem and the agent selects the right tools automatically. Most tools are free, no credit card required.
Try it free