Man pages for GenomeNet/deepG
Deep Learning for Genome Sequence Data

auc_wrapper	Mean AUC score
balanced_acc_wrapper	Balanced accuracy metric
compile_model	Compile model
conf_matrix_cb	Confusion matrix callback.
create_dummy_data	Write random sequences to fasta file
create_model_genomenet	Create GenomeNet Model with Given Architecture Parameters
create_model_lstm_cnn	Create LSTM/CNN network
create_model_lstm_cnn_multi_input	Create LSTM/CNN network that can process multiple samples for...
create_model_lstm_cnn_target_middle	Create LSTM/CNN network to predict middle part of a sequence
create_model_lstm_cnn_time_dist	Create LSTM/CNN network for combining multiple sequences
create_model_transformer	Create transformer model
create_model_twin_network	Create twin network
crispr_sample	CRISPR data
dataset_from_gen	Collect samples from generator and store in rds or pickle...
deepG-package	deepG for GenomeNet
early_stopping_time_cb	Stop training callback
ecoli_small	Ecoli subset
evaluate_linear	Evaluate matrices of true targets and predictions from layer...
evaluate_model	Evaluates a trained model on fasta, fastq or rds files
evaluate_sigmoid	Evaluate matrices of true targets and predictions from layer...
evaluate_softmax	Evaluate matrices of true targets and predictions from layer...
exp_decay	Exponential Decay
f1_wrapper	F1 metric
focal_loss_multiclass	Focal loss for two or more labels
generator_dummy	Random data generator
generator_fasta_label_folder	Data generator for fasta/fasta files
generator_fasta_label_folder_wrapper	Generator wrapper
generator_fasta_label_header_csv	Data generator for fasta/fastq files and label targets
generator_fasta_lm	Language model generator for fasta/fastq files
generator_initialize	Initializes generators defined by...
generator_random	Randomly select samples from fasta files
generator_rds	Rds data generator
get_class_weight	Estimate frequency of different classes
get_generator	Wrapper for generator functions
get_output_activations	Get activation functions of output layers
get_start_ind	Computes start position of samples
heatmaps_integrated_grad	Heatmap of integrated gradient scores
integrated_gradients	Compute integrated gradients
int_to_n_gram	Encode sequence of integers to sequence of n-gram
layer_aggregate_time_dist_wrapper	Aggregation layer
layer_pos_embedding_wrapper	Layer for positional embedding
layer_pos_sinusoid_wrapper	Layer for positional encoding
layer_transformer_block_wrapper	Transformer block
load_cp	Load checkpoint
load_prediction	Read states from h5 file
loss_cl	Contrastive loss
merge_models	Merge two models
model_card_cb	Create model card
n_gram_dist	Get distribution of n-grams
n_gram_of_matrix	One-hot encoding matrix to n-gram encoding matrix
noisy_loss_wrapper	Loss function for label noise
one_hot_to_seq	Char sequence corresponding to one-hot matrix.
parenthesis	Parenthesis data
pipe	Pipe operator
plot_cm	Plot confusion matrix
plot_roc	Plot ROC
predict_model	Make prediction for nucleotide sequence or entries in...
predict_with_n_gram	Predict the next nucleotide using n-gram
remove_add_layers	Remove layers from model and add dense layers
remove_checkpoints	Remove checkpoints
reset_states_cb	Reset states callback
reshape_input	Replace input layer
reshape_tensor	Reshape tensors for set learning
resume_training_from_model_card	Continue training from model card
seq_encoding_label	Encodes integer sequence for label classification.
seq_encoding_lm	Encodes integer sequence for language model
sgdr	Stochastic Gradient Descent with Warm Restarts
split_fasta	Split fasta file into smaller files.
stepdecay	Step Decay
summarize_states	Create summary of predictions
train_model	Train neural network on genomic data
train_model_cpc	Train CPC inspired model
validation_after_training_cb	Validation after training callback