PlasmidLM

A 17.7M parameter autoregressive language model for plasmid DNA sequence generation, trained on ~108K plasmid sequences from Addgene.

Model Details

Property	Value
Parameters	17.7M
Architecture	Transformer decoder (dense MLP), LLaMA-style
Hidden size	384
Layers	10
Attention heads	8
Intermediate size	1,536
Max sequence length	16,384 tokens
Tokenizer	Character-level (single DNA bases)
Vocab size	120

Training

• Data: ~108K plasmid sequences from Addgene, annotated with functional components via pLannotate
• Steps: 15,000
• Eval loss: 0.093
• Token accuracy: 96.1%

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("McClain/PlasmidLM", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("McClain/PlasmidLM", trust_remote_code=True)

# Condition on antibiotic resistance + origin of replication
prompt = "<BOS><AMR_KANAMYCIN><ORI_COLE1><SEP>"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=4096, temperature=0.8, do_sample=True, top_p=0.95)
print(tokenizer.decode(outputs[0].tolist()))

The model generates plasmid DNA sequences conditioned on functional annotations (antibiotic resistance markers, origins of replication, promoters, reporters, etc.) provided as special tokens in the prompt.

Input Format

<BOS><TOKEN1><TOKEN2>...<SEP>

The model generates DNA bases (A/T/C/G) after the <SEP> token until it produces <EOS> or hits the maximum length.

Special Tokens

Token	Purpose
<BOS>	Beginning of sequence
<EOS>	End of sequence
<SEP>	Separator between prompt annotations and DNA sequence
<PAD>	Padding
<AMR_*>	Antibiotic resistance markers (e.g., <AMR_KANAMYCIN>, <AMR_AMPICILLIN>)
<ORI_*>	Origins of replication (e.g., <ORI_COLE1>, <ORI_P15A>)
<PROM_*>	Promoters (e.g., <PROM_CMV>, <PROM_T7>)
<REP_*>	Reporters (e.g., <REP_EGFP>, <REP_MCHERRY>)

Related Models

• McClain/PlasmidLM-kmer6 — kmer6 tokenizer, 19.3M params, dense
• McClain/PlasmidLM-kmer6-MoE — kmer6 tokenizer, 78.3M total params, Mixture-of-Experts

Limitations

• This is a pretrained base model -- generated sequences are not optimized for functional element placement. Post-training with RL improves fidelity.
• Generated sequences are not experimentally validated. Always verify computationally and experimentally before synthesis.
• Trained on Addgene plasmids, which are biased toward commonly deposited vectors.
• Maximum context of 16K tokens (~16 kbp).

Citation

@misc{thiel2026plasmidlm,
  title={PlasmidLM: Language Models for Plasmid DNA Generation},
  author={Thiel, McClain},
  year={2026}
}