SaeedLab/SeqScreen-lora

SeqScreen - ESM2 LoRA Adapter

This repository contains the LoRA adapter weights for the protein encoder used in SeqScreen, trained on filtered ChEMBL. SeqScreen is a sequence-based virtual screening method built on a dual-encoder contrastive architecture. The adapter fine-tunes ESM2 T36 on protein-molecule interaction task.

The projection layers are available separately at SaeedLab/SeqScreen-Finetuning, which also contains the full model description, architecture diagram, and usage examples.

[Github Repo] | [Dataset on HuggingFace] | [Model Collection] | [Cite]

Abstract

Virtual screening aims to identify candidate molecules that bind to a target protein, playing a central role in computational drug discovery. Sequence-based deep learning methods offer an applicable alternative to structure-based approaches, but typically process one protein-molecule pair at a time, limiting their scalability to large molecular libraries. Contrastive learning methods inspired by CLIP have shown promise for learning joint protein-molecule representations, but standard CLIP training was designed for symmetric tasks and does not account for the asymmetric and one-to-many nature of protein-molecule binding. In this paper, we introduce SeqScreen, a sequence-based virtual screening method built on a dual-encoder contrastive architecture. SeqScreen introduces a protein-centric batch construction strategy and an asymmetric multi-positive InfoNCE loss to cope with the protein-centric nature of virtual screening. We conduct a systematic evaluation across 8 protein language models and 3 molecular language model variants. The protein-centric batch construction consistently outperforms standard CLIP training across all evaluated encoders, while requiring approximately 32 times fewer training epochs and 7 times fewer forward passes during inference compared to pair-based methods. On the LIT-PCBA dataset, SeqScreen outperforms all sequence-based baselines, achieving a relative improvement of up to 39% in EF at 0.5 over the best competing method, while remaining competitive with traditional docking approaches without requiring 3D structural information.

Model Details

This adapter corresponds to the SeqScreen-Finetuning configuration, in which ESM2 T36 is fine-tuned via LoRA alongside the projection layers. Two configurations are available in this collection:

• SeqScreen-Frozen: only the projection layers are trained, both encoders are frozen.
• SeqScreen-Finetuning: the projection layers and ESM2 T36 are trained via LoRA, MolDeBERTa MLC is frozen.

Field	Value
Base model	facebook/esm2_t36_3B_UR50D
Adapter type	LoRA
Target modules	query, key, value
LoRA rank (r)	16
LoRA alpha	32
LoRA dropout	0.05
Task type	FEATURE_EXTRACTION

Usage

This adapter must be used together with SaeedLab/SeqScreen-Finetuning, which provides the projection layers. The full usage example, including molecule encoding and similarity computation, is available in that repository.

Dependencies

pip install transformers peft torch

Citation

The paper is under review. As soon as it is accepted, we will update this section.

License

This model and associated code are released under the CC-BY-NC-ND 4.0 license and may only be used for non-commercial, academic research purposes with proper attribution. Any commercial use, sale, or other monetization of this model and its derivatives, which include models trained on outputs from the model or datasets created from the model, is prohibited and requires prior approval. Downloading the model requires prior registration on Hugging Face and agreeing to the terms of use. By downloading this model, you agree not to distribute, publish or reproduce a copy of the model. If another user within your organization wishes to use the model, they must register as an individual user and agree to comply with the terms of use. Users may not attempt to re-identify the deidentified data used to develop the underlying model. If you are a commercial entity, please contact the corresponding author.

Contact

For any additional questions or comments, contact Fahad Saeed (fsaeed@fiu.edu).