BENCHmark for drug Screening with COllaborative FIltering (benchscofi) Python Package

This repository is a part of the EU-funded RECeSS project (#101102016), and hosts the implementations and / or wrappers to published implementations of collaborative filtering-based algorithms for easy benchmarking.

Statement of need

As of 2022, current drug development pipelines last around 10 years, costing $2billion in average, while drug commercialization failure rates go up to 90%. These issues can be mitigated by drug repurposing, where chemical compounds are screened for new therapeutic indications in a systematic fashion. In prior works, this approach has been implemented through collaborative filtering. This semi-supervised learning framework leverages known drug-disease matchings in order to recommend new ones.

There is no standard pipeline to train, validate and compare collaborative filtering-based repurposing methods, which considerably limits the impact of this research field. In benchscofi, the estimated improvement over the state-of-the-art (implemented in the package) can be measured through adequate and quantitative metrics tailored to the problem of drug repurposing across a large set of publicly available drug repurposing datasets.

Install the latest release

The fastest way to get access to all functionalities of benchscofi is to run the following command:

## Using the Docker image: will open a container
docker push recessproject/benchscofi:1.0.1

Documentation about benchscofi (and a manual installation) can be found at this page. The complete list of dependencies for benchscofi can be found at requirements.txt (pip).

Licence

This repository is under an OSI-approved MIT license.

Citation

If you use benchscofi in academic research, please cite it as follows

Réda, Clémence, Jill-Jênn Vie, and Olaf Wolkenhauer. "A new standard for drug repurposing by collaborative filtering: stanscofi and benchscofi." (2023).

Community guidelines with respect to contributions, issue reporting, and support

You are more than welcome to add your own algorithm to the package!

1. Add a novel implementation / algorithm

Add a new Python file (extension .py) in src/benchscofi/ named <model> (where model is the name of the algorithm), which contains a subclass of stanscofi.models.BasicModel which has the same name as your Python file. At least implement methods preprocessing, model_fit, model_predict_proba, and a default set of parameters (which is used for testing purposes). Please have a look at the placeholder file Constant.py which implements a classification algorithm which labels all datapoints as positive. It is highly recommended to provide a proper documentation of your class, along with its methods. When pushing a new algorithm to benchscofi, it is automatically tested (see tests/test_models.py and TemplateTest.py which are run). In order to run this test locally, please run in the tests/ folder:

python3 -m test_models <model> <dataset:default=Synthetic>

2. Rules for contributors

Pull requests and issue flagging are welcome, and can be made through the GitHub interface. Support can be provided by reaching out to recess-project[at]proton.me. However, please note that contributors and users must abide by the Code of Conduct.

Benchmark AUC and NDCG@items values (default parameters, single random training/testing set split) [updated 08/11/23]

These values (rounded to the closest 3rd decimal place) can be reproduced using the following command in folder tests/

python3 -m test_models <algorithm> <dataset:default=Synthetic> <batch_ratio:default=1>

:no_entry:'s represent failure to train or to predict. N/A's have not been tested yet. When present, percentage in parentheses is the considered value of batch_ratio (to avoid memory crash on some of the datasets). [mem]: memory crash [err]: error

The NDCG score is computed across all diseases (global), at k=#items.

:no_entry: Note that results from ``LibMFWrapper'' are not reproducible, and the resulting metrics might slightly vary across iterations.

:no_entry: XGBoost and SimpleBinaryClassifier do not take into account unlabeled points (they assume they are negative points).

Datasets

*Synthetic dataset created with function generate_dummy_dataset in stanscofi.datasets and the following arguments:

npositive=200 #number of positive pairs
nnegative=100 #number of negative pairs
nfeatures=50 #number of pair features
mean=0.5 #mean for the distribution of positive pairs, resp. -mean for the negative pairs
std=1 #standard deviation for the distribution of positive and negative pairs
random_seed=124565 #random seed

[a] Réda, Clémence. (2023). TRANSCRIPT drug repurposing dataset (2.0.0) [Data set]. Zenodo. doi:10.5281/zenodo.7982976

[b] Gottlieb, A., Stein, G. Y., Ruppin, E., & Sharan, R. (2011). PREDICT: a method for inferring novel drug indications with application to personalized medicine. Molecular systems biology, 7(1), 496.

[c] Luo, H., Li, M., Wang, S., Liu, Q., Li, Y., & Wang, J. (2018). Computational drug repositioning using low-rank matrix approximation and randomized algorithms. Bioinformatics, 34(11), 1904-1912.

[d] Réda, Clémence. (2023). PREDICT drug repurposing dataset (2.0.1) [Data set]. Zenodo. doi:10.5281/zenodo.7983090

[e] Liang, X., Zhang, P., Yan, L., Fu, Y., Peng, F., Qu, L., … & Chen, Z. (2017). LRSSL: predict and interpret drug–disease associations based on data integration using sparse subspace learning. Bioinformatics, 33(8), 1187-1196.