Skill up with AI and learn from visionaries Andrew Ng and Jared Kaplan on June 26.

SNOWFLAKE CERTIFIED

Build a Bioinformatics Solubility Dashboard

By: Chanin Nantasenemat

Published: Jun. 12, 2025

import streamlit as st

st.title('☘️ Solubility Dashboard')

# Data Filtering
mol_size = st.slider('Select a value', 100, 500, 300)
df['MOLWT_CLASS'] = pd.Series(['small' if x < mol_size else 'large' for x in df['MOLWT']])
df_class = df.groupby('MOLWT_CLASS').mean().reset_index()

st.divider()

# Calculate Metrics
molwt_large = round(df_class['MOLWT'][0], 2)
molwt_small = round(df_class['MOLWT'][1], 2)
numrotatablebonds_large = round(df_class['NUMROTATABLEBONDS'][0], 2)
numrotatablebonds_small = round(df_class['NUMROTATABLEBONDS'][1], 2)

import streamlit as st

st.title('☘️ Solubility Dashboard')

# Data Filtering
mol_size = st.slider('Select a value', 100, 500, 300)
df['MOLWT_CLASS'] = pd.Series(['small' if x < mol_size else 'large' for x in df['MOLWT']])
df_class = df.groupby('MOLWT_CLASS').mean().reset_index()

st.divider()

# Calculate Metrics
molwt_large = round(df_class['MOLWT'][0], 2)
molwt_small = round(df_class['MOLWT'][1], 2)
numrotatablebonds_large = round(df_class['NUMROTATABLEBONDS'][0], 2)
numrotatablebonds_small = round(df_class['NUMROTATABLEBONDS'][1], 2)

import streamlit as st

st.title('☘️ Solubility Dashboard')

# Data Filtering
mol_size = st.slider('Select a value', 100, 500, 300)
df['MOLWT_CLASS'] = pd.Series(['small' if x < mol_size else 'large' for x in df['MOLWT']])
df_class = df.groupby('MOLWT_CLASS').mean().reset_index()

st.divider()

# Calculate Metrics
molwt_large = round(df_class['MOLWT'][0], 2)
molwt_small = round(df_class['MOLWT'][1], 2)
numrotatablebonds_large = round(df_class['NUMROTATABLEBONDS'][0], 2)
numrotatablebonds_small = round(df_class['NUMROTATABLEBONDS'][1], 2)

import streamlit as st

st.title('☘️ Solubility Dashboard')

# Data Filtering
mol_size = st.slider('Select a value', 100, 500, 300)
df['MOLWT_CLASS'] = pd.Series(['small' if x < mol_size else 'large' for x in df['MOLWT']])
df_class = df.groupby('MOLWT_CLASS').mean().reset_index()

st.divider()

# Calculate Metrics
molwt_large = round(df_class['MOLWT'][0], 2)
molwt_small = round(df_class['MOLWT'][1], 2)
numrotatablebonds_large = round(df_class['NUMROTATABLEBONDS'][0], 2)
numrotatablebonds_small = round(df_class['NUMROTATABLEBONDS'][1], 2)

import streamlit as st

st.title('☘️ Solubility Dashboard')

# Data Filtering
mol_size = st.slider('Select a value', 100, 500, 300)
df['MOLWT_CLASS'] = pd.Series(['small' if x < mol_size else 'large' for x in df['MOLWT']])
df_class = df.groupby('MOLWT_CLASS').mean().reset_index()

st.divider()

# Calculate Metrics
molwt_large = round(df_class['MOLWT'][0], 2)
molwt_small = round(df_class['MOLWT'][1], 2)
numrotatablebonds_large = round(df_class['NUMROTATABLEBONDS'][0], 2)
numrotatablebonds_small = round(df_class['NUMROTATABLEBONDS'][1], 2)

import streamlit as st

st.title('☘️ Solubility Dashboard')

# Data Filtering
mol_size = st.slider('Select a value', 100, 500, 300)
df['MOLWT_CLASS'] = pd.Series(['small' if x < mol_size else 'large' for x in df['MOLWT']])
df_class = df.groupby('MOLWT_CLASS').mean().reset_index()

st.divider()

# Calculate Metrics
molwt_large = round(df_class['MOLWT'][0], 2)
molwt_small = round(df_class['MOLWT'][1], 2)
numrotatablebonds_large = round(df_class['NUMROTATABLEBONDS'][0], 2)
numrotatablebonds_small = round(df_class['NUMROTATABLEBONDS'][1], 2)

import streamlit as st

st.title('☘️ Solubility Dashboard')

# Data Filtering
mol_size = st.slider('Select a value', 100, 500, 300)
df['MOLWT_CLASS'] = pd.Series(['small' if x < mol_size else 'large' for x in df['MOLWT']])
df_class = df.groupby('MOLWT_CLASS').mean().reset_index()

st.divider()

# Calculate Metrics
molwt_large = round(df_class['MOLWT'][0], 2)
molwt_small = round(df_class['MOLWT'][1], 2)
numrotatablebonds_large = round(df_class['NUMROTATABLEBONDS'][0], 2)
numrotatablebonds_small = round(df_class['NUMROTATABLEBONDS'][1], 2)

watch the demo

All Solutions

Overview

Using Snowflake, Python, and Streamlit, you can create an interactive tool that helps visualize and understand the relationships between molecular weight, rotatable bonds, LogP values, and aromatic proportions - all key factors in determining a molecule's solubility and potential as a drug candidate.

Build an interactive dashboard that visualizes important molecular properties and their relationship to solubility, providing valuable insights for pharmaceutical research.

Overview of this bioinformatics project

Build a Bioinformatics Solubility Dashboard DIAGRAM

An interactive bioinformatics dashboard that visualizes molecular properties from the Delaney solubility dataset, allowing researchers to explore relationships between molecular weight, rotatable bonds, LogP values, and aromatic proportions.