LucaProt: A novel deep learning framework that incorporates protein amino acid sequence and structural information to predict protein function.

Efficient implementatin of ESM family.

Multi-target de novo molecular generator conditioned on AlphaFold's latent protein embeddings.

Nature Computational Science: Unbiased organism-agnostic and highly sensitive signal peptide predictor with deep protein language model

[AAAI 2025] CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction

We developed a dual-channel model named LucaPCycle, based on the raw sequence and protein language large models, to predict whether a protein sequence has phosphate-solubilizing functionality and its specific type among the 31 fine-grained functions.

LucaProt: A novel deep learning framework that incorporates protein amino acid sequence and structural information to predict protein function.

PLMFit platform for TL on PLMs

A book about Language/deep-learning models in Genomics.

Developing classification models for DNA-Binding proteins through machine learning and large language models

PPTStab: Designing of thermostable proteins with a desired melting temperature

Protein Diversification and Generation through Yielded mutations (Prodigy) Protein is an end-to-end platform for plug and play protein engineering

Collection of prediction models for biological tasks

TooT-PLM-ionCT: A bioinformatics framework utilizing protein language models for accurate classification of ion channels and ion transporters from membrane proteins.

Large language models for predicting ion channels modulating proteins

[Under Review] Implementation of Recursive Cleaning for Large-scale Protein Data via Multimodal Learning

Code for the manuscript "Application of Protein Structure Encodings and Sequence Embeddings for Transporter Substrate Prediction".

Exploring protein sequence generation of a target protein family using pretrained and fine-tuned protein language models (pLMs).

Assessing the applicability domain of protein language models trained on UniRef clusters using embedding-based similarity metrics