# GSON module "chimie informatique sous python"
This course is mostly based on [teachopencadd](https://github.com/volkamerlab/teachopencadd).
Huge thanks to them for providing such good learning material.
## Launch notebooks directly in your browser
- If you prefer the modern `jupyter lab` interface: [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/ICOA-SBC/GSON-cheminformatics/HEAD)
- be careful that for the exos using `nbautoeval`, the cell output may return error
- for the moment it is **NOT recommended to use above method**
- If you prefer the traditional `jupyter notebook` interface: [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/ICOA-SBC/GSON-cheminformatics/HEAD?urlpath=/tree/)
The materials are exactly the same. The only difference is the appearance.
The 1st launch can take around 10 minutes, and it will be faster from 2nd time.
It **does not require any setup/installation on your machine** (which is quite easy to use). You just need an Internet connection and a browser.
**Remarks:**
1. To save resources, your connection to the `Binder` server will be **automatically cut off** if you have no activity (cell edit/cell execution) for around 10 mins
2. Your changes to the notebooks will **NOT be saved**. So if you close the browser and re-open `Binder`, you lose all what you have done previously...
## Special instructions for promo 2023-2024
If you are using `Windows` on your own PC, before each course, please execute the command `git pull` in your terminal, to get the latest version of material.
If you are using the `Linux` session on the PCs of "salle info", here are the commands to follow, from Tuesday to Friday:
1. Open a terminal, copy-paste below command into it, and execute it:
```bash
/opt/anaconda3/bin/conda init
```
2. Normally, the message of the terminal will suggest you to close and re-open the terminal after above command is executed successfully.
Simply close and re-open another terminal.
You should now see `(base)` on the leftmost of your prompt. (ask the teachers if you still cannot see it)
3. Create the virtual environment for this course from given file, by copy-paste below command into your terminal, and execute it:
```bash
conda env create -f https://raw.githubusercontent.com/ICOA-SBC/GSON-cheminformatics/master/environment.yml
```
- This file contains a list of `conda`/`pip` packages that are required for this course.
- You are encouraged to check the content of this file, to make sure it does not contain malicious software.
- This command will take 3-10 mins, depending on the configuration of your PC, and the Internet connection
4. Once above command finishes with success, you can now clone the repo to your local PC, by copy-paste below command into your terminal, and execute it:
```bash
git clone https://github.com/ICOA-SBC/GSON-cheminformatics
```
5. Activate the virtual environment:
```bash
conda activate teachopencadd
```
- You should observe that the `(base)` has become `(teachopencadd)`, meaning that you are now in this new virtual environment.
6. You are ready to go. Simply launch the `notebook` interface with command:
```bash
jupyter notebook
```
## Organisation of session 2023-2024
### Lundi 15 janvier 2024 13h30-17h30
- Introduction
- Slides 1_GSON_intro (30 min) XM & JM
- Slides 2_introduction_informatique (45 min) XM
- Talktorial Introductif 1 Intro Python, jupyter (1h40) XM
### Mardi 16 janvier 2024 13h30-17h30
- Talktorial Introductif 2 Intro chemoinfo - RDKit (1h40) JM
- Data Acquisition (1h30) XM
- Talktorial 1 Data acquisition from ChEMBL
### Mercredi 17 janvier 2024 13h30-17h30
- Filtering (1h45-2h) JM
- Descriptors and ADME (1h30)
- Slides 4_Descripteurs_fingerprints
- Talktorial 2 Molecular filtering: ADME/Lipinski criteria
- Filtering (40 min) XM
- Talktorial 3 Substructure removal : PAINS
### Jeudi 18 janvier 2024 13h30-17h30
- Ligand based Screening (2h30) JM
- Slides 5_fingerprint_similarity (30 min)
- Talktorial 4 Fingerprints and Molecular Similarity (2h)
- Clustering (1h45) XM
- Talktorial 5 : Compound clustering
### Vendredi 19 janvier 2024 13h30-17h30
- Machine Learning (1h45) JM
- Slides 6_Machine Learning
- Talktorial 7 Machine Learning (ROC curve)
- Applications in chemoinformatic (45 min) XM & JM
- Slides 7_Applications
- Exam (60 min)
## History of previous years
- 2018: Fabrice, Colin
- 2019: Colin, Gautier
- 2020: Gautier, Pierre-Yves
- 21 students
- Integration of TeachOpenCADD and binder
- 2021: Gautier, Pierre-Yves
- 22 students
- Distance learning, via TEAMS
- Integration of nbautoeval (Exercises and Quiz)
- 2022: Pierre-Yves, Xiaojun
- 9 students (7 present, 2 absent)
- Introduce ```mamba``` for quicker env resolution
- Added short introduction of Linux Commands
- 2023: Pierre-Yves, Xiaojun
- 5 students (4 present, 1 absent)
- Created a pre-course questionnaire to better adapt the course to future students attending the course
- 2024: Xiaojun, Jérémy
- 17 students (16 inscriptions + 1 volunteer participant)
- Cleaned not used packages/channels in `environment.yml` for quicker env resolution
- Added `Slide 7_Applications`, to showcase other fields of applications not covered in the course
## Installation
Suppose that you are using **Linux** (**MacOS** should work the same way, since it is also **Unix**):
1. Install `miniconda` (or `anaconda` if you prefer)
- For installation details, please refer to their [official documentation](https://docs.conda.io/en/latest/miniconda.html).
2. Open a terminal, you should normally see `(base)` before your prompt. (See below FAQ part if you cannot see `(base)`)
Create the virtual environment for this course from given file:
```bash
conda env create -f https://raw.githubusercontent.com/ICOA-SBC/GSON-cheminformatics/master/environment.yml
```
- This file contains a list of `conda`/`pip` packages that are required for this course.
- You are encouraged to check the content of this file, to make sure it does not contain malicious software.
3. Open a terminal, and clone the repo to your local PC:
```bash
git clone https://github.com/ICOA-SBC/GSON-cheminformatics
```
4. Activate the virtual environment:
```bash
conda activate teachopencadd
```
- You should observe that the `(base)` has become `(teachopencadd)`, meaning that you are now in this new virtual environment.
5. You are ready to go. Simply launch the `notebook` interface with command:
```bash
jupyter notebook
```
## FAQ
### What if you cannot find `conda` by typing `which conda`, or you do not see `base` before your prompt?
Experience 2024:
In the computer rooms of COST, `conda` is installed at `/opt/anaconda3`, not under each user's `/home`.
Furthermore, it is NOT added to the `$PATH`, making it unfindable by `which conda` command.
Even more, the `/home` of each student will be automatically deleted on the 2nd day of the course, after restarting the PC...(by default the PCs are automatically shut down during the night).
So it means the students have to repeat the steps of
- initiate `conda`
- create `conda` virtual environment
- clone the course material
from Tuesday to Friday, before each course starts (which is annoying!)
### Work in progress, reserved for teachers
1. Open a terminal, and type `echo $PATH` to check the existing PATHS (normally you shoud not be able to find `/opt/anaconda3`).
2. Type `gedit ~/.bashrc`. A text editor interface will automatically appear.
3. Add `export PATH=/opt/anaconda3/bin:$PATH` to the end of the file, then save and close the file.
4. Reload the profile with `source ~/.bashrc`
5. Type the command `which conda`, you should be able to find it at `opt/anaconda3/`.
6. Type the command `conda init bash` to initiate it.
7. Reload the profile with `source ~/.bashrc`.
After all these steps, you should now see `(base)` before your prompt.
### Anot
没有合适的资源?快使用搜索试试~ 我知道了~
研究生院Orléans数字化学信息学课程期间与学生共享的笔记本存储库。.zip
共87个文件
png:22个
ipynb:19个
yaml:8个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 174 浏览量
2024-03-25
15:27:16
上传
评论
收藏 14.23MB ZIP 举报
温馨提示
国内外优秀项目,值得商业研发或毕业设计
资源推荐
资源详情
资源评论
收起资源包目录
研究生院Orléans数字化学信息学课程期间与学生共享的笔记本存储库。.zip (87个子文件)
GSON-cheminformatics-master
cours_2
PCA.ipynb 1.2MB
T1_ChEMBL.ipynb 127KB
data
meds.sdf 11.12MB
bioact_df_T1_ChEMBL.p 1.63MB
df_IC50_T1_ChEMBL.p 536KB
T2_adme_filtering_student.ipynb 33KB
T2_adme_filtering.ipynb 251KB
images
chemble_table1.png 220KB
chembl_webservices_schema_diagram.jpg 71KB
adme.png 129KB
radarplot.png 306KB
T1_ChEMBL_student.ipynb 34KB
PCA_Student.ipynb 23KB
corrections
quiz
T4_mol_similarity.yaml 5KB
PCA.yaml 4KB
intro.yaml 7KB
substructure_filtering.yaml 3KB
T5_cmpd_clustering.yaml 3KB
ML.yaml 3KB
T1_ChEMBL.yaml 5KB
ADME.yaml 3KB
exercices
__init__.py 0B
intro.py 673B
T4_mol_similarity.py 3KB
ML.py 2KB
T5_cmpd_clustering.py 3KB
ADME.py 5KB
PCA.py 4KB
T1_ChEMBL.py 3KB
cours_3
data
molsim_df_T4.p 2.49MB
enrichment_data_T4.p 142KB
T4_mol_similarity_student.ipynb 147KB
T3_substructure_filtering_student.ipynb 24KB
T3_substructure_filtering.ipynb 522KB
T4_mol_similarity.ipynb 725KB
images
PAINS_Figure.jpeg 110KB
enrichment_plot.png 244KB
PAINS_Figure2.jpeg 161KB
morgan_fp.png 48KB
maccs_fp.png 27KB
data
T7
mlp_roc.png 301KB
rf_roc.png 294KB
svm_roc.png 302KB
T4
enrichment_plot.png 190KB
T2
EGFR_compounds_lipinski.csv 531KB
radarplot_not_rof.png 247KB
radarplot_rof.png 235KB
T5
cluster_representatives.svg 36KB
molSet_largestCluster.sdf 409KB
cluster_dist_cutoff_0.20.png 54KB
T6
mcs_largestcluster.svg 71KB
ACP
meds.sdf 11.12MB
T3
substructures.svg 115KB
unwantedSubstructures.csv 4KB
EGFR_compounds_lipinski_noPAINS_noBrenk.csv 163KB
EGFR_compounds_lipinski_noPAINS.csv 250KB
README.md 80B
T1
EGFR_compounds.csv 520KB
compound_df_T1_ChEMBL_20240109.p 20.19MB
EGFR_compounds_from_chembl_query_20190411.p 2.34MB
cours_1
1_IntroToPythonAndJupyter.ipynb 122KB
data
mytest_mol3D.sdf 5KB
EGFR-course.csv 335B
2_IntroToChemoinformatics.ipynb 17KB
2_IntroToChemoinformatics_student.ipynb 21KB
1_IntroToPythonAndJupyter_student.ipynb 27KB
init.sh 930B
cours_4
data
fingerprints_str_T5.p 8.88MB
T7_machine_learning_student.ipynb 25KB
T5_compound_clustering_student.ipynb 34KB
T6_compound_mcs.ipynb 1.09MB
images
butina_full.pdf 289KB
growing.png 67KB
transition.png 34KB
query.png 16KB
mymols.png 33KB
ML_overview.png 26KB
FP_TP_fig.png 15KB
RF_example.png 48KB
ANN_wiki.png 46KB
seeds.png 18KB
T5_compound_clustering.ipynb 474KB
T7_machine_learning.ipynb 306KB
environment.yml 1KB
.gitignore 38B
README.md 9KB
纵向毕业季.bmp 2.79MB
共 87 条
- 1
资源评论
专家-百锦再
- 粉丝: 8562
- 资源: 731
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功