aspuru-guzik-group/stoned-selfies

Stars
119
Rank 297,930 (Top 6 %)
Language
Jupyter Notebook
Created almost 4 years ago
Updated 3 months ago

aspuru-guzik-group/stoned-selfies

aspuru-guzik-group

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

This repository contains code for the paper: Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules using SELFIES

STONED-SELFIES

This repository contains code for the paper: Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules using SELFIES. By: AkshatKumar Nigam, Robert Pollice, Mario Krenn, Gabriel dos Passos Gomes, Alán Aspuru-Guzik

Prerequisites:

For cloning the repository, please have a look at the Branch Navigator section.

Before running the code, please ensure you have the following:

SELFIES (any version) - The code was run with v1.0.1. The code is compatible with all v1+.
RDKit
Python 3.0 or up
numpy

Experiment Navigator:

Please have a look at our Tutorial Document. There we provide quick details on how to form local chemical subspaces, generating chemical paths & obtaining median molecules.
Experiment B: Formation of Local Chemical Spaces
Experiment C: Chemical Paths and Rediscovery (with a GA)
Experiment D: Interpolation via Chemical Path formation
Experiment E: Median Molecules for Photovoltaics (obtaining median molecules)

Questions, problems?

Make a github issue 😄. Please be as clear and descriptive as possible. Please feel free to reach out in person: (akshat[DOT]nigam[AT]mail[DOT]utoronto[DOT]ca, rob[DOT]pollice[AT]utoronto[DOT]ca, mario[DOT]krenn[AT]utoronto[DOT]ca , gabriel[DOT]gomes[AT]utoronto[DOT]ca)

License

Apache License 2.0

selfies

Robust representation of semantically constrained graphs, in particular for molecules in chemistry

chemical_vae

Code for 10.1021/acscentsci.7b00572, now running on Keras 2.0 and Tensorflow

ORGANIC

Code repo for optimizing distributions of molecules.

Jupyter Notebook

GA

Code for the paper: Augmenting genetic algorithms with deep neural networks for exploring the chemical space

phoenics

Phoenics: Bayesian optimization for efficient experiment planning

olympus

Olympus: a benchmarking framework for noisy optimization and experiment planning

Jupyter Notebook

JANUS

Code for the paper "JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design"

Tartarus

A Benchmarking Platform for Realistic And Practical Inverse Molecular Design

ChemOS

gryffin

group-selfies

Jupyter Notebook

qtorch

qTorch (Quantum Tensor Contraction Handler) https://arxiv.org/abs/1709.03636 -> for quantum simulation using tensor networks

DiffiQult

A fully autodifferentiable and variational HF

funsies

funsies is a lightweight workflow engine 🔧

gpHSP

Code to build a probabilistic predictive model for HSP

Jupyter Notebook

atlas

A brain for self-driving laboratories

Theseus

Conceptual understanding through efficient inverse-design of quantum optical experiments

SCILLA

Automated discovery of superconducting circuits

Pasithea

Deep Molecular Dreaming

Computer-vision-for-the-chemistry-lab

Use convolutional neural net to detect segment and classify material phases and vessels in chemistry lab and other setting involving materials in mostly transparent vessels

assessing_mol_prediction_confidence

https://arxiv.org/abs/2102.11439

QNODE

Quantum dynamics latent neural ode

xtb-gaussian

A wrapper to run xtb inside Gaussian.

dionysus

For analysis of calibration, performance, and generalizability of probabilistic models on small molecular datasets. Paper on RSC Digital Discovery: https://pubs.rsc.org/en/content/articlehtml/2023/dd/d2dd00146b

golem

Golem: an algorithm for robust experiment and process optimization

Jupyter Notebook

selfies_tutorial

Jupyter Notebook

Beyond-Molecular-Structure-ML-for-OPV-Materials-Devices

kraken

Code to compute electronic and steric features to create a database of ligands and their properties

Meta-VQE

Meta-VQE data and examples repository

Jupyter Notebook

gemini

scalable multi-fidelity machine learning

molar

Molar is a database management to make it easy to store experiment whether computational or not

curiosity

da_for_polymers

Augmenting Polymer Datasets via Iterative Rearrangement

gp_redox_rxn

Code repo for redox potentials with GPs

Jupyter Notebook

long-acting-injectables

Code and results for Machine Learning Models to Accelerate the Design of Polymeric Long-Acting Injectables

Jupyter Notebook

cheapocrest

Conformer generation on the cheap.

acdc_laser

iacta

Code for the paper "Automatic Discovery of Chemical Reactions Using Imposed Activation"

chimera

Chimera: hierarchy-based multi-objective optimization

gryffin-known-constraints

Results for Bayesian optimization with known experimental and design constraints for chemistry applications

Jupyter Notebook

Organic-molcules-with-inverted-gaps

Code and data for organic molecules with inverted singlet-triplet gaps.

atlas-unknown-constraints

Unknown constraints in Bayesian optimization benchmark with Atlas

Jupyter Notebook

routescore

For working on the RouteScore/subway maps project code.

Artificial-Design-of-Organic-Emitters

Code and data for "Artificial Design of Organic Emitters via a Genetic Algorithm Enhanced by a Deep Neural Network".

Semantic-segmentation-of-materials-and-vessels-in-chemistry-lab-using-FCN

Given an image find the region of vessels/container and the material inside it. Assign one or class per pixel using fully convolutional net (FCN)) for semantic segmentation.

quantum-generative-models

kreed

Code for Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance

Jupyter Notebook

Instance-segmentation-of-images-of-materials-in-transparent-vessels-using-GES-net-

Hierarchical instance aware segmentation of materials in vessels in chemistry lab setting using generator evaluator selector net

MERMES

Multimodal Reaction Mining pipeline for ElectroSynthesis: extract reaction information from figures

QIPA

Jupyter Notebook

mission_control

MissionControl: a workflow library.

waveflow

Boundary-conditioned normalizing flows for electronic structures.

jobman

A library for managing job submissions.

chemspyd

CompositeMS

Rational-design-of-organic-molecules-with-inverted-gaps

Code and data for "Rational Design of Organic Molecules with Inverted Gaps between First Excited Singlet and Triplet".

electrode-polishing

DELFI