Questions tagged [deep-learning]
The deep-learning tag has no summary.
20 questions
1 vote
1 answer
19 views
How can I improve ROC-AUC beyond 0.76 in predicting REST binding sites?
I'm working on a machine learning model to predict the binding of the transcription factor REST to candidate DNA binding sites for my final project in a bio-informatics course (McGill U, COMP561, ...
3 votes
1 answer
151 views
Low Memory Usage with DeepVariant
I am running DeepVariant on a c5.4xlarge instance on AWS EC2 with Ubuntu Server 24.04. I'm using htop to monitor my CPU and memory usage. During make_examples, I noticed that only 8GB of my 32GB of ...
3 votes
0 answers
41 views
Q8 Accuracy Evaluation metric mathematical expression used in Protein Secondary Structure Prediction
I am working on Protein Secondary Structure Prediction using Recurrent Neural Network (GRU) model. I came across few open source projects which already worked on the similar problem. All of them are ...
0 votes
0 answers
86 views
TCGA pathology slides magnification
Does anybody know if there is a way to find out what are the magnification levels of the TCGA pathology slides? Are they all 40x? I can't seem to find a label of that anywhere
1 vote
2 answers
676 views
Why does DNABert use overlapping k-mers as input?
I was reading through the DNABERT paper and found that their input features were k-mers. This is essentially using rolling window features. Why train a transformer-like model on sequences of the form ...
1 vote
2 answers
137 views
How many protein sequences do we usually have for each species?
My question is exactly the one in the title. I add a particular example for more clarity. If I want to study the sequence of protein IkBα, do I find only one sequence or is there a database that ...
1 vote
1 answer
90 views
Gene rank scores from LINCS database: Evangelista et al. 2022
The website https://maayanlab.cloud/sigcom-lincs/#/SignatureSearch/UpDown can be used to "Identify reversers and mimickers from over 1 million signatures by entering up and down gene sets .. &...
1 vote
1 answer
63 views
What options should I explore to improve the output of the protein reconstruction?
We developed a neural network-based protein reconstruction tool to reconstruct the main chain from only CA atoms. we generated data from some selected PDBs from the RCSB website to train an NN model. ...
5 votes
3 answers
2k views
Why can't AlphaFold predict the consequences of point-mutations?
In the literature, it specifically states that AlphaFold has "Has not been trained to predict structural consequences of point mutations". See : https://alphafold.com/faq AlphaFold has not ...
0 votes
0 answers
151 views
How can I convert protein distance maps and sequences to a pdb files?
How can I convert protein distance maps and sequences to pdb files? For the same problem, in the case of a model predicting the structure of a protein, such as AlphaFold, how do we convert the ...
1 vote
1 answer
59 views
Transfer learning for a Convolutional NN for Recursion dataset
As a practice data analysis I am trying to train a convolutional neural network (CNN) on some cellular images made publicly available on Kaggle in 2019 by the company Recursion via supervised deep ...
1 vote
1 answer
390 views
Reproducible PyTorch Model
I'm using PyTorch (1.7.1), PyTorch Geometric (1.6.3), NVIDIA Cuda (11.2). I need to make a neural network reproducible for a competition. However, when I try: ...
0 votes
0 answers
51 views
Build protein-protein interaction prediction deep learning model
I'm an undergraduate biology student and my thesis is on designing a deep learning architecture to predict whether two proteins interact or not given their primary sequences. I have read some papers ...
2 votes
1 answer
101 views
Important genes beyond PAM50 for breast cancer classification
Note: this question has also been asked on Biostars I am currently trying to complete a Breast Cancer Classification task using Neural Networks. I have experimented with using my full dataset of gene ...
1 vote
1 answer
56 views
how to get access to genotypes and phenotypes used for a GWAS
I'm a master's student working on genomic prediction of complex traits using deep learning. i'm looking for a dataset of human genotypes and phenotypes that has been used for a GWAS. The only thing i ...