# Tag Info

Accepted

### DeepMind just announced a breakthrough in protein folding, what are the consequences?

Imagine if given an amino acid sequence, you could quickly calculate what the shape of the corresponding protein would be. You would be able to predict what effect a mutation would have on the shape ...
• 29.1k
Accepted

### What is the current status of machine learning applied to materials or molecular systems?

Here is state of the art research: Smith J.S. et al, Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning, July 2019 Nat. Commun. 2019, 10 (1)...
• 1,413
Accepted

### Does DeepMind's new protein folding software (AlphaFold) also work well for metalloproteins (proteins with metal cofactors)?

It's a great question! Some of my answer will be taken from my answer to your question on the AI stack exchange, but cross-site questions are allowed and your question here is slightly different so my ...
• 29.1k

### Machine learning interatomic potentials for molecular dynamic simulations: are they good?

Before talking about the pros and cons of ML-potentials, there is a huge conceptual difference between empirical- and ML-potential that needs to be clarified. In empirical potentials, one uses data ...
• 251
Accepted

### Machine learning interatomic potentials for molecular dynamic simulations: are they good?

(Expanding my comment into an answer) When ML-based forcefields are compared to classical forcefield directly, I think we miss the most important points. ML-based models have several advantages: They ...
• 1,658

### What is the state of the art in terms of local atomic environment descriptors for machine learning?

If you are familiar with the Behler-Parrinello symmetry functions implemented in AMP, you may be interested in seeing how they compare to other atom-centered representations in terms of speed and ...
• 333
Accepted

### What does machine learning learn about DFT?

Total energies and HOMO-LUMO gaps are very different quantities, and naturally necessitate very different neural network designs (including the choice of descriptors and architectures) in order to ...
• 7,463
Accepted

### Artificial intelligence is a hot topic, but should I pursue it if I'm interested in Matter Modeling?

"I am a student now and should decide my major to research soon. AI/ML is a very hot research field and I am very interested in it, but I have some doubts before I study AI/ML." AI is ...
• 29.1k

### How to start a Machine Learning project for chemical properties prediction?

Admittedly, there are tons of materials on the chemistry + machine learning topics. Let me give one: An introductory text I find useful is Machine Learning in Chemistry from Janet and Kulik in ACS in ...
• 1,658
Accepted

### General Techniques for Smart Sampling in Matter Machine Learning?

This is not an exhaustive answer. This is an evolving research area in terms of applying ML to dataset generation. I am most familiar with the use case for constructing atomistic potential energy ...
• 2,763

### What is the current status of machine learning applied to materials or molecular systems?

Machine learning (ML) is rapidly gaining its popularity in the field of materials science due to its exceptional ability to learn from data to guide experimentalists, thus reducing traditional trial ...
• 1,952
Accepted

### What are the advantages of (semi)-empirical force fields over Machine Learning Potentials?

The answer to this question is inevitably going to be opinionated. My opinion is that there are still very good reasons to explore the development of force fields while also pursuing better ML ...
• 2,763
Accepted

### Deep Neural Networks: Are they able to provide insights for the many-electron problem or DFT?

"However, it is notorious due to the exponential wall" That is completely true, though there's indeed some methods such as FCIQMC, SHCI, and DMRG that try to mitigate this: How to overcome ...
• 29.1k
Accepted

### What are some examples of active learning methods used in atomistic machine learning?

Inverse designing of materials with known target properties is of great importance (to reduce time, labour, financial etc. costs) than the traditional way of materials design which is guided by human ...
• 1,952

### Benchmark Timings of Machine Learning Potentials vs Molecular Mechanics Force Fields

We performed some timing benchmarks as part of our recent paper, albeit not on molecular dynamics: "Assessing conformer energies using electronic structure and machine learning methods" Int ...
• 7,863
Accepted

### Getting interpretable chemical information from hashed molecular fingerprints

Using RDKit, it's fairly easy to depict bits on example molecules - it's even an example in the documentation "Generating Images of Fingerprint Bits") ...
• 7,863
Accepted

### What are some available software packages for automated finding of local and absolute minima on PES?

The Atomic Simulation Environment has two nice implementations of global optimization algorithms. The first is a basin hopping algorithm from a 1997 paper by Wales and Doye in J. Phys. Chem. A. The ...
• 6,941

### Can Machine Learning lead to the more accurate theories and methods for matter modeling?

It is certainly possible to develop ML models that yield more accurate results than would be possible without ML. One route to do this is through so-called "Δ-learning" where you use ML to ...
• 6,941
Accepted

### Is there a database where one can find the Electron Density data of materials?

I recently made charge densities available for the MOFs and coordination polymers of the Quantum MOF (QMOF) Database. Please read the GitHub page for details on how to access the charge densities. ...
• 6,941

### What is the best way to measure similarity between molecules of the same formula?

tldr; The most common approach is to use fingerprints and compute the Tanimoto similarity There are a variety of ways to compute "molecular similarity" but the most common approach is to ...
• 7,863

### What does machine learning learn about DFT?

It could just be that the features you are using are well suited for describing total energies in these sorts of systems, but not in describing the differences of eigenvalues. When people do ML to try ...
• 729

### Artificial intelligence is a hot topic, but should I pursue it if I'm interested in Matter Modeling?

I did my master's research project in predicting absorption spectra using machine learning (with fingerprints). So, my research is somewhat in the field of material modelling you can say. I want to ...
• 5,834

### How to improve my cross-validation R2_score?

You don't give a lot of details (e.g., type of model, target property, etc.), but with only 300 molecules, it's very likely that your model is over-fit. Thus when you cross-validate, you get low $R^2$....
• 7,863
Accepted

### FireWorks for Workflow management or TensorFlow

Tensorflow and FireWorks are different kinds of software. The "workflow management" features of Tensorflow are primarily designed to manage running Tensorflow itself, while FireWorks and ...
• 1,718

### DeepMind just announced a breakthrough in protein folding, what are the consequences?

Keep in mind that many if not most proteins have multiple quasi-stable conformations, so their 3D structure is not actually a single conformation but rather a Markov matrix of conformations, with ...

### DeepMind just announced a breakthrough in protein folding, what are the consequences?

Probably one of the important applications is Computer Aided Drug Discovery (CADD). If the protein structure could be accurately predicted, one could design protein-ligand docking on the binding ...
• 3,609

### Can Machine Learning lead to the more accurate theories and methods for matter modeling?

Within Monte Carlo (MC) methods, there are a few areas of active research in this regard: Training ML models to identify phase transitions: In practice, it challenging to identify phase transitions ...
• 6,434

### How to proceed with learning application of Machine Learning in material modelling?

The term "Machine learning" is quite general. Let's look at the three main domains of it : Supervised-Learning: In this method, you would need to train a neural network or a statistical ...
• 4,278