mistral-7b-drug-prots_pair

PharMistral · Stage II

The final PharMistral model: given a raw protein sequence it generates candidate ligands, with no target-specific retraining and no structural input. On held-out targets it produced 99.5% chemically valid molecules, 57% of them unique.

From PharMistral: Drug generation for novel protein targets by Mistral Large Language Model (Computer Methods and Programs in Biomedicine Update, 2026). Code: PharMistral.

Training

Stage II of a two-stage process on Mistral-7B: joint pre-training on unpaired protein and small-molecule sequences, then sequence-conditioned fine-tuning on high-affinity protein–ligand pairs from ChEMBL-26. Sequence length 1,500, batch size 4 × 4 gradient-accumulation steps on 4 GPUs, learning rate 5e-5 with cosine decay, fill-in-the-middle rate 0.5. Use the matching tokenizer drug-prot-tokenizer-v2-mistral. Training scripts: GitHub.

Artifacts from this paper

Artifact
mistral-7b-drug-prots	Stage I: Mistral-7B after joint pre-training on protein sequences and small molecules
mistral-7b-drug-prots_pair	Stage II: the final sequence-conditioned model
drug-prot-tokenizer-v2-mistral	Tokenizer used for both stages
Protein-drug-v2	Stage I data: unpaired protein and small-molecule sequences
Protein-drug-pair-v2	Stage II data: high-affinity protein–ligand pairs from ChEMBL-26

Intended use

Research use only. Generated molecules are computational hypotheses: they have not been synthesised or tested experimentally, and they require the usual medicinal-chemistry, safety and regulatory evaluation before any practical use.

Citation

@article{bendjeddou2026pharmistral,
  title   = {PharMistral: Drug generation for novel protein targets by Mistral Large Language Model},
  author  = {Asma Bendjeddou and Kamyar Zeinalipour and Dalal Bardou and Marco Maggini and Franco Scarselli and Monica Bianchini},
  journal = {Computer Methods and Programs in Biomedicine Update},
  volume  = {10},
  pages   = {100257},
  year    = {2026},
  doi     = {10.1016/j.cmpbup.2026.100257}
}