Inspiration

The average vaccine discovery time takes a minimum 14 months, about 0.5 billion dollar investment, and over 2000 people trying hundreds of formulas to see if it kills the virus. While there are millions of people waiting for a vaccine without knowing how to help.

What it does

We are combining AI and gamification to predict which protein sequences from the new coronavirus are the best candidates for a COVID-19 vaccine. We gathered data from the virus of the SARS 2003 outbreak (also a coronavirus) and turned it into a puzzle game. By playing the game, users are describing new features of experimentally validated vaccine candidates. This information is used in an AI model to predict new vaccine candidates.

Our model is based on state-of-the-art vaccine prediction models to which we are incorporating gamification. By enriching experimentally-validated data through human-based computing (data augmentation), we are increasing the accuracy of vaccine prediction and saving time and reducing costs in pre-clinical trials. By allowing anyone to become a scientist in the process of vaccine discovery, we are helping to fulfill a need for action that is very present right now. Our platform connects researchers in need of human-based data processing with users who contribute as crowd players.

How we built it

In our prototype phase, we’ve turned a research tool (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1479323/) into a puzzle-game. Each solved puzzle is teaching the AI to find a pattern among the amino-acid chemical properties in a protein sequence. Each puzzle is generated from existing protein-based vaccines created for SARS 2003 outbreak, a virus also in the coronavirus family. Therefore, we can use similar formulas to COVID-19. The science behind AnalysisMode

Accomplishments that we're proud of

  • Released a new landing page interface experience, reducing the visitor bounce rate from 73% to 30%. Therefore reducing our marketing costs by -120%. https://www.analysismode.com/
  • Newly published article, on Luxembourg’s business magazine. https://www.siliconluxembourg.lu/analysismode-tool-helps-scientists-discover-the-vaccine-for-coronavirus/
  • A beta game version live
  • Contacted by a journalist from “O Estadao”, a major press in Brazil, with weekly 33M unique visitors.
  • Initiated discussion with Pratica Capital venture capital and two angel investors in Luxembourg.
  • Increased daily unique visitors by 325% from 90 to 383.
  • Marketing campaign reduced Cost per User Acquisition to 0.01$ (landing page view), the campaign had 89 shares ($0.13/share).
  • 81.75% of the users are now visiting the site by phone, as an effect of the UI improvement allowing the puzzle-game to played on smaller screens.
  • Found +15 new supporters for the project - the names will be announced soon on the website.
  • Reached a 25K gameplays from 98 countries
  • Increased retention to 6,28% (average on apple and google stores is 2%)
+ 33 more
Share this project:

Updates

posted an update

Want to play a game and help find a vaccine formula candidate for COVID-19 ?! Our gamified prediction tool can improve the speed of vaccine and drug discovery, while also being environmentally friendly by replacing supercomputers.

We replace supercomputers with superplayers. Faster tools. Faster response. Pandemic ready.

Check our 48 hours progress! :) https://www.analysismode.com/ Please share your feedback.

Log in or sign up for Devpost to join the conversation.

posted an update

Specifically, our goals for the Global Hack are:

[Frontend] Migrate the current puzzle game and landing page in to react. [Frontend] Implement gamification elements: new progress bar, achievements badges, profile page, global ranking per puzzle. [Frontend] Implement a global progress bar. How far are we from the vaccine [Frontend] Create a mobile app version using react-native. [Backend / Game Design] Implement new game logic. Which players will find drawings rather than just vertical 'repetitions'. [Frontend] Implement a scoring algorithm, to give players feedback about their puzzle solutions. [Game UI] Create a game character. A character to explain the game and grow with the player. -- We need a storyline for this. [Game UI] Add soundtrack and effect to the game, to increase engagement. [UI] Create a design system and a new color scheme. [UI] Create new game symbols and colors. The new game version will have larger puzzle grids. [Data Science] Generate puzzle levels from negative epitopes. [Data Science] Create a puzzle solver algorithm, we will use this to benchmark against human players. [Content] Create a press release and instructions/explanations about the new game version [Marketing] Create content to market the launching of this new version. [Marketing] Support our posting schedules on our Facebook, Twitter, LinkedIn [Marketing] Compile FAQs from users, and reply to their comments. [Marketing] Define social media strategy for each channel. 1) Which ones need more content and which kind; 2) Which has better audience reach and should have greater focus; 3) grow our network in each channel [Marketing] Create social media groups to join our superfans together

Log in or sign up for Devpost to join the conversation.

posted an update

The objectives that we had before the hack. So how much we managed to achieve? Most of them! Some of the tasks like game design are ready and will be implemented this week.

DONE [Business] Research how much laboratories and pharmaceuticals would pay for a vaccine formula. List possible buyers. DONE[Business] Reach mentors working on Universities to know: which COVID projects are currently being done; how many students have interest in health science projects; if possible to create a community group with students to enable discussion/testing of AnalysisMode; if possible to contact students to write a term paper or case-study about AnalysisMode. DONE [Business] Prepare pitch deck containing the problem size, our solution, the value proposition, go-to-market strategy, and progress so far. In Progress [Business] Prepare a list of VCs and Angels (angelList) interested in COVID-19 projects and biotech. DONE[Business] Reach mentors for PR / marketing advice. Find good connections to lead to press coverage. DONE[Marketing] Make a strategy plan to find our marketing audience. DONE[Marketing] Create marketing campaigns on Facebook/others. In Progress [Marketing] Create community groups on Facebook, find other related communities to post and invite people to join. (Guerrilla marketing) DONE[Content] Create marketing content to be advertised on social platforms. DONE[Content] Organize the creation of video content or animation explaining the AnalysisMode tool. DONE[Content] Create charts explaining the size of the vaccine discovery problem: how long it takes; length of clinical trials; problems with side-effects; In Slides. DONE[Bioinformatics] Write an explanation of our scientific explanation, which algorithms are being used to predict the vaccine, and how much training the AI needs. DONE[Bioinformatics] Compile a list of universities with active research in epitope prediction (protein-based vaccine). Also, compile a list of recently published articles. DONE[Bioinformatics] Get data of played games to create a Hidden Markov Model or frequency matrix or state machine with the probabilities of a vaccine formula. DONE And EVEN MORE![Game design] Review the game difficulty, suggestions for changing the game logic to increase difficulty while teaching the AI faster And EVEN MORE! DONE[Data Analysis] Calculate how many possible ways of creating different puzzle combinations. In Progress[Data Analysis] Calculate how long would take a computer to solve one puzzle game. In Progress[Development] Implement a new game UI, as the current one has confusing UX and doesn’t fit in a tablet screen. In Progress[Development] Add social elements to increase the social presence of the project.

Log in or sign up for Devpost to join the conversation.

posted an update

I reviewed the existing Game and began to enhance the concept, as well in lights of Mobile Gaming, to leverage as well as people all over the work, especially Asia and Africa (in these areas, people use mostly phones for their private matters). Games like AnalysisMode are usually played while commuting or at home (which at the moment would as well benefit the people who are in quarantine --> they can contribute to the research, do something with purpose). I try to integrate already a mobile-first approach into the game strategy and concept. I will start to identify possible narratives, to develop the gameplay even further.

Log in or sign up for Devpost to join the conversation.

posted an update

Hey everyone! Great job! This is an update of our today’s work. :muscle:

Add if I missed something!

We created a story board for a video explanation. Created ML model strategy Created a marketing strategy and initiated 5 marketing campaigns in 4 different channels. Prepared first drafts of the written pitch. Prepared scientific explanation and mini dictionary for the website. New UI for the game Created a gamification strategy with the mentor. Defined value proposition and list of potential partners. Doing a research about establishing a company or an NGO, looking for legal help. Wrote a prospect list of active universities with active research on COVID-19

Log in or sign up for Devpost to join the conversation.

posted an update

Meet the team:

Tiago Sampaio: AI developer, startup founder, former immunology & vaccine researcher, having developed vaccines for parasites using the protein-based vaccine (epitopes) method. Milda Dapkeviciute: startup founder, graduated in business and tourism. Skilled in public speaking and coaching. Arnold Mauragas: startup founder, IT professional, graduated in business management and marketing. Skilled in project management and strategic planning. @Carmen Moreno Data science and marketing, can create explanations about the game. @Ayana de Brito biologist with experience in data science, also content writing and digital marketing @Antonia Bioinformatics BSc. @Nina Wiedemann ML, data science and have some basic bioinformatics knowledge. @Jannis Born Mentor. PhD student in Computational Systems Biology @ ETH & IBM in Zürich. Expertise in data science, deep learning & machine learning, especially when applied to biomolecular data.

Let's have fun and make history! We will solve the COVID-19 crisis together! :smile:

Log in or sign up for Devpost to join the conversation.

posted an update

Hackathon objectives/tasks:

  1. [Business] Research how much laboratories and pharmaceuticals would pay for a vaccine formula. List possible buyers.
  2. [Business] Reach mentors working on Universities to know: which COVID projects are currently being done; how many students have interest in health science projects; if possible to create a community group with students to enable discussion/testing of AnalysisMode; if possible to contact students to write a term paper or case-study about AnalysisMode.
  3. [Business] Prepare pitch deck containing the problem size, our solution, the value-proposition, go-to-market strategy, and progress so far.
  4. [Business] Prepare a list of VCs and Angels (angelList) interested in COVID-19 projects and biotech.
  5. [Business] Reach mentors for PR / marketing advice. Find good connections to lead to press coverage.
  6. [Marketing] Make a strategy plan to find our marketing audience.
  7. [Marketing] Create marketing campaigns on Facebook/others.
  8. [Marketing] Create community groups on Facebook, find other related communities to post and invite people to join. (Guerrilla marketing)
  9. [Content] Create marketing content to be advertised on social platforms.
  10. [Content] Organize the creation of video content or animation explaining the AnalysisMode tool.
  11. [Content] Create charts explaining the size of the vaccine discovery problem: how long it takes; length of clinical trials; problems with side-effects;
  12. [Bioinformatics] Write an explanation of our scientific explanation, which algorithms are being used to predict the vaccine, and how much training the AI needs.
  13. [Bioinformatics] Compile a list of universities with active research in epitope prediction (protein-based vaccine). Also, compile a list of recently published articles.
  14. [Bioinformatics] Get data of played games to create a Hidden Markov Model or frequency matrix or state machine with the probabilities of a vaccine formula.
  15. [Game design] Review the game difficulty, suggestions for changing the game logic to increase difficulty while teaching the AI faster.
  16. [Data Analysis] Calculate how many possible ways of creating different puzzle combinations.
  17. [Data Analysis] Calculate how long would take a computer to solve one puzzle game.
  18. [Development] Implement a new game UI, as the current one has confusing UX and doesn’t fit in a tablet screen.
  19. [Development] Add social elements to increase the social presence of the project.

Log in or sign up for Devpost to join the conversation.

posted an update

Welcome message

Hi everyone, welcome to the team!!

As you know our goal is to speed-up the vaccine discovery by enabling people without the scientific knowledge to contribute to research.

In our prototype phase, we’ve turned a research tool (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1479323/) into a puzzle-game. Each solved puzzle is teaching the AI to find a pattern among the amino-acid chemical properties in a protein sequence. Each puzzle is generated from existing protein-based vaccines created for SARS 2003 outbreak, a virus also in the coronavirus family. Therefore, we’re can use similar formulas to COVID-19.

Here’s what we’ve accomplished :)

  • Released a new landing page interface experience, reducing the visitor bounce rate from 73% to 30%. Therefore reducing our marketing costs by -120%. https://www.analysismode.com/
  • Newly published article, on Luxembourg’s business magazine. https://www.siliconluxembourg.lu/analysismode-tool-helps-scientists-discover-the-vaccine-for-coronavirus/
  • A scheduled interview with Luxembourg Journal (journal.lu).
  • Contacted by a journalist from “O Estadao”, a major press in Brazil, with weekly 33M unique visitors.
  • Initiated discussion with Pratica Capital venture capital and two angel investors in Luxembourg.
  • Increased daily unique visitors by 325% from 90 to 383.
  • Marketing campaign reduced Cost per User Acquisition to 0.01$ (landing page view), the campaign had 29 shares ($0.13/share).
  • 81.75% of the users are now visiting the site by phone, as an effect of the UI improvement allowing the puzzle-game to played on smaller screens.
  • Found +15 new supporters for the project - the names will be announced soon on the website.

Log in or sign up for Devpost to join the conversation.