Questions tagged [machine-learning]
for questions about applications of machine learning algorithms to chemistry, not the machine learning methods themselves. Often bridging cheminformatics and computational chemistry, these methods consider how to represent chemical data to ML methods, accuracy thereof, and applications of chemical interest.
30
questions
2
votes
0
answers
26
views
How does ML / AI models can help us in high throughput screening studies?
I am a chemist interested in applying fast methods to search for suitable molecular candidates for several applications (let's say HOMO LUMO gaps, excitation energies, etc.) As a consequence, I ...
5
votes
2
answers
102
views
How to get continuous spectral data into intensities of channels centered around wavelengths?
Currently, I am looking into using a spectral sensor from SparkFun in order to obtain spectroscopic data to feed into a trained neural network, however this sensor gives intensities based on inputs ...
- 53
1
vote
1
answer
272
views
QM9 atomization energies
I am doing experiments with the QM9 dataset from
http://quantum-machine.org/datasets/
and began with some simple checks on results from the literature. Consistent with what the authors of the paper
...
- 461
2
votes
1
answer
67
views
Encoding molecule bond information in matrix form
I have the following problem: I have a pentacene molecule and would like to encode its bond information into a matrix form, to feed it later on to a Machine Learning (ML) algorithm (a Graph Neural ...
- 61
1
vote
0
answers
182
views
SMILES vs. Graph for generating molecules
I have seen this question, but mine is slightly different, focusing on generating molecules.
There are many published methods for generating molecules; some of which generate SMILES and others ...
- 111
0
votes
0
answers
72
views
Machine learning-based drug design: how to determine the desired properties given a target?
I am working on a machine learning-based drug design project. The machine learning part was easily understood for me being from a computer science background. However, the biochemistry part is what I ...
- 319
3
votes
1
answer
256
views
What are the physicochemical properties related to medical drugs in the PubChem database?
I am not a chemist, in fact, I come from a computer science background. However, I am involved in a project related to artificial intelligence-based drug discovery. For this, I am trying to make a ...
- 319
1
vote
0
answers
112
views
Where to find the ChEMBL21 database in CSV format?
I come from an artificial intelligence (AI) background (and not from chemistry).
However, my Ph.D. thesis is about Deep Reinforcement Learning for drug design.
From one of the most famous papers in ...
- 319
5
votes
0
answers
241
views
Who named the QM7 and QM9 datasets?
On the surface, this looks like a silly question, but I honestly can't find an answer for it.
Here's what I've found:
The dataset was introduced in Ramakrishnan R., Dral P. et al., “Quantum chemistry ...
- 51
1
vote
0
answers
126
views
Are molecular properties robust towards manipulations? [closed]
Machine learning algorithms analyze molecules by looking at their molecular representations (e. g. SMILES and graph) and turning them into feature maps that help the algorithm to distinguish them. In ...
- 1,503
2
votes
0
answers
205
views
The Use of AI and Machine Learning in Organic Chemistry
I am trying to do a bit of research into the current use of machine learning in chemical industry. I've been told my original question was too general so I'll try to be more specific about what I'm ...
- 225
2
votes
0
answers
41
views
Any large databases of IR Spectra that you are able to download many spectra in bulk [closed]
I am currently working on a machine learning project, in which I need access to many IR spectra, the more the better, in order to build a classifier that will used some unsupervised learning in order ...
- 117
3
votes
1
answer
107
views
Probabilistic molecular graph models
Let a collection of molecular graphs have at most $N$ nodes, $d$ node types (atom type), and $t$ edge types (bond types). A graph from this collection is normally represented by the tuple $(F, E)$ ...
- 1,503
4
votes
0
answers
53
views
Validity of graph-based molecular representation in ML
I was reading about molecular graph based generative models, which attempt to generate new molecules by training on a subset of a molecular dataset, such as QM9. In these works, there are 2 types of ...
- 1,503
2
votes
2
answers
157
views
What are the GDB-13 criteria for "synthetically accessible organic molecules"?
I'm trying to understand the QM datasets (QM7, QM8, QM9), however, in the description of QM7 the data is described as follows:
[The] QM7 dataset, which is a subset of GDB-13 (a database of nearly 1 ...
- 167