No wet lab? Discover materials in code.
Applied Materials Science, GuildTrek’s computation-first track for engineers entering materials informatics. Six to nine months, DFT and molecular dynamics plus ML interatomic potentials, and an honest read on scarce data. No wet lab required. Cohorts are forming now; join the early-access list and pick yours.
Cohort forming · limited seats
Fees shared on enquiry · nothing due to apply
What you walk away with
32
Weeks, foundations to discovery
0
Wet labs, computation-first
3
Pillars: simulation, informatics, discovery
100%
Real databases and simulators
1
Closed-loop discovery workflow
Sound familiar?
If any of these is you, keep reading.
If any of these sound like you, this computation-first track was built for exactly your gap.
“You want materials science but have no lab access.”
You discover materials in code, against real databases and simulators.
“DFT and molecular dynamics feel out of reach.”
You run them hands-on with Quantum ESPRESSO and LAMMPS.
“You have heard of graph neural nets but never applied them.”
You build property predictors with M3GNet and CGCNN.
“Materials data is scarce and you do not know how to cope.”
You learn active learning and Bayesian optimization to make it count.
“You are an engineer eyeing materials but unsure how to enter.”
One computation-first path: simulate, predict, then discover.
Why this is different
Plenty of materials lectures stay on the chalkboard. This one runs in code.
The difference is computation: real databases and simulators, with an honest read on scarce data and expensive DFT.
Another materials lecture
GuildTrek
A 40-hour video course you half-finish
Simulations and models you run on real materials data
Textbook crystallography
Code against the Materials Project and real databases
A wet lab you cannot access
Computation-first discovery, no bench required
“Just collect more data”
Active learning and Bayesian optimization for scarce data
A PDF certificate
A public GitHub portfolio of discovery workflows
In 6–9 months, you go from
- "Materials science needs a lab"
- "I have never run a simulation"
- "I am an engineer, not a chemist"
“I simulate materials, predict their properties with ML, and drive discovery in a closed loop, all in code.”
Proof, not a PDF
Simulations and models you run in code.
You query real materials databases, run DFT and molecular dynamics, and train property models, all in code with no wet lab.
The curriculum
What you'll cover.
A structured, level-by-level path. The full topic-by-topic detail comes on enrolment.
1Level 1 · Materials & Computational Foundations
Weeks 1–10- Structure–property paradigm & crystallography
- Bonding, phases, properties & characterization
- Python + pymatgen, ASE & the Materials Project
- Materials databases & data handling
2Level 2 · Simulation & Materials Informatics
Weeks 11–22- DFT & molecular dynamics (Quantum ESPRESSO, LAMMPS)
- Featurization & property prediction
- Graph neural nets for materials (M3GNet, CGCNN)
- ML interatomic potentials & high-throughput screening
3Level 3 · Accelerated Discovery & Enterprise Value
Weeks 23–32- Bayesian optimization & active learning
- Inverse design & generative models (CDVAE)
- Autonomous / self-driving labs
- Domain applications & R&D ROI
4Optional · Industry Certification Prep
- University certs, simulation (ANSYS/COMSOL) & transferable ML
Where it leads
What you'll be ready for.
Cohort forming · limited seats
Stop reading about discovery. Start simulating materials.
Join the early-access list for the next Applied Materials Science cohort and pick the batch that fits you.