Model description

Click to expand

This is a random forest classifier capable of predicting whether a given pair of transcriptscome from the same gene or not. It is trained on a dataset derived from ensembl transcripts, and is being evaluated on transcripts from the same sources, and others such as FlyBase

How to Get Started with the Model

[More Information Needed]

Model Card Authors

Click to expand

Andrew Green (afg1)

Model Card Contact

You can contact the model card authors through following channels: [More Information Needed]

Citation

Below you can find information related to citation.

BibTeX:

[More Information Needed]

Intended uses & limitations

Click to expand

This model is experimental, and is undergoing further testing.

Five-fold cross validation

We test the model on a random subset of the transcript pairs processed from all our coordinate data. These metrics represent the performance on the binary classification task of 'do these two transcripts come from the same gene'

fold	balanced_acc	F1	auc	ap
0	0.970089	0.989711	0.995063	0.998216
1	0.968053	0.98935	0.994941	0.998181
2	0.970278	0.989625	0.995177	0.998239
3	0.968382	0.989364	0.994861	0.998184
4	0.968858	0.989405	0.994907	0.997969