Comments (37)
I'm hoping that I got the assignment correctly. In case I'm making a mistake, I'll greatly appreciate any corrections
from ersilia.
I think the way forward is to test the model by installing and trying it out after which we can then make a video tutorial on how newbies can install and use the model.
from ersilia.
@GemmaTuron I think we have two separate tutorials to cater for technical contributors and non technical contributors so that we come up with tutorials that will be of great use to our community.
from ersilia.
Thanks @GemmaTuron for the feedback. I found the resources cited by @AishaSaman very useful. I could create a simple tutorial using the template.
from ersilia.
Does this have to include articles from blog posts?
This is exciting and i would love to collaborate with you on this
Find below an example
https://towardsdatascience.com/how-to-use-machine-learning-for-drug-discovery-1ccb5fdf81ad
from ersilia.
Greetings @GemmaTuron
During my esearch, I came accross this video on Youtube, I don't know if it can be of help in any way
https://www.youtube.com/watch?v=SoeQZJLQlMc
from ersilia.
Below are links to some articles that I came across;
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3884843/
https://www.researchgate.net/publication/256200380_Open_source_drug_discovery_-_A_limited_tutorial
https://www.knime.com/blog/tutorials-for-computer-aided-drug-design-using-knime-workflows
from ersilia.
Hi, I am Aisha and I am Outreachy internship applicant.
I think this website have really good, simple tutorials for inspiration:
https://material.io/design/machine-learning/barcode-scanning.html#usage
Things that inspire me and I found helpful are:
- step by step with pictures and videos where necessary for better understanding
- dos and donts are shown with green and red colors
- links to related articles with each topic
- use cases shown
from ersilia.
I believe the 'Getting Started' page of Python is a good example. I would like to write such for Ersilia.
from ersilia.
Hello @GemmaTuron I have searched and gone through several tutorials from other FOSS communities and I found one at https://wiki.openmrs.org/display/docs/Developer+Guide so inspiring that we can borrow a leaf as we develop ours for Ersilia Model Hub and am passionate to contribute to the project.
from ersilia.
Hi @GemmaTuron I found this helpful for the usability of the Firefox FOSS project;
https://itsfoss.com/firefox/
And this for the VLC FOSS project;
https://itsfoss.com/install-latest-vlc/
https://www.flexclip.com/learn/vlc.html.
I am open to collaboration with other contributors to this issue
from ersilia.
Hello,
@AviatorIfeanyi, you link to a high level introduction to ML for drug discovery, but here we are looking at creating specific tutorials for the Ersilia Model hub, our tool. Please think how to do this and find perhaps more adapted examples before continuing
@Ama-tech0001, the first resources you list are also high level overview of using computer science for drug discovery. The most relevant and similar to what we need is the knime workflow. Good find, get your inspiration from there to work on issue #17
@victorabba a video tutorial would be fantastic!
@AishaSaman this is a good example, you can use it as a template to work on issue #17
@julietugo the "Getting Started" in python is good but very general, we would like something more detailed to the Ersilia Model Hub
@kbetty, the Developer manual is focused on new developers and contributors. Is not a bad idea but here we were thinking of tutorials for users, not developers. Can you find a user-oriented example?
@adeola-dev, you are citing great documentation of installation instructions, but here we are looking at more tutorial-type of examples, can you find one?
But to all of you, thanks for your work you are all citing interesting resources and I encourage you to answer my comments before moving to issue #17
from ersilia.
Thank you for the comments @GemmaTuron
Can you please check out what I did in issue #17 ?
from ersilia.
@kbetty, the Developer manual is focused on new developers and contributors. Is not a bad idea but here we were thinking of tutorials for users, not developers. Can you find a user-oriented example?
Thanks for the insight. I have gone through several user-oriented guides but the one at https://wiki.openmrs.org/pages/viewpage.action?pageId=589851 out-stands them and I think we can borrow a leaf and we come up with a user-friendly deployment guide for AI/ML models.
from ersilia.
Hi @GemmaTuron , I hope this will help
https://youtu.be/yL_NqXZgmks
from ersilia.
@GemmaTuron Knime flow as suggested by @Ama-tech0001 looks great, I believe I can create a similar tutorial and possibly include a short tutorial video on how to use the Ersilia Model Hub.
Here is a sample tutorial I found
https://torchdrug.ai/docs/tutorials/
On a video tutorial, I found this material
https://www.youtube.com/watch?v=ghUyZknxq5o
In our own video tutorial, I suggest no voice, just a low background music and captions on the screen that explains each step
from ersilia.
Pictures helps as anchor to direction and it gives a visualization of what to expect as well as a road map. I would like to contribute to this project by creating a picture tutorial for users.
from ersilia.
Thank you @GemmaTuron for the feedback. I believe this is what you are looking for - https://towardsai.net/p/l/how-to-discover-antiviral-drugs-with-deep-learning. I can create this kind of tutorial for Ersilia
from ersilia.
@GemmaTuron Here is Google AutoML. Though works on the cloud, It's an open source platform that enables people with little knowledge of ML to train models specific to their use cases.
Features:
Image classification
Video intelligence
Auto ML translation
Natural language
Links
https://www.youtube.com/watch?v=kgxfdTh9lz0
https://www.youtube.com/watch?v=aUfIFoMEIgg
from ersilia.
@GemmaTuron mam i would love to work on this issue.
from ersilia.
@GemmaTuron I have been reading more about the project to gather information on how best we can develop a simple tutorials for The Ersilia Model Hub. And as from my findings there are things we need to put into consideration
- The users of the tutorial(Most of the users/research scientists are not computer experts).
- The limitation users may encounter when using the tutorials during deploying
- The main barriers of AI adoption in experimental research.
- etc
Those factors above need to be carefully analysed so that we will create a tutorial for The Ersilia Model Hub ready to use AI model which will be easier for users(researchers) to adopt.
from ersilia.
Getting to know more on the project, I discovered that after Ersilia AI models are validated they are published for use but they lack the Deployment feature which can aid users to use the tool(s) with ease. Of which these users most of them are scientists who are actually not computer experts and this results into our tools not being widely adopted by the users.
So the Tutorial we are developing/creating is to address the issue above. And to my understanding based on the research have curried out we are creating a Deployment feature to our AI models for users to easily adopt to the tools during their research.
@GemmaTuron let me know whether am on track as I explore more with the project?
from ersilia.
Thanks @GemmaTuron for the feedback. I found the resources cited by @AishaSaman very useful. I could create a simple tutorial using the template.
please head to issue #17 to start working on this!
from ersilia.
Getting to know more on the project, I discovered that after Ersilia AI models are validated they are published for use but they lack the Deployment feature which can aid users to use the tool(s) with ease. Of which these users most of them are scientists who are actually not computer experts and this results into our tools not being widely adopted by the users.
So the Tutorial we are developing/creating is to address the issue above. And to my understanding based on the research have curried out we are creating a Deployment feature to our AI models for users to easily adopt to the tools during their research.
@GemmaTuron let me know whether am on track as I explore more with the project?
Hi @kbetty, you have done a good research! Indeed, non technical users might face difficulties in using the Hub. We would like one or two slides/text/video showing how can they use it (at the current stage of deployment, which is through CLI)
from ersilia.
@GemmaTuron Here is Google AutoML. Though works on the cloud, It's an open source platform that enables people with little knowledge of ML to train models specific to their use cases.
Features: Image classification Video intelligence Auto ML translation Natural language
Links https://www.youtube.com/watch?v=kgxfdTh9lz0 https://www.youtube.com/watch?v=aUfIFoMEIgg
Hi @MsChineme , this is a good find and a very nice example.
from ersilia.
@GemmaTuron mam i would love to work on this issue.
Hello @ps-19, comment with some examples you will use as a template and then go ahead to issue #17 !
from ersilia.
@GemmaTuron Here is Google AutoML. Though works on the cloud, It's an open source platform that enables people with little knowledge of ML to train models specific to their use cases.
Features: Image classification Video intelligence Auto ML translation Natural language
Links https://www.youtube.com/watch?v=kgxfdTh9lz0 https://www.youtube.com/watch?v=aUfIFoMEIggHi @MsChineme , this is a good find and a very nice example.
Thank you @GemmaTuron . Do I proceed to the next step, if yes? Please what is the next step?
from ersilia.
@GemmaTuron I think it already listed but a video tutorial as i learned a lot from video tutorials or like what you did in ersilia book to download the Ubuntu and other packages for ersilia API which was very straightforward and helpful.
from ersilia.
As part of the ground work during my research so that we develop a useful tutorial for users, I discovered there are as two ways of using the product:
- Using the CLI
- Using an online platform via cloud services( A web-based app)
However, at the our current stage of deployment, the user can so far use the CLI. My idea that am working on is to come up with the skeleton of a useful Table of Content for the tutorial which we can brainstorm on and then add content accordingly.
cc: @GemmaTuron
from ersilia.
We are working to develop simple tutorials for the Ersilia Model Hub. Can you comment below suggestion one example of a good tutorial from another FOSS project we could get inspiration from?
This is a required step to tackle Issue #17
Hello, I am Vaishnavi, Outreachy applicant.
First, we must install the model and analyze the problems the user might encounter during installation.
Then make a tutorial video which will show everything steps by step, from where to install it to how to use it.
from ersilia.
We are working to develop simple tutorials for the Ersilia Model Hub. Can you comment below suggestion one example of a good tutorial from another FOSS project we could get inspiration from?
This is a required step to tackle Issue #17Hello, I am Vaishnavi, Outreachy applicant. First, we must install the model and analyze the problems the user might encounter during installation. Then make a tutorial video which will show everything steps by step, from where to install it to how to use it.
I found a series of tutorial videos that explain everything about the app, starting with what it is, how to use it, what plus points are, etc.
Here I am sharing this series I think this will be helpful to make any tutorial video.
https://youtu.be/HCc7wzUH4ts - Introduction and app overview
https://youtu.be/gH2G0niO6cM - Visualize your thoughts
https://youtu.be/4sp2X4nsBwA - Tell the story through media
https://youtu.be/z_H7i-ERVQI - Capture everything
https://youtu.be/jq42O1W_Iys - Share for feedback
https://youtu.be/oANcUP2Q9XA - Meetings with meaning
from ersilia.
Hi @GemmaTuron I see a lot of traction here! Can we nominate some assignees? (see right bar).
from ersilia.
We are working to develop simple tutorials for the Ersilia Model Hub. Ca you comment below suggestion one example of a good tutorial from another FOSS project we could get inspiration from?
This is a required step to tackle Issue #17
Hi @GemmaTuron,
These are a few suggestions of good tutorials I found from different sources. Please provide feedback. Thank you.
https://www.youtube.com/watch?v=SoeQZJLQlMc
https://material.io/design/machine-learning/barcode-scanning.html#usage
https://towardsai.net/p/l/how-to-discover-antiviral-drugs-with-deep-learning
https://www.youtube.com/watch?v=kgxfdTh9lz0
from ersilia.
Hi @GemmaTuron,
These are a few suggestions of good tutorials I found from different sources. Please provide feedback. Thank you.
https://www.youtube.com/watch?v=SoeQZJLQlMc
https://material.io/design/machine-learning/barcode-scanning.html#usage
https://towardsai.net/p/l/how-to-discover-antiviral-drugs-with-deep-learning
https://www.youtube.com/watch?v=kgxfdTh9lz0
from ersilia.
Hello, @GemmaTuron Can we make tutorial how Ersilia Model Hub will help in future for mankind ?
from ersilia.
@GemmaTuron @miquelduranfrigola I have gone through your documentation,specifically the strategic plan, and I have an idea of what you guys stand for and a partial vision for what you intend Ersilia to become.
In light of that, I believe your tutorials should be modeled more like a mini-course similar to the ones in the links below
I would argue that it would be much easier to grow a tutorial organically as a course over-time and would capture all of Ersilia's values.
https://huggingface.co/course/chapter1/1
https://spacy.io/usage/spacy-101
or,create mini-projects using Ersilia's models the structure could be similar to the link attached by a fellow community member
https://www.youtube.com/watch?v=kgxfdTh9lz0
I can come up with something similar.
from ersilia.
Hello all,
Thanks for your ideas, sound great! Please follow the new contribution guidelines to make sure we can track each applicant's work and suggestions!
I will close this issue now to move the discussions to the relevant thread
from ersilia.
Related Issues (20)
- 🐕 Batch: Ersilia Pack Development
- 🐕 Batch: New EOS Template
- 🐕 Batch: Make Ersilia CLI work with new Packing strategy
- 🐕 Batch: Design and document endpoints in the new app template within Ersilia Pack
- 🐈 Task: Use SPDX License identifiers in the Model Request issue template HOT 1
- 🐈 Task: Remove PyAirtable as a hard dependency HOT 1
- 🐈 Task: Fix action that uploads Ersilia base image to DockerHub
- 🐈 Task: Bump requests and docker-py versions in ersilia
- 🐕 Batch: Maintain additional credentials' requirements within models HOT 1
- 🐈 Task: Docker build for ersilia-pack HOT 2
- 🐛 Bug: log file not found warning after using the track flags
- 🐛 Bug: Fetching models on MacBook (M1) results in 404 error due to looking for linux/arm64 HOT 1
- 🐕 Batch: Define Model Installs through a YAML file instead of a Dockerfile HOT 3
- 🐕 Batch: Resource monitoring with different input scenarios and systems HOT 2
- 🐛 Bug: Numpy versions conflicts HOT 2
- 🐛 Bug: Tracking functionality does not work when a result CSV file is not specified
- 🐛 Bug: Performance Metrics Fail for String Output Model HOT 4
- 🐛 Bug: Ersilia close when model serving is interrupted HOT 2
- 🦠 Model Request: Cardiotoxicity Classifier HOT 13
- 🦠 Model Request: Demo Malaria Model HOT 8
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ersilia.