This is a private hackathon open to undergraduate and postgraduate students from African universities; see the full list of universities and university representatives here. If your university is participating you can reach out to them from 22 March for the secret code.
How to prepare for UmojaHack
DeepChain™ is a revolutionary new platform that uses deep learning to model protein interactions to help design better drugs and understand the biochemical world in more detail. One of the things it can be used for is to evaluate the effectiveness of neutralizing antibodies against viruses like COVID-19 and influenza.
In this challenge, InstaDeep is asking for your help to design a function to score how effectively an antibody binds to the influenza virus receptor binding domain. Identifying a neutralising antibody that effectively targets the influenza virus could offer enormous therapeutic potential.
The objective of this challenge is to predict the binding of influenza.
Influenza pandemics occur when a new flu virus can infect people and spread globally. In 1918, an estimated 500 million people (one-third of the world’s population) became infected with this virus, with at least 50 million people dying as a result. More recently the H3N2 variant has been shown to have dangerous pandemic potential.
We now use preventive measures to try and prevent such a catastrophe, in the form of annual vaccines. However, influenza’s genetic makeup is constantly evolving, preventing one single vaccine from being effective. As a result, we still have annual "seasonal flu" epidemics, which have a significant impact both in terms of lives and healthcare costs. A possible co-infection with influenza and COVID-19 could carry even higher risks.
For this reason, we need neutralising antibodies that can target any new flu variants that might escape current vaccines’ protection. As opposed to a vaccine, these would constitute a therapeutic option for patients who are already infected. Designing a neutralising antibody targeting this the H3N2 influenza virus variant could offer enormous therapeutic potential.
How does influenza work?
The flu virus targets the cells in your respiratory system, like your nose, throat and lungs. The virus uses a special protein called haemagglutinin (HA) to attach to those specialised respiratory cells. Once it gets inside, it hijacks those cells to start making copies of itself.
Antibodies that bind to the head domain of HA typically have potent neutralising activity for the virus; hence we will focus on designing a good binding scorer for the receptor bind domain (RBD) of the HA protein head.
About InstaDeep (instadeep.com)
InstaDeep delivers AI-powered decision-making systems for the Enterprise. With expertise in both machine intelligence research and concrete business deployments, we provide a competitive advantage to our customers in an AI-first world. As one of the leading AI companies in Africa, InstaDeep knows first-hand what African talent is truly capable of.
InstaDeep has more than 120 employees spread across its headquarters in London, and offices in Paris, Tunis, Dubai, Lagos and Cape Town. In addition to its connections to African educational institutions, the company also possesses strong ties to elite French schools and top rated universities in the UK. To apply: instadeep.bamboohr.com/jobs and firstname.lastname@example.org.
About Microsoft (microsoft.com)
Microsoft (Nasdaq “MSFT” @microsoft) enables digital transformation for the era of an intelligent cloud and an intelligent edge. Microsoft has operated in Africa for more than 25 years. In that time they have built strong partnerships across the continent, helped bridge gaps in infrastructure, connectivity and capability, and are working to empower countries in Africa to digitally transform while creating sustained societal impact. Earlier this year, Microsoft opened Africa’s first hyper-scale data centers in Johannesburg and Cape Town, South Africa. Most recently, the company also announced the opening of two Africa Development Centers in Nairobi and Lagos, where world class African talent can create innovative solutions for local and global impact.
About Standard Bank (standardbank.com)
Standard Bank Group is a financial institution that offers banking and financial services to individuals, businesses, institutions and corporations in Africa and abroad. All Standard Bank products and services are based on a set of values that uphold the empowerment of their customers. Both internally, and in daily engagement with their clients we foster transparency, innovation, accountability and superior service.
This is a private hackathon open to undergraduate and postgraduate students from African universities; see the full list of universities here. If your university is participating you can reach out to them from 22 March for the secret code.
Teams and collaboration
You may participate in competitions as an individual or in a team of up to four people. When creating a team, the team must have a total submission count less than or equal to the maximum allowable submissions as of the formation date. A team will be allowed the maximum number of submissions for the competition, minus the total number of submissions among team members at team formation. Prizes are transferred only to the individual players or to the team leader.
Multiple accounts per user are not permitted, and neither is collaboration or membership across multiple teams. Individuals and their submissions originating from multiple accounts will be immediately disqualified from the platform.
Code must not be shared privately outside of a team. Any code that is shared, must be made available to all competition participants through the platform. (i.e. on the discussion boards).
The Zindi user who sets up a team is the default Team Leader. The Team Leader can invite other data scientists to their team. Invited data scientists can accept or reject invitations. Until a second data scientist accepts an invitation to join a team, the data scientist who initiated a team remains an individual on the leaderboard. No additional members may be added to teams within the final 5 days of the competition or the last hour of a hackathon, unless otherwise stated in the competition rules
A team can be disbanded if it has not yet made a submission. Once a submission is made individual members cannot leave the team.
All members in the team receive points associated with their ranking in the competition and there is no split or division of the points between team members.
Datasets and packages
The solution must use publicly-available, open-source packages only. Your models should not use any of the metadata provided.
You may use only the datasets provided for this competition. Automated machine learning tools such as automl are not permitted.
You may use pretrained models as long as they are openly available to everyone.
The data used in this competition is the sole property of Zindi and the competition host. You may not transmit, duplicate, publish, redistribute or otherwise provide or make available any competition data to any party not participating in the Competition (this includes uploading the data to any public site such as Kaggle or GitHub). You may upload, store and work with the data on any cloud platform such as Google Colab, AWS or similar, as long as 1) the data remains private and 2) doing so does not contravene Zindi’s rules of use.
You must notify Zindi immediately upon learning of any unauthorised transmission of or unauthorised access to the competition data, and work with Zindi to rectify any unauthorised transmission or access.
Your solution must not infringe the rights of any third party and you must be legally entitled to assign ownership of all rights of copyright in and to the winning solution code to Zindi.
Submissions and winning
You may make a maximum of 100 submissions per day.
Before the end of the competition, you need to choose 2 submissions to be judged on for the private leaderboard. If you do not make a selection your 2 best public leaderboard submissions will be used to score on the private leaderboard.
Zindi maintains a public leaderboard and a private leaderboard for each competition. The Public Leaderboard includes approximately 50% of the test dataset. While the competition is open, the Public Leaderboard will rank the submitted solutions by the accuracy score they achieve. Upon close of the competition, the Private Leaderboard, which covers the other 50% of the test dataset, will be made public and will constitute the final ranking for the competition.
Note that to count, your submission must first pass processing. If your submission fails during the processing step, it will not be counted and not receive a score; nor will it count against your daily submission limit. If you encounter problems with your submission file, your best course of action is to ask for advice on the Competition’s discussion forum.
If you are in the top 5 at the time the leaderboard closes, we will email you to request your code. On receipt of email, you will have 2 hours to respond and submit your code following the submission guidelines detailed below. Failure to respond will result in disqualification.
If your solution places 1st, 2nd, or 3rd on the final leaderboard, you will be required to submit your winning solution code to us for verification, and you thereby agree to assign all worldwide rights of copyright in and to such winning solution to Zindi.
If two solutions earn identical scores on the leaderboard, the tiebreaker will be the date and time in which the submission was made (the earlier solution will win).
If the error metric requires probabilities to be submitted, do not set thresholds (or round your probabilities) to improve your place on the leaderboard. In order to ensure that the client receives the best solution Zindi will need the raw probabilities. This will allow the clients to set thresholds to their own needs.
The winners will be paid via bank transfer, PayPal, or other international money transfer platform. International transfer fees will be deducted from the total prize amount, unless the prize money is under $500, in which case the international transfer fees will be covered by Zindi. In all cases, the winners are responsible for any other fees applied by their own bank or other institution for receiving the prize money. All taxes imposed on prizes are the sole responsibility of the winners. The top 3 winners or team leaders will be required to present Zindi with proof of identification, proof of residence and a letter from your bank confirming your banking details.
You acknowledge and agree that Zindi may, without any obligation to do so, remove or disqualify an individual, team, or account if Zindi believes that such individual, team, or account is in violation of these rules. Entry into this competition constitutes your acceptance of these official competition rules.
Zindi is committed to providing solutions of value to our clients and partners. To this end, we reserve the right to disqualify your submission on the grounds of usability or value. This includes but is not limited to the use of data leaks or any other practices that we deem to compromise the inherent value of your solution.
Zindi also reserves the right to disqualify you and/or your submissions from any competition if we believe that you violated the rules or violated the spirit of the competition or the platform in any other way. The disqualifications are irrespective of your position on the leaderboard and completely at the discretion of Zindi.
Reproducibility of submitted code
Consequences of breaking any rules of the competition or submission guidelines:
Monitoring of submissions
We reserve the right to request code from any user at any time during a challenge. You will have 24 hours to submit your code following the rules for code review (see above). Zindi reserves the right not to explain our reasons for requesting code.
Teams may win in one challenge category, and are encouraged to enter only one
The evaluation metric for this challenge is the Root Mean Squared Error.
The target can be any values between 0 and 1, inclusive.
Your submission file should look like:
In order to win, you must:
1st Place: Individual/team prize - $1000 and university prize $2000
2nd Place: $600
3rd Place: $400
Instadeep will set up internship interviews with the top 3 teams.
Standard Bank will invite the top 3 teams to a career day where they will introduce you to recruitors.
This hackathon will run from 9:00 GMT on Saturday, 27 March to 16:29 GMT on Sunday, 28 March.
Follow all the action and updates on YouTube.
08:00 GMT Welcome and orientation and introduction to our sponsors.
08:45 GMT A short introduction to each challenge so you can decide which challenge to follow.
09:00 GMT Competition opens (note that users can sign up for a competition and join teams before the time)
09:00 GMT Tutorials on how to get started with each challenge will be shared on YouTube and the discussion forum
10:00 GMT Q&A session with a Zindi data scientist (Amy) answering any questions you may have about the challenge on YouTube. Post your questions on the discussion or Twitter and tag us.
12:00 GMT Chat with NVIDIA and Sendy, come prepared with questions
14:00 GMT Chat with Old Mutual
08:00 GMT Welcome back
08:15 GMT Q&A session with a Zindi data scientist (Amy) answering any questions you may have about the challenge on YouTube. Post your questions on the discussion or Twitter and tag us.
12:00 GMT Chat with a Zindi ambassador
14:30 GMT Final address and the count down starts to the end of the hackathon.
15:00 GMT Submissions close
15:30 GMT Private leaderboard is revealed and announcement of international winners and prizes.
Using DeepChain™ to check the influenza receptor binding domain
You can use DeepChain™ to check the complex structure between the haemagglutinin (HA) and the prospective antibody by following these instructions:
The Spanish Influenza pandemic of 1918 infected over 500M people, about 4 times as much as the current COVID-19 pandemic.
For this challenge, InstaDeep is asking for your help to develop a better treatment to combat future influenza pandemics. In this piece, we aim to explain the basics of biology so that you understand the impact you are having in the current scientific knowledge and healthcare by participating in this challenge.
As we all know, the cell is the building block of all living things, whether human, animal or vegetal.
In multicellular beings, each cell has a function, and will clump together to form tissue, organs etc. Cells contain three main structures:
Legend: The three main components of a cell are the membrane, the cytoplasm and the nucleus.
These structures are composed of molecules, which are structures created by binding various chemical compounds. A molecule can be constructed by simple atoms, such as water (H2O, which is two hydrogen atoms and one oxygen atom), or by more complex systems of atoms, such as amino acids.
One of the key molecular components of a cell and living organisms are proteins. Proteins are large, complex molecules that play many critical roles in the body: catalyze reactions, transport and react to signals, build tissues, and detect and protect us from infections.
Proteins are long, linear sequences made from 20 different amino acids, and their function relies on the 3D and 4D structures they acquire once they are formed.
Legend: Proteins are synthesized as strings of amino acids, which are then folded into a 3D structure with function.
An antibody is a type of protein that plays a critical role in the body’s immune response to pathogens like influenza.
Proteins can bind to each other and to other molecules, such as ions, small molecules and other macromolecules. These are called ligands.
Binding between proteins and ligands isn’t random. The protein discriminates between many different molecules and will only bind to the most compatible ligand, much like a puzzle piece slotting into place. The bond can be weak and transient or strong and persistent. When designing drugs or proteins, the aim is to maximise the compatibility of the ligand to the protein we want it to attach to and to make the bond as solid as possible.
Legend: Proteins bind their ligands through specific and reversible interactions.
One thing to note is that all these structures are influenced by the environment they’re in. They move, flex and fold in different ways, and the binding is affected by other proteins and ligands as well. Nothing here is completely static.
Although some molecules can easily travel into cells, the majority need to be either passively or actively transported via protein channels through the cell membrane.
The influenza virus uses its haemagglutinin (HA) protein, located on its external shell, to attach to specialized cells in your throat, nose and lungs and enter them via a sialic acid-containing receptor. From there, the newly infected cell goes on to cause an immune reaction, usually resulting in the cell’s death.
How can we block this infection? Antibodies!
Legend: The Influenza virus uses proteins located on its envelope to attach to and enter targeted cells. In the challenge, the participants will be designing antibodies that prevent this virus-cell contact.
Influenza pandemics occur when a new flu virus can infect people and spread globally.
We now use preventive measures to try and prevent such a catastrophe, in the form of annual vaccines. However, influenza’s genetic makeup is constantly evolving and mutating, preventing one single vaccine from being effective. As a result, we still have annual "seasonal flu" epidemics, which have a significant impact both in terms of lives and healthcare costs. Recently the H3N2 variant has been shown to have dangerous pandemic potential. A possible co-infection with influenza and COVID-19 could carry even higher risks.
For this reason, we need neutralising antibodies that can target any new flu variant that might escape current vaccines’ protection. As opposed to a vaccine, these would constitute a therapeutic option for patients who are already infected, preventing the virus from spreading and essentially, stalling and defeating the infection.
Using DeepChain, an AI-accelerated protein design platform by InstaDeep, we can score the effectiveness of an antibody-protein binding. All we need is an antibody sequence, and that’s where you come in!