Overview
========

Please refer to the separate `online manual <http://mlatom.com/manual/>`_ for the command-line use of MLatom.

- Simulations

  - :ref:`single-point calculations <cl_manual_sp>`
  - :ref:`geometry optimizations <cl_manual_geomopt>` (minima and transition states, IRC)
  - :ref:`frequencies & thermochemistry <cl_manual_freq>`
  - :ref:`molecular dynamics <cl_manual_md>`
  - :ref:`IR and power spectra from MD <cl_manual_md2vib>`
  - :ref:`simulations with AI-enhanced QM methods and pre-trained ML models <cl_manual_simu_pretrain_model>` (AIQM1, ANI-1ccx, etc.)
  - :ref:`simulations with QM methods <cl_manual_qm_methods>`
  - :ref:`simulations with user-trained models <cl_manual_simu_user_train_model>`
  - :ref:`quantum dynamics with machine learning <cl_manual_qdml>`
  - :ref:`UV/vis spectra <cl_manual_UV>` (ML-NEA)
  - :ref:`two-photon absorption cross sections <cl_manual_two_photon_absorption>` (ML-TPA)

- Learning

  - :ref:`training popular ML models <cl_manual_train_popular>` (KREG, ANI, sGDML, PhysNet, DPMD, GAP-SOAP, KRR-CM)
  - :ref:`training generic ML models <cl_manual_traingeneric>` (kernel ridge regression with many kernels)
  - :ref:`optimizing hyperparameters <cl_manual_hyperopt>`
  - :ref:`evaluating ML models <cl_manual_estAccMLmodel>` (also with learning curves)
  - :ref:`Δ-learning <cl_manual_deltalearning>`
  - :ref:`self-correction <cl_manual_selfcorrection>`

- Data

  - :ref:`converting XYZ coordinates to molecular descriptor <cl_manual_xyz2x>` (RE, Coulomb matrix, …)
  - :ref:`analyzing data sets <cl_manual_analyze>`
  - :ref:`sampling <cl_manual_sample>` (random, structure-based, farthest-point) and splitting datasets