prescient-design/lobster
Jan 2025 – Feb 2025
2 Months active
Languages Used
PDBPythonJinja
Technical Skills
Antibody EngineeringBioinformaticsPDB File ManipulationProtein Structure AnalysisPyTorchPython
Frédéric Dreyer
PROFILE
Frédéric Dreyer
Frederic Dreyer contributed to the prescient-design/lobster repository by developing two core features over a two-month period, focusing on antibody modeling and protein language model integration. He built the Predict Fv PDB Formatter, a Python-based tool that processes antibody variable fragment structures, ensuring correct chain identifiers and residue numbering for downstream modeling. Dreyer also integrated the ESMSC-small model into LobsterPMLM, enabling support for Synthyra/ESMplusplus_small with optional bfloat16 precision and a new dataset embedding method. His work leveraged skills in PyTorch, bioinformatics, and deep learning, delivering robust, well-tested solutions that improved model compatibility and workflow reliability.
Overall Statistics
Feature vs Bugs
100%Features
Repository Contributions
2Total
Bugs
0
Commits
2
Features
2
Lines of code
1,969
Activity Months2
Your Network
33 people
Work History
February 2025
1 Commits • 1 Features
Feb 1, 2025February 2025 — Prescient Design Lobster: Implemented ESMSC-small model integration in LobsterPMLM, enabling loading and utilization of Synthyra/ESMplusplus_small, optional bfloat16 precision, and a new dataset embedding method. Adjustments were made to accommodate the ESMSC-small model type. A minimal ESMSC-small implementation was delivered (commit 0d0285628ee2fa0065a9fadce646a8036f2ed9c5) (#37). This work broadens model compatibility, accelerates experimentation, and enhances embedding quality for downstream tasks.
1 Commits • 1 Features
Feb 1, 2025February 2025 — Prescient Design Lobster: Implemented ESMSC-small model integration in LobsterPMLM, enabling loading and utilization of Synthyra/ESMplusplus_small, optional bfloat16 precision, and a new dataset embedding method. Adjustments were made to accommodate the ESMSC-small model type. A minimal ESMSC-small implementation was delivered (commit 0d0285628ee2fa0065a9fadce646a8036f2ed9c5) (#37). This work broadens model compatibility, accelerates experimentation, and enhances embedding quality for downstream tasks.
February 2025
January 2025
1 Commits • 1 Features
Jan 1, 2025January 2025 monthly summary for prescient-design/lobster focusing on feature delivery and code quality improvements in the antibody modeling pipeline.
January 2025
1 Commits • 1 Features
Jan 1, 2025January 2025 monthly summary for prescient-design/lobster focusing on feature delivery and code quality improvements in the antibody modeling pipeline.
Activity
Loading activity data...
Quality Metrics
Correctness85.0%
Maintainability80.0%
Architecture85.0%
Performance70.0%
AI Usage20.0%
Skills & Technologies
Programming Languages
JinjaPDBPython
Technical Skills
Antibody EngineeringBioinformaticsDeep LearningHugging Face TransformersMachine LearningNatural Language ProcessingPDB File ManipulationProtein Structure AnalysisPyTorchPython
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline