Upload data/feng-2024/zenodo-14025191-v2/README.md with huggingface_hub
Browse files
data/feng-2024/zenodo-14025191-v2/README.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Benchmarking of Machine Learning Methods for Predicting Synthetic Lethality Interactions
|
| 2 |
+
|
| 3 |
+
### Data Preparation and Download Instructions
|
| 4 |
+
|
| 5 |
+
After downloading data from this project, follow these steps to prepare the training data:
|
| 6 |
+
|
| 7 |
+
**Step 1:** Download all the data parts from the [](https://doi.org/10.5281/zenodo.13691648) provided in the repository.
|
| 8 |
+
|
| 9 |
+
> **Matters needing attention:**
|
| 10 |
+
>
|
| 11 |
+
> - The actual command will depend on how you're downloading files from Google Drive. For the convenience of downloading, the files have been compressed and split.
|
| 12 |
+
>
|
| 13 |
+
> - We have prepared two versions of data, namely the complete version (`data_large.tar.gz`) and the version without PiLSL database (`data_small.tar.gz`).
|
| 14 |
+
>
|
| 15 |
+
> - The decompressed size of the complete version is about 90GB, while the decompressed size of the version without PiLSL database is about 22GB.
|
| 16 |
+
>
|
| 17 |
+
> - (Due to the extremely time-consuming database construction process, it is recommended to download the complete version of the data.
|
| 18 |
+
> However, the data version without PiLSL database can successfully run all 10 models except PiLSL.)
|
| 19 |
+
|
| 20 |
+
**Step 2:** Combine the parts into a single archive.
|
| 21 |
+
|
| 22 |
+
```bash
|
| 23 |
+
cat data_large.tar.gz.part* > data_large.tar.gz # Complete version, the size after extracted is about 100GB.
|
| 24 |
+
# cat data_small.tar.gz.part* > data_small.tar.gz # The version without PiLSL database, the size after extracted is about 25GB.
|
| 25 |
+
```
|
| 26 |
+
**Step 3:** Verify the integrity of the downloaded files.
|
| 27 |
+
```bash
|
| 28 |
+
md5sum -c data_large.tar.gz.md5
|
| 29 |
+
# md5sum -c data_small.tar.gz.md5 # The version without PiLSL database
|
| 30 |
+
```
|
| 31 |
+
**Step 4:** Extract the dataset.
|
| 32 |
+
```bash
|
| 33 |
+
tar -xzvf data_large.tar.gz
|
| 34 |
+
# tar -xzvf data_small.tar.gz # The version without PiLSL database
|
| 35 |
+
```
|