Closed victorabba closed 2 years ago
There are a lot of scientist and researchers that are not technically inclined especially in the programming field. This is a huge limitation as most medical research works deals with analysis of historical data which is required to design a predictive model. Ersilia could help eliminate this huddle by designing models that requires little or no programming experience. This will save the researcher a lot of resources outsourcing the task.
The potential ability of the Ersilia model in predicting and preventing future disease occurance in an individual cannot be overemphasized. For instance the incorporation of a machine learning model capable of predicting wether an individual is potentially diabetic or not is quite possible since such a model is built using prognosis data of several patients. Such technique can be applied to the prediction of heart diseases. The ability of the Ersilia model hub to use ML algorithms in medicine is what picked my interest in the project.
I believe the Ersilia model is the future of AI in medicine.
I made the 'slack' word a link and also modified the project name.
Hi @victorabba You have already made some previous contributions, could you check how @ifeoluwafavour has linked them in her github issue and do the same? This way we have all contributions in one space. Thanks!
Initial tasks:
1 I added a contributing guideline for contributors.
2 I created a step by step process for installing the Ersilia model in a windows operating system. I used the Oracle virtual box system to install the Ubuntu. The file is present in the documentation folder.
I modified the template for a fixing a bug issue
I added a question to feature request
In the Outreachy documentation project I made the 'slack' word a link and also modified the project name.
Hi @GemmaTuron , I added some contents to my file containing the Ersilia installation steps using Windows. I've also created a pull request for it, please review and let me know if there are any other changes required.
Hi @victorabba thanks for linking your work here. The WSL installation is very detailed, but I would appreciate if you use markdown formatting to make it easier to follow (for example, use titles and subtitles with the ### ). The steps are really detailed so perhaps you could divide them in sections (Installation of Oracle, Installation of Ubutnu, Installation of Dependencies)
Like I commented in @ifeoluwafavour 's work, state somewhere that it does not matter if the dependencies are installed in windows they need to be installed again in the virtual box
thanks!
Thanks for the corrections @Gemma. I will implement them right away.
Current tasks:
1 Blogpost for the Ersilia 2021-2023 strategic plan.
2 A bogpost on Application of AI/ML in biomedical research.
3 Twitter template for new model release (280 characters max):
Hello fans! We have a new model in the hub. The model is used for (explain the function of the model). For more information on the model check out the documentation__(put link to documentation/literature).
4 Newsletter template:
To calculate the molecular mass of Aspirin.
Result of molecular mass of Aspirin.
Hi @victorabba
I cannot access the blogposts, can you revise permissions? thanks!
Ok. You can try now I have reviewed permissions.
Class ErsiliaModel(ErsiliaBase): """ Defines the instance of the ersilia model class and fetches the model""".
def is_valid(self): """ Checks if the model is valid""".
def api( self, api_name=None, input=None, output=None, batch_size=DEFAULT_BATCH_SIZE ): """ Defines the model API name, input, output and size""".
def api_task(self, api_name, input, output, batch_size): """ Defines the tasks of the model API"""
def serve(self): """ Serves the model""".
def close(self): """Closes the model""".
Graphic material
1 An image slide to explain Ersilia's mission and vision. https://docs.google.com/presentation/d/1zKa6SBnGXrmIa-vwR87I8HGK00DAZ2IO/edit?usp=drivesdk&ouid=108466039633231002874&rtpof=true&sd=true
2 A tutorial video on how to use the Ersilla model hub.
https://drive.google.com/file/d/11_ccuBi2grs0WsTPzjJlmcre_wDcsvLo/view?usp=drivesdk
Hi @victorabba i was going through your image and i noticed that the content was overlapping the slides. Kindly re-check.
@adeolaadedeji what app are you using to view it? I'm using a Wps app and it's perfect.
Hi, @victorabba i used google drive. You can check it using the app.
It's not a doc file. It's a ppt file. It's uploaded to Google drive but opens with wps or any app that has PowerPoint.
On Fri, Apr 8, 2022, 13:02 adeolaadedeji @.***> wrote:
Hi, @victorabba https://github.com/victorabba i used google drive. You can check it using the app.
— Reply to this email directly, view it on GitHub https://github.com/ersilia-os/ersilia/issues/106#issuecomment-1092787850, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXG7FLQVOGQT6ENO4VSD74LVEAN3LANCNFSM5SNN735Q . You are receiving this because you were mentioned.Message ID: @.***>
Well done Victor!
Thanks @Ife
Commented on @ifeoluwafavour and @AIgbine Blogpost for Ersilia's strategic plan.
Hi @victorabba,
I am revising all your work, thanks for the effort you are putting into this.
Hope you find some of these comments helpful, take your time to incorporate them and let us know
Thanks @Gemma, I will make the changes.
On Fri, Apr 8, 2022, 17:30 gemmaturon @.***> wrote:
Hi @victorabba https://github.com/victorabba,
I am revising all your work, thanks for the effort you are putting into this.
- Strategic plan: I really like that you use the KPI term, well thought. Some minor changes: I would try to rephrase the " we tend to" for something more clear, we accomplish, we aim to... and I know its boring but try to find a different sentence each time rather than repeating the same. Many times writing requires to find two or three ways to say the same. And revise the acronyms, the best is to add them the first time they appear, for example Low and Middle Income Countries (LMIC) and then simply use the same throughout the text.
- AI in biomedical Research: Researchers at the Ersilia institute have developed a model which can predict whether a substance has antibiotic components or not. Can you make this more general? we do not only work on antibiotics but in general try to speed up drug discovery against infectious diseases
- The twitter post is good but could you try to make it more catchy? People only spend seconds looking at Twitter! Somthing like: We have a new model in the Hub! ... Also if you need you can use more than one post (if you do not have twitter, these are called threads, so there is a main message and then a few hidden, with less important messages. All limited in length)
- Good its the first newsletter template I am revising! Could you separate between users and then funders, or how much we have raised? Something about how many volunteers work with us would be nice
Hope you find some of these comments helpful, take your time to incorporate them and let us know
— Reply to this email directly, view it on GitHub https://github.com/ersilia-os/ersilia/issues/106#issuecomment-1093067696, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXG7FLVJCNCQ6HX7LXYC6J3VEBNLHANCNFSM5SNN735Q . You are receiving this because you were mentioned.Message ID: @.***>
Hey @victorabba I actually a little correction on a document you created victor_windows.md #181 a typo where they was used instead of the.
Thanks @dchidindu5
Hello @GemmaTuron , I have implemented all the changes.
Great job @victorabba so far. I really love your blogpost on AI in medical research. Very insightful.
Thanks @loweyvana
Hi @victorabba
You have done a lot of work, I am loving the video, very explanatory! I think you are more than ready to submit your final application, thanks for the hard work you put into it!
Thanks @Gemma. I'm pleased to hear that.
Hello @victorabba. Your tutorial is precise and well explained. Nice Job.
Great tutorial @victorabba
This issue has been closed.
Applicant: @victorabba
Welcome to the Ersilia Open Source Initiative. This issue will serve to track all your contributions for the project “Improving the documentation and outreach material of the Ersilia Model Hub”.
Please tick the tasks as you complete them. To make a final application it is not required to have completed all tasks. Only the Initial Steps and Community sections are REQUIRED. The tasks are not ordered from more to less important, they are simply related to different skills. Start where you feel most comfortable. This project can be adapted to the applicants interests, please focus on the type of tasks that you prefer / have better skills / would like to work on as an intern.
Initial steps:
[x] Comment under this issue explaining why are you interested in this project
GitHub documentation:
[ ] Incorporate feedback from the mentor
Writing dissemination material
[x] Create a template for a short Newsletter (1 paragraph) to send every month to our community (funders, users, contributors). It should mention metrics (models in the hub, number of users, funding…), thank you etc
Technical skills (required for the tutorial only)
[x] Write a docstring for the ErsiliaModel class. Use the Google Python Style guide. Paste the docstring as a comment below (do not use a PR).
Graphic material
[x] Incorporate feedback from the mentor
Scientific content
[ ] Search the scientific literature and suggest 3 new models (comment in this issue) that would be relevant to incorporate in the Hub.
Community
[x] If you have feedback from your peers, answer it in this issue.
Other
If you have interest in working on related topics, or have new suggestions, please do the following
[ ] Link in the comments any other PR you have contributed to.
Final application