Deep learning and neural network articles

[krassowski]

@vd4mmind I know that you already taken care of the DL/ML methods, but as promised here are some methods to check out:

title	journal	link	Journal Rank	Type
AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics.	Bioinformatics (Oxford, England)	https://doi.org/10.1093/bioinformatics/btaa442	484	Computational method
Enhancing the prediction of disease-gene associations with multimodal deep learning.	Bioinformatics (Oxford, England)	https://doi.org/10.1093/bioinformatics/btz155	484	Computational method
MOLI: multi-omics late integration with deep neural networks for drug response prediction.	Bioinformatics (Oxford, England)	https://doi.org/10.1093/bioinformatics/btz318	484	Computational method
Quantifying functional impact of non-coding variants with multi-task Bayesian neural network.	Bioinformatics (Oxford, England)	https://doi.org/10.1093/bioinformatics/btz767	484	Computational method
iSOM-GSN: An Integrative Approach for Transforming Multi-omic Data into Gene Similarity Networks via Self-organizing Maps.	Bioinformatics (Oxford, England)	https://doi.org/10.1093/bioinformatics/btaa500	484	Computational method
Evaluation of colorectal cancer subtypes and cell lines using deep learning.	Life science alliance	https://doi.org/10.26508/lsa.201900517	2050	Computational method
Learning representations of microbe-metabolite interactions.	Nature methods	https://doi.org/10.1038/s41592-019-0616-3	15	Other research article

[vd4mmind]

Hi @krassowski ,

Cool table. I didn’t know iSOM-GSN and AITL.

Some methods in the above mentioned tables are there in the MS already. I have to go through the SOM variant. Didn’t know there is one for multi-Omics. But for now we have both ML and DL based mentioned. If we want to include more, let me know.

[krassowski]

I guess inclusion of more of these would not be desired given the word limit... Unless we will need to for into the current opinions/trend guidelines - then it warrants discussion of the new ones form the above (with NN being an emerging/recently popular group of methods)