iFeatureOmega CLI

https://github.com/superzchen/ifeatureomega-cli
Admin
iFeatureOmega CLI is a Python toolkit for the feature engineering, analysis, and visualization of...
Tokens:1,392
Snippets:17
Trust Score:6.1
Update:2 months ago
Show doc for...
Tokens:
Raw
### Install Dependencies

Source: https://github.com/superzchen/ifeatureomega-cli/blob/main/README.md

Commands to install required libraries using conda.

```sh
$ conda install biopython
$ conda install -c rdkit rdkit
$ conda install -c salilab dssp
$ conda install -c bioconda msms
$ conda install networkx
```

--------------------------------

### Install iFeatureOmega

Source: https://github.com/superzchen/ifeatureomega-cli/blob/main/README.md

Commands to install the GUI or CLI version of iFeatureOmega via pip3.

```sh
# GUI version
pip3 install iFeatureOmegaGUI

# CLI version
pip3 install iFeatureOmegaCLI
```

--------------------------------

### Run iFeatureOmega GUI

Source: https://github.com/superzchen/ifeatureomega-cli/blob/main/README.md

Commands to launch the iFeatureOmega GUI.

```sh
# GUI version
$ python
>>> from iFeatureOmegaGUI import runiFeatureOmegaGUI
>>> runiFeatureOmegaGUI()
```

--------------------------------

### Run iFeatureOmega CLI

Source: https://github.com/superzchen/ifeatureomega-cli/blob/main/README.md

Commands to perform DNA sequence analysis using the iFeatureOmega CLI.

```sh
# CLI version
$ python
>>> import iFeatureOmegaCLI
>>> dna = iFeatureOmegaCLI.iDNA('<abs_path>/data_examples/DNA_sequences.txt')
>>> dna.display_feature_types()
>>> dna.import_parameters('<abs_path>/parameters/DNA_parameters_setting.json')
>>> dna.get_descriptor("Kmer")
>>> print(dna.encodings)
>>> dna.to_csv("Kmer.csv", "index=False", header=False)
```

--------------------------------

### Download Anaconda

Source: https://github.com/superzchen/ifeatureomega-cli/blob/main/README.md

Download link for the Anaconda platform.

```sh
Download anaconda from:https://repo.anaconda.com/archive/ (Version: 2020.02)
```

--------------------------------

### Initialize iAnalysis with data

Source: https://github.com/superzchen/ifeatureomega-cli/blob/main/README.md

Load a CSV file into a pandas DataFrame and initialize the iAnalysis class instance.

```sh
$ python
>>> import iFeatureOmegaCLI
>>> import pandas as pd
>>> df = pd.read_csv('<abs_path>/data_examples/data_without_labels.csv', sep=',', header=None, index_col=None)
```

```sh
>>> data = iFeatureOmegaCLI.iAnalysis(df)
```

--------------------------------

### View iAnalysis documentation

Source: https://github.com/superzchen/ifeatureomega-cli/blob/main/README.md

Access the docstring for the iAnalysis class to understand its functionality.

```sh
$ python
>>> import iFeatureOmegaCLI
>>> print(iFeatureOmegaCLI.iAnalysis.__doc__)
```

--------------------------------

### Perform feature analysis and processing

Source: https://github.com/superzchen/ifeatureomega-cli/blob/main/README.md

Execute clustering, dimensionality reduction, and normalization algorithms, then save the results to CSV files.

```sh
>>> data.kmeans(nclusters=3)            # k-means clustering
>>> data.MiniBatchKMeans(nclusters=2)   # Mini-Batch K-means
>>> data.GM()                           # Gaussian mixture
>>> data.Agglomerative()                # Agglomerative
>>> data.Spectral()                     # Spectral
>>> data.MCL()                          # Markov clustering
>>> data.hcluster()                     # Hierarchical clustering
>>> data.APC()                          # Affinity propagation clustering 
>>> data.meanshift()                    # Mean shift
>>> data.DBSCAN()                       # DBSCAN

# save cluster result
>>> data.cluster_to_csv(file="cluster_result.csv")

# dimensionality reduction
>>> data.t_sne(n_components=2)          # t-distributed stochastic neighbor embedding
>>> data.PCA(n_components=2)            # Principal component analysis
>>> data.LDA(n_components=2)            # Latent dirichlet allocation

# save dimensionality reduction result
>>> data.dimension_to_csv(file="dimension_reduction_result.csv")

# feature normalization
>>> data.ZScore()                       # ZScore
>>> data.MinMax()                       # MinMax

# save feature normalization result
>>> data.normalization_to_csv(file="feature_normalization_result.csv")
```
Tokens:
Raw