README.md

metadata

tags:
  - dna
  - human_genome

WARNING

This readme should be changed according to current model. Num steps: 810000

GENA-LM

GENA-LM is a transformer masked language model trained on human DNA sequence.

Differences between GENA-LM and DNABERT:

• BPE tokenization instead of k-mers;
• input sequence size is about 3000 nucleotides (512 BPE tokens) compared to 510 nucleotides of DNABERT
• pre-training on T2T vs. GRCh38.p13 human genome assembly.

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

Examples

How to load the model to fine-tune it on classification task

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

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

Model description

GENA-LM model is trained in a masked language model (MLM) fashion, following the methods proposed in the BigBird paper by masking 85% of tokens. Model config for gena-lm-bert-base 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 using the latest T2T human genome assembly (https://www.ncbi.nlm.nih.gov/assembly/GCA_009914755.3/). Pre-training was performed for 500,000 iterations with the same parameters as in BigBird, except sequence length was equal to 512 tokens and we used pre-layer normalization in Transformer.

Downstream tasks

Currently, gena-lm-bert-base model has been finetuned and tested on promoter prediction task. Its' performance is comparable to previous SOTA results. We plan to fine-tune and make available models for other downstream tasks in the near future.

Fine-tuning GENA-LM on our data and scoring

After fine-tuning gena-lm-bert-base on promoter prediction dataset, following results were achieved:

model	seq_len (bp)	F1
DeePromoter	300	95.60
GENA-LM bert-base (ours)	2000	95.72
BigBird	16000	99.90

We can conclude that our model achieves comparable performance to the previously published results for promoter prediction task.