metadata

tags:
  - dna
  - human_genome

GENA-LM (gena-lm-bert-base-t2t)

GENA-LM is a Family of Open-Source Foundational Models for Long DNA Sequences.

GENA-LM models are transformer masked language models trained on human DNA sequence.

Differences between GENA-LM (gena-lm-bert-base-t2t) and DNABERT:

BPE tokenization instead of k-mers;
input sequence size is about 4500 nucleotides (512 BPE tokens) compared to 512 nucleotides of DNABERT
pre-training on T2T vs. GRCh38.p13 human genome assembly.

Source code and data: https://github.com/AIRI-Institute/GENA_LM

Paper: https://www.biorxiv.org/content/10.1101/2023.06.12.544594

This repository also contains models that are finetuned on downstream tasks:

promoters predictions (branch promoters_300_run_1)
splice sites prediction (branch spliceai_run_1)
epigenetic features and gene expression (trained on enformer dataset, branch enformer)

and models that are used in our GENA-Web web tool for genomic sequence annotation:

deepsea (gena_web_deepsea, branch gena_web_deepsea)
deepstarr (gena_web_deepstarr, branch gena_web_deepstarr)

Examples

How to load pre-trained model for Masked Language Modeling

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained('AIRI-Institute/gena-lm-bert-base-t2t')
model = AutoModel.from_pretrained('AIRI-Institute/gena-lm-bert-base-t2t', trust_remote_code=True)

How to load pre-trained model to fine-tune it on classification task

Get model class from GENA-LM repository:

git clone https://github.com/AIRI-Institute/GENA_LM.git

from GENA_LM.src.gena_lm.modeling_bert import BertForSequenceClassification
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('AIRI-Institute/gena-lm-bert-base-t2t')
model = BertForSequenceClassification.from_pretrained('AIRI-Institute/gena-lm-bert-base-t2t')

or you can just download modeling_bert.py and put it close to your code.

OR you can get model class from HuggingFace AutoModel:

from transformers import AutoTokenizer, AutoModel
model = AutoModel.from_pretrained('AIRI-Institute/gena-lm-bert-base-t2t', trust_remote_code=True)
gena_module_name = model.__class__.__module__
print(gena_module_name)
import importlib
# available class names:
# - BertModel, BertForPreTraining, BertForMaskedLM, BertForNextSentencePrediction,
# - BertForSequenceClassification, BertForMultipleChoice, BertForTokenClassification,
# - BertForQuestionAnswering
# check https://huggingface.co/docs/transformers/model_doc/bert
cls = getattr(importlib.import_module(gena_module_name), 'BertForSequenceClassification')
print(cls)
model = cls.from_pretrained('AIRI-Institute/gena-lm-bert-base-t2t', num_labels=2)

Model description

GENA-LM (gena-lm-bert-base-t2t) model is trained in a masked language model (MLM) fashion, following the methods proposed in the BigBird paper by masking 15% of tokens. Model config for gena-lm-bert-base-t2t is similar to the bert-base:

512 Maximum sequence length
12 Layers, 12 Attention heads
768 Hidden size
32k Vocabulary size

We pre-trained gena-lm-bert-base-t2t using the latest T2T human genome assembly (https://www.ncbi.nlm.nih.gov/assembly/GCA_009914755.3/). The data was augmented by sampling mutations from 1000-genome SNPs (gnomAD dataset). Pre-training was performed for 2,100,000 iterations with batch size 256 and sequence length was equal to 512 tokens. We modified Transformer with Pre-Layer normalization, but without the final layer LayerNorm.

Evaluation

For evaluation results, see our paper: https://www.biorxiv.org/content/10.1101/2023.06.12.544594v1

Citation

@article{GENA_LM,
    author = {Veniamin Fishman and Yuri Kuratov and Maxim Petrov and Aleksei Shmelev and Denis Shepelin and Nikolay Chekanov and Olga Kardymon and Mikhail Burtsev},
    title = {GENA-LM: A Family of Open-Source Foundational Models for Long DNA Sequences},
    elocation-id = {2023.06.12.544594},
    year = {2023},
    doi = {10.1101/2023.06.12.544594},
    publisher = {Cold Spring Harbor Laboratory},
    URL = {https://www.biorxiv.org/content/early/2023/06/13/2023.06.12.544594},
    eprint = {https://www.biorxiv.org/content/early/2023/06/13/2023.06.12.544594.full.pdf},
    journal = {bioRxiv}
}