Skip to main content
8 votes
Accepted

Machine learning using protein-sequences

There are two types of features which can be extracted from protein sequences. It is not possible to known which, if any, of these features would be useful in classification tasks. It may not be ...
Aalawlx's user avatar
  • 517
7 votes
Accepted

Generate ligands candidates based on protein shape

TL;DR: docking is much slower than any ML approach, but the ML approach can be constrained by pharmacophores dictated by the active site. Side note: Scale The scale for ligand space exploration is ...
Matteo Ferla's user avatar
  • 4,234
7 votes

Rule Extraction from nnet results

R's nnet package only supports fully connected neural networks with one hidden layer. This is the most primitive type of network. I doubt it will work well for promotors finding. In addition, such ...
user172818's user avatar
  • 6,535
5 votes

How can I use annotations to remove variants not relevant to cancer risk?

While your question is specific to cancerous germline mutations, I'd suggest you look at the COSMIC database of somatic mutations to include in your analysis. There are other factors to include in ...
A_Skelton73's user avatar
4 votes
Accepted

Rule Extraction from nnet results

Short answer: you can't. Neural networks use positive and negative examples to add weights to the neural network architecture that is provided to it. Trying to deconvolve the meaning behind the ...
ithinkiam's user avatar
  • 356
3 votes

De novo motif discovery in protein sequences

I think MEME is a good tool for your purpose, but there are others as well. I can think of InterProScan for example (although I am not sure if it is really de novo). Here a summary of available tools.
benn's user avatar
  • 3,571
3 votes

How can I use annotations to remove variants not relevant to cancer risk?

I don't think it will be possible to do what you ask, right now with current knowledge. Selecting variants relevant to cancer risk is still an open problem and usually requires quite a lot of human ...
bernatgel's user avatar
  • 166
3 votes

Gene names from components in NMF analysis

NMF of a gene expression matrix into $k$ components works to decompose the expression matrix into an activity matrix ($H$) and latent factor matrix ($W$). $W$ describes the $k$ latent factors (often ...
Tomas Bencomo's user avatar
2 votes

Link Prediction in Bipartite Networks between biological pathways and drugs

I am not sure if I understood correctly how you classify the drugs. But what you attempt to do is similar to what they do here but in that article they use the drugs targeted to a molecule/pathway to ...
llrs's user avatar
  • 4,713
2 votes

Proteins that cannot form biofilm?

One option is to treat all proteins that are not explicitly known to form a biofilm as proteins that are incapable of doing so, but this will likely result in many false negatives. You could take a ...
holmrenser's user avatar
2 votes

Preparing binary matrix data for Scikit classification algorithms

Since you are using R, you probably don't want to use scikit-learn, which is for Python. However, there is a similar R library mlr ("R package to make machine learning in R easy") that provides a ...
burger's user avatar
  • 2,199
2 votes

Recommendation for a binary dataset for Computational Biology open access (as in a dataset with 1 and 0 that can be used to apply ML techniques?

Kaggle has a cats v dogs dataset if you want to try your hand at biological image classification: https://www.kaggle.com/c/dogs-vs-cats The DREAM challenge competitions are usually specifically ...
Jay Moore's user avatar
  • 1,012
2 votes

General framework for fusing biological networks

I believe you're referring to something related to multi-layer networks. Here you can find an interesting reading about this kind of networks: https://academic.oup.com/comnet/article/2/3/203/2841130 ...
gabt's user avatar
  • 348
2 votes

Deep learning RNA sequences

I come from a protein background and this problem is analogous to protein torsion angle prediction, which in turn is a variant of protein secondary structure prediction. Conventional ways to go here ...
jgreener's user avatar
  • 941
2 votes

Deep learning RNA sequences

The question of folding of RNA sequences looks slightly similar to protein folding - perhaps searching in this domain might bring more suggestions. An example of (current) state of the art of deep ...
ellimilial's user avatar
2 votes
Accepted

Why my bim file doesn't match to my ped file as the Plink documentation suggests?

Responded in the plink2-users group (https://groups.google.com/forum/#!topic/plink2-users/zgJxdXxvdLo ).
Christopher Chang's user avatar
2 votes

BERT Language Model and Gene Sequences - How Do I Relate Clusters of Sequences?

The UMAP results look very pretty :) If I were to try to make sense of this blob, I'd try to do the following. Pull out Gene Ontology (GO) terms for a list of candidate genes (you can try to subset ...
mortonjt's user avatar
  • 121
2 votes
Accepted

Integrative analysis of omics studies using machine learning

The steps you describe are correct. For step 2 it is usually normalized to mean 0 and variance 1. However the "machine learning" part is important. Having several samples being technical replicates ...
llrs's user avatar
  • 4,713
2 votes

Any suggestions for cultivar identification using SSR (simple sequence repeat) markers

Use Fst (migration statistic) such as the Fstat program to generate a distance matrix and solve it via clustering, such as UPGMA or neighbor-joining. This analysis is particularly useful for diploids. ...
M__'s user avatar
  • 12.5k
2 votes

Any suggestions for cultivar identification using SSR (simple sequence repeat) markers

Not to discount @Michael's answer (unsupervised learning is very handy for descriptive analysis of this kind of problem), but classification based on microsatellite data should not be too difficult. ...
Maximilian Press's user avatar
2 votes
Accepted

Challenging benchmarks for supervised learning on sparse scRNA-seq data

You could try the PBMC 3k data from the Satija lab: https://satijalab.org/seurat/articles/pbmc3k_tutorial.html For well-annotated data, there's the Single-cell proteo-genomic reference map: https://...
gringer's user avatar
  • 14.3k
2 votes

Reproducible PyTorch Model

There is this nice function from Kaggle: ...
Soerendip's user avatar
  • 1,295
2 votes

De novo antibody sequencing fromMS/MS Ion Trap proteomics raw signal

A few notes on data generation first: There are currently two broad approaches for the generation of bottom-up or "shotgun" MS proteomics: data-dependent acquisition (DDA) and data-...
2 votes

How to identify genomic regions / peaks associated with enhancers (TF binding sites)? Is there a tool or a formal recipe?

If you have reads from chip-seq or atac you can use tools like homer or macs to identify peaks in your data. Once you have the peaks, these programs allow you to do motif discovery to annotate your ...
Niek de Klein's user avatar
2 votes
Accepted

Applying glmnet to identify predictors for subtypes

Final answer. Keep in mind I work in Python so I'm trying to translate here. The output of coef(cv.lassoModel) ... those are your genes of interest thats your ...
M__'s user avatar
  • 12.5k
1 vote

What are the state-of-the-art cell-type RNA-Seq deconvolution methods?

I see a lot of people using xCell. There should also be papers systematically compare many different methods, which might interest you.
Phoenix Mu's user avatar
1 vote

How do I set a neural network to loop multiple times and average the resulting values?

The concern with your approach is called 'leakage' because you are parameterising the same data set that you are training. This can easily lead to overtraining is in ANN (artificial neural networks) ...
M__'s user avatar
  • 12.5k
1 vote

BERT Language Model and Gene Sequences - How Do I Relate Clusters of Sequences?

In truth deep neural networks quite mainstream now, albeit they are a pain because of their reliance on very expensive graphics cards to process the data (GPU) rather than traditional CPU. There are ...
M__'s user avatar
  • 12.5k
1 vote

Feature extraction methods that can handle inconsistent numbers of atoms for molecular dynamics

This answer is no longer on topic. The question is about what is the best machine learning algorithm to use to analyse atomic coordinates from an MD trajectory in order to infer a novel properties. &...
Matteo Ferla's user avatar
  • 4,234
1 vote
Accepted

Use of Electronic Phenotype in EHR

I understand that Phenotype is a set of criteria that you apply on your EHR data to select patients of interest from EHR database. No, a phenotype is a way of behavior or other observed ...
Devon Ryan's user avatar
  • 19.6k

Only top scored, non community-wiki answers of a minimum length are eligible