My Research
Translating the Language of Life
PhD Researcher - ENSI Manouba - 2023 - Present
Life2Lang
A sequence-to-sequence protein language model bridging sequence understanding and generation, currently in resubmission to ISMB/ECCB, a Bioinformatics journal, and NeurIPS GenBio.
UniprotKG
Structured UniProt into a queryable biomedical knowledge graph to power instruction-dataset construction for LLM fine-tuning.
Eshmun
A controlled tokenizer ablation on a 120M-parameter causal language model trained on SwissProt sequences, comparing amino-acid-level vs. 10K/20K/32K BPE vocabularies to isolate the effect of domain-specific vocabulary design on downstream protein tasks.
Designing a chain-of-thought pretraining signal grounded in static biophysical features, plus a reinforcement-learning stage with structural/functional reward models.
Eshmun-R1
Distilled a 1.3B-parameter teacher (InstructProtein) into a 400M-parameter student via alternating layer extraction (6L-ALT), then fine-tuned on a 212K-example in-house instruction dataset built from SwissProt.
Ran GRPO (RLVR) on the SFT checkpoint with a composite verifiable reward - format gate, PSIPRED-based secondary-structure correctness, and a Gaussian length penalty - on Colab Pro A100.
Research Objectives
- Develop protein language models that unify sequence understanding and generation
- Build structured knowledge resources (UniprotKG) to support LLM fine-tuning on biological data
- Study how domain-specific tokenization and vocabulary design affect downstream protein tasks
- Apply reasoning-oriented post-training (chain-of-thought, RLVR) grounded in biophysical and structural reward signals
Publications
- Abidi K., Inoubli W., Mephu Nguifo E. - "DGCN: Learning Graph Representations Via Dense Connections," Procedia Computer Science, Vol. 225, 2023, pp. 951-960. doi.org/10.1016/j.procs.2023.10.082