Deep Learning

Fighting Coronavirus COVID-19 with Data Science & Crowdsourcing: 3 Projects You Should Know About

March 6, 2020
8 min read
home-banner.jpg

The Coronavirus is here. As we see the level of cases increasing, medical facilities ramping up preparedness, travel restrictions implemented, supply chains being disrupted, and preparing for other worst-case scenarios, the next question is how can we as community combat and understand this virus? While vaccine research has accelerated on a worldwide global effort, there is also another global phenomenon that has emerged, and that is using open data science and crowdsourcing to understand and combat the virus. This blog post will focus on a few of these projects that just about anyone can get started on today.

COVID-19 - Analysis, Viz, Prediction & Comparisons (Kaggle)

Perhaps the most comprehensive data analysis and visualization utilizing the Novel Corona Virus 2019 Dataset, this Kaggle notebook that shows a wide array of data science and visualization methods.

Number of COVID-19 Cases Compared Hubei, China, World

Representation of COVID-19 Coronavirus Cases Outside China
Coronavirus Number of Confirmed Cases Outside China

Coronavirus COVID-19 Cases in China

Coronavirus Number of Confirmed Cases Outside China
Data Science PC | Exxact

COVID-19 Coronavirus Recovery and Mortality Rate over Time

Coronavirus Recovery and Mortality Rate Over Time

Libraries used in this Coronavirus (COVID-19) Kernel

# storing and anaysis
import numpy as np
import pandas as pd

# visualization
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import seaborn as sns

from plotnine import *
import calmap

import plotly.express as px
import folium

# color pallette
cdr = ['#393e46', '#ff2e63', '#30e3ca'] # grey - red - blue
idr = ['#f8b400', '#ff2e63', '#30e3ca'] # yellow - red - blue

Coronavirus Spike Protein Binder Design Puzzle Game (fold.it)

Coronaviruses display a "spike" protein on their surface, which binds tightly to a receptor protein found on the surface of human cells. Once the virus spike binds to the human receptor, it can infect the human cell and replicate it. (Check this link for updates to this game!)

COVID-19 Virus

image source: CDC

In this puzzle, players are presented with the binding site of the coronavirus spike protein. The backbone and most of the sidechains are completely frozen, except for sidechains at the binding site, where the spike protein normally interacts with the human receptor protein. Players can design a new protein that binds to these sidechains, blocking interactions with the human receptor. In order to bind the coronavirus target, designs will need to make lots of contacts and H-bonds with the spike protein at this binding site. But designs will also need to have lots of secondary structure (helices or sheets) and a large core so that they fold up correctly!

GPU Molecular Dynamics

Analysis of Coronavirus Dataset of COVID-19 in South Korea (Kaggle)

COVID-19 has infected more than 5,000 people in South Korea. South Korea currently has the second-highest infection counts in the world. KCDC (Korea Centers for Disease Control & Prevention) announces the information of COVID-19 quickly and transparently.

Source of data: KCDC (Korea Centers for Disease Control & Prevention)

Coronavirus COVID-19 Reason for Infection in South Korea

Infection Reason | Coronavirus Korea Analysis

South Korea Coronavirus Affected Regions Map Visualization

Libraries Used for this Analysis

import numpy as np
import pandas as pd 
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from datetime import date, timedelta
from sklearn.cluster import KMeans

Guidelines for Coronavirus Prevention & Treatment (CDC)

This is from the CDC, if you're outside the United States, check with your local or regional governments for additional guidance. There is currently no vaccine to prevent coronavirus disease in 2019 (COVID-19). The best way to prevent illness is to avoid being exposed to this virus. However, as a reminder, the CDC always recommends everyday preventive actions to help prevent the spread of respiratory diseases, including:

  • Avoid close contact with people who are sick.
  • Avoid touching your eyes, nose, and mouth.
  • Stay home when you are sick.
  • Cover your cough or sneeze with a tissue, then throw the tissue in the trash.
  • Clean and disinfect frequently touched objects and surfaces using a regular household cleaning spray or wipe.
  • Follow CDC’s recommendations for using a facemask.
    • CDC does not recommend that people who are well wearing a facemask to protect themselves from respiratory diseases, including COVID-19.
    • Facemasks should be used by people who show symptoms of COVID-19 to help prevent the spread of the disease to others. The use of facemasks is also crucial for health workers and people who are taking care of someone in close settings (at home or in a health care facility).
  • Wash your hands often with soap and water for at least 20 seconds, especially after going to the bathroom; before eating; and after blowing your nose, coughing, or sneezing.
    • If soap and water are not readily available, use an alcohol-based hand sanitizer with at least 60% alcohol. Always wash hands with soap and water if hands are visibly dirty.

For information about handwashing, see CDC’s Handwashing website

For information specific to healthcare, see CDC’s Hand Hygiene in Healthcare Settings

These are everyday habits that can help prevent the spread of several viruses. CDC does have specific guidance for travelers.

ebook deep learning 2020

home-banner.jpg
Deep Learning

Fighting Coronavirus COVID-19 with Data Science & Crowdsourcing: 3 Projects You Should Know About

March 6, 20208 min read

The Coronavirus is here. As we see the level of cases increasing, medical facilities ramping up preparedness, travel restrictions implemented, supply chains being disrupted, and preparing for other worst-case scenarios, the next question is how can we as community combat and understand this virus? While vaccine research has accelerated on a worldwide global effort, there is also another global phenomenon that has emerged, and that is using open data science and crowdsourcing to understand and combat the virus. This blog post will focus on a few of these projects that just about anyone can get started on today.

COVID-19 - Analysis, Viz, Prediction & Comparisons (Kaggle)

Perhaps the most comprehensive data analysis and visualization utilizing the Novel Corona Virus 2019 Dataset, this Kaggle notebook that shows a wide array of data science and visualization methods.

Number of COVID-19 Cases Compared Hubei, China, World

Representation of COVID-19 Coronavirus Cases Outside China
Coronavirus Number of Confirmed Cases Outside China

Coronavirus COVID-19 Cases in China

Coronavirus Number of Confirmed Cases Outside China
Data Science PC | Exxact

COVID-19 Coronavirus Recovery and Mortality Rate over Time

Coronavirus Recovery and Mortality Rate Over Time

Libraries used in this Coronavirus (COVID-19) Kernel

# storing and anaysis
import numpy as np
import pandas as pd

# visualization
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import seaborn as sns

from plotnine import *
import calmap

import plotly.express as px
import folium

# color pallette
cdr = ['#393e46', '#ff2e63', '#30e3ca'] # grey - red - blue
idr = ['#f8b400', '#ff2e63', '#30e3ca'] # yellow - red - blue

Coronavirus Spike Protein Binder Design Puzzle Game (fold.it)

Coronaviruses display a "spike" protein on their surface, which binds tightly to a receptor protein found on the surface of human cells. Once the virus spike binds to the human receptor, it can infect the human cell and replicate it. (Check this link for updates to this game!)

COVID-19 Virus

image source: CDC

In this puzzle, players are presented with the binding site of the coronavirus spike protein. The backbone and most of the sidechains are completely frozen, except for sidechains at the binding site, where the spike protein normally interacts with the human receptor protein. Players can design a new protein that binds to these sidechains, blocking interactions with the human receptor. In order to bind the coronavirus target, designs will need to make lots of contacts and H-bonds with the spike protein at this binding site. But designs will also need to have lots of secondary structure (helices or sheets) and a large core so that they fold up correctly!

GPU Molecular Dynamics

Analysis of Coronavirus Dataset of COVID-19 in South Korea (Kaggle)

COVID-19 has infected more than 5,000 people in South Korea. South Korea currently has the second-highest infection counts in the world. KCDC (Korea Centers for Disease Control & Prevention) announces the information of COVID-19 quickly and transparently.

Source of data: KCDC (Korea Centers for Disease Control & Prevention)

Coronavirus COVID-19 Reason for Infection in South Korea

Infection Reason | Coronavirus Korea Analysis

South Korea Coronavirus Affected Regions Map Visualization

Libraries Used for this Analysis

import numpy as np
import pandas as pd 
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from datetime import date, timedelta
from sklearn.cluster import KMeans

Guidelines for Coronavirus Prevention & Treatment (CDC)

This is from the CDC, if you're outside the United States, check with your local or regional governments for additional guidance. There is currently no vaccine to prevent coronavirus disease in 2019 (COVID-19). The best way to prevent illness is to avoid being exposed to this virus. However, as a reminder, the CDC always recommends everyday preventive actions to help prevent the spread of respiratory diseases, including:

  • Avoid close contact with people who are sick.
  • Avoid touching your eyes, nose, and mouth.
  • Stay home when you are sick.
  • Cover your cough or sneeze with a tissue, then throw the tissue in the trash.
  • Clean and disinfect frequently touched objects and surfaces using a regular household cleaning spray or wipe.
  • Follow CDC’s recommendations for using a facemask.
    • CDC does not recommend that people who are well wearing a facemask to protect themselves from respiratory diseases, including COVID-19.
    • Facemasks should be used by people who show symptoms of COVID-19 to help prevent the spread of the disease to others. The use of facemasks is also crucial for health workers and people who are taking care of someone in close settings (at home or in a health care facility).
  • Wash your hands often with soap and water for at least 20 seconds, especially after going to the bathroom; before eating; and after blowing your nose, coughing, or sneezing.
    • If soap and water are not readily available, use an alcohol-based hand sanitizer with at least 60% alcohol. Always wash hands with soap and water if hands are visibly dirty.

For information about handwashing, see CDC’s Handwashing website

For information specific to healthcare, see CDC’s Hand Hygiene in Healthcare Settings

These are everyday habits that can help prevent the spread of several viruses. CDC does have specific guidance for travelers.

ebook deep learning 2020