• NCBI sequence processing for gene bank sequences
• RADAR sensor optimization and codon editing
• Plasmid-ready output for synthetic biology applications

def main():
    # Input DNA sequence below
    dna = ""  # the sequence you want to be made into a sensor seq

    dna = clean_sequence(dna)
    codons = to_codons(dna)
    sequence = make_sequence(codons)
    print("Spaced sequence:", sequence)

    reverse = reverse_sequence(sequence)
    print("Reversed:", reverse)

    complement = reverse_complement(reverse)
    print("Reverse complement:", complement)

    edited_sequence = sequence_edit(complement)
    print("Edited sequence:", edited_sequence)

def clean_sequence(seq):
    """Remove non-alphabetic characters from DNA sequence"""
    cleaned = ""
    for char in seq:
        if char.isalpha():
            cleaned += char
    return cleaned

def to_codons(seq):
    """Convert DNA sequence to codon triplets"""
    codons = []

    remainder = len(seq) % 3
    print(f"{remainder} letters were excluded from your sequence.")
    length = len(seq) - remainder

    i = 0
    while i + 2 < length:
        codon = seq[i] + seq[i+1] + seq[i+2]
        codons.append(codon)
        i = i + 3
    return codons

def make_sequence(codons):
    """Create spaced sequence from codon list"""
    spaced_sequence = codons[0]
    for i in range(1, len(codons)):
        spaced_sequence = spaced_sequence + " " + codons[i]
    return spaced_sequence

def reverse_sequence(sequence):
    """Reverse the DNA sequence"""
    reverse = ""
    for i in range(len(sequence) - 1, -1, -1):  # start at last index, go to 0
        reverse += sequence[i]
    return reverse

def reverse_complement(reverse):
    """Generate reverse complement of DNA sequence"""
    complement = ""
    for char in reverse:
        if char.lower() == "a":
            complement += "t"
        elif char.lower() == "t":
            complement += "a"
        elif char.lower() == "c":
            complement += "g"
        elif char.lower() == "g":
            complement += "c"
        else:
            complement += char
    return complement

def sequence_edit(complement):
    """Edit sequence to optimize for sensor applications"""
    current_sequence = complement.split(" ")
    new_sequence = current_sequence[:]
    tgg_indices = [i for i, codon in enumerate(current_sequence) if codon.lower() == "tgg"]
    if tgg_indices:
        middle_index = tgg_indices[len(tgg_indices) // 2]
        new_sequence[middle_index] = "uag"
    for i in range(len(new_sequence)):
        codon = new_sequence[i].lower()
        if not (tgg_indices and i == middle_index):
            if codon == "taa":
                new_sequence[i] = "gaa"
            elif codon == "tag":
                new_sequence[i] = "gag"
            elif codon == "tga":
                new_sequence[i] = "gga"
            elif codon == "atg":
                new_sequence[i] = "agg"
            else:
                new_sequence[i] = codon
    edited_sequence = make_sequence(new_sequence)
    return edited_sequence

main()

• Statistical analysis with t-tests on replicate datasets
• Annotated plotting for publication-ready visualizations
• Fold change calculation and standardized gating

# -*- coding: utf-8 -*-
"""RADARoutput_plotting_template.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1lti9eKx7lz_DEt0c3L70LSz1aiHnVvHw
"""

#### IMPORT NECESSARY PYTHON PACKAGES ###

!pip install statannotations

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
from IPython.display import display
from statannotations.Annotator import Annotator

"""**Now we need to upload the data file into the colab. Run the code below and then upload the csv file with your data**"""

from google.colab import files

# Upload a file from local computer
uploaded = files.upload()

data = pd.read_csv('sample raw data for plotting - Sheet1.csv')


# print out data to see what we are working with

data.head()

# Calculate the average of the three 'normalized GFP output' columns and create a new column 'Average GFP Output'
data['Average GFP Output'] = data[['normalized GFP output', 'normalized GFP output.1', 'normalized GFP output.2']].mean(axis=1)

# Reshape the data for plotting
data_melted = data.melt(id_vars=['Unnamed: 0'], value_vars=['normalized GFP output', 'normalized GFP output.1', 'normalized GFP output.2'], var_name='Replicate', value_name='GFP Output')

# Create the figure and axes
fig, ax = plt.subplots(figsize=(5, 5))

# Create the swarm plot
sns.swarmplot(x='Unnamed: 0', y='GFP Output', data=data_melted, ax=ax, color='gray')

# Add markers for the average GFP output
sns.pointplot(x='Unnamed: 0', y='Average GFP Output', data=data, ax=ax, color='black', linestyles='', marker='_', markersize=20, markeredgewidth=3)


# Set labels and title
ax.set_xlabel('Sample')
ax.set_ylabel('GFP Output (normalized to background)')

# Rotate x-axis labels for better readability
plt.xticks(rotation=90, ha='right')

# Display the plot
plt.tight_layout()
plt.show()

"""# Task
Create a new column in the dataframe `data` that is the average of columns 2, 3, and 4. Generate a swarm plot using columns 2, 3, and 4, with each replicate plotted across the row. Add a bold dash marker representing the average of the three replicates for each row. Create a second plot using the same data, perform independent t-tests comparing the first and second samples, and the third and fourth samples. Display the statistical test results as stars on the second plot and print the p-values for these comparisons.
"""

# Reshape the data for plotting
data_melted = data.melt(id_vars=['Unnamed: 0'], value_vars=['normalized GFP output', 'normalized GFP output.1', 'normalized GFP output.2'], var_name='Replicate', value_name='GFP Output')

# Confirm the structure of the melted DataFrame by displaying its head
display(data_melted.head())

# Create the figure and axes
fig, ax = plt.subplots(figsize=(5, 5))

# Create the swarm plot
sns.swarmplot(x='Unnamed: 0', y='GFP Output', data=data_melted, ax=ax, color='gray')

# Add markers for the average GFP output
sns.pointplot(x='Unnamed: 0', y='Average GFP Output', data=data, ax=ax, color='black', linestyles='', marker='_', markersize=20, markeredgewidth=3)

# Set labels and title
ax.set_xlabel('Sample')
ax.set_ylabel('GFP Output (normalized to background)')

# Rotate x-axis labels for better readability
plt.xticks(rotation=90, ha='right')

# Adjust layout
plt.tight_layout()

# Display the plot
plt.show()

"""## Define pairs for statistical testing

### Subtask:
Specify the pairs of samples to be compared using independent t-tests.

**Reasoning**:
Create a list of tuples specifying the pairs of samples for independent t-tests based on the 'Unnamed: 0' column in the `data` DataFrame.
"""

# Get the sample names from the 'Unnamed: 0' column
sample_names = data['Unnamed: 0'].tolist()

# Specify the pairs for comparison
pairs = [(sample_names[0], sample_names[1]), (sample_names[2], sample_names[3])]

# Print the pairs to verify
print(pairs)

"""## Add statistical annotations to the plot

### Subtask:
Use `statannotations` to add significance stars to the specified pairs on the plot.

**Reasoning**:
Create an Annotator object, set the statistical test, and apply the annotations to the plot.
"""

# Create an Annotator object
annotator = Annotator(ax, pairs, data=data_melted, x='Unnamed: 0', y='GFP Output')

# Configure the statistical test
annotator.configure(test='t-test_ind', text_format='star', loc='outside')

# Run the test and add annotations
annotator.apply_and_annotate()

# Display the plot with annotations
fig

"""## Perform statistical tests and print p-values

### Subtask:
Manually perform independent t-tests for the specified pairs and print the resulting p-values.

**Reasoning**:
Perform independent t-tests for the specified pairs and print the resulting p-values.
"""

from scipy.stats import ttest_ind

# Filter data for the first pair (complete match -trigger vs complete match +trigger)
complete_match_minus_trigger = data_melted[data_melted['Unnamed: 0'] == 'complete match -trigger']['GFP Output']
complete_match_plus_trigger = data_melted[data_melted['Unnamed: 0'] == 'complete match +trigger']['GFP Output']

# Perform independent t-test for the first pair
ttest_complete = ttest_ind(complete_match_minus_trigger, complete_match_plus_trigger)

# Print the p-value for the first pair
print(f"P-value for 'complete match -trigger' vs 'complete match +trigger': {ttest_complete.pvalue}")

# Filter data for the second pair (partial match -trigger vs partial match +trigger)
partial_match_minus_trigger = data_melted[data_melted['Unnamed: 0'] == 'partial match -trigger']['GFP Output']
partial_match_plus_trigger = data_melted[data_melted['Unnamed: 0'] == 'partial match +trigger']['GFP Output']

# Perform independent t-test for the second pair
ttest_partial = ttest_ind(partial_match_minus_trigger, partial_match_plus_trigger)

# Print the p-value for the second pair
print(f"P-value for 'partial match -trigger' vs 'partial match +trigger': {ttest_partial.pvalue}")

"""## Summary:

### Data Analysis Key Findings

*   The average GFP output for each sample was calculated and added as a new column (`Average GFP Output`) to the `data` DataFrame.
*   A swarm plot was successfully generated displaying individual data points and the average GFP output for each sample, with replicate data plotted across rows.
*   Independent t-tests were performed comparing 'complete match -trigger' with 'complete match +trigger' and 'partial match -trigger' with 'partial match +trigger'.
*   The p-value for the comparison between 'complete match -trigger' and 'complete match +trigger' was approximately 0.0174.
*   The p-value for the comparison between 'partial match -trigger' and 'partial match +trigger' was approximately 0.0185.
*   Significance stars based on the t-test results were successfully added to the plot.

### Insights or Next Steps

*   Both comparisons showed statistically significant differences in GFP output (p < 0.05), suggesting that the "+trigger" condition has a significant impact on GFP expression for both complete and partial matches.
*   Further investigation into the magnitude of the GFP output change and potential biological implications of the observed differences between complete and partial matches under the "+trigger" condition could be valuable.

"""