Machine Learning in Bioinformatics

Fast-Part: Fast and Accurate Data Partitioning for Biological Sequence Analysis

Fast-Part partitions biological sequence data efficiently while maintaining homology separation and stratification ratios.

Predicting the subcellular location of prokaryotic proteins with DeepLocPro

DeepLocPro is a subcellular location predictor for prokaryotic proteins, outperforming PSORTb 3.0 on benchmark metrics using experimentally verified data.

FAPM: Functional Annotation of Proteins using Multi-Modal Models Beyond Structural Modeling

FAPM improves protein functional annotation by combining protein sequence and language models, outperforming sequence-only methods on benchmarks and phage proteins with few homologs.

Distilling structural representations into protein sequence models

The paper introduces ISM, a sequence-only model that improves upon ESM2 by incorporating structural information, achieving better performance on mutation stability and structure prediction tasks.

PLM-interact: extending protein language models to predict protein-protein interactions

PLM-interact improves PPI prediction by jointly encoding protein pairs, achieving 16-28% AUPR gains across multiple species.

InterLabelGO+: Unraveling label correlations in protein function prediction

InterLabelGO+ improves protein function prediction by combining deep learning and alignment-based methods with a novel loss function and dynamic weighting, achieving strong performance in the CAFA5 challenge.

FastProtein: An automated software for in silico proteomic analysis

FastProtein is an open-source proteomics analysis tool that automates in silico protein property prediction and annotation, providing a user-friendly interface for both small and large-scale studies.

Hybrid Transformer and Neural NetworkConfiguration for Protein Classification UsingAmino Acids

This paper introduces a hybrid machine learning model for protein classification using amino acids, achieving 95% accuracy and outperforming existing methods by 15%.

Bacterial protein function prediction via multimodal deep learning

DeepEST predicts bacterial protein functions using a multimodal deep learning framework combining gene expression, localization, and structure data, outperforming existing methods on a 25-species benchmark.

Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers

This paper introduces LC-PLM, a protein language model based on BiMamba-S architecture, showing improved performance on protein tasks compared to Transformer-based models.

Preprocessing homologous regions in annotated protein sequences concerning machine-learning applications

This paper introduces two tools, HAM and HAC, to preprocess protein sequences by masking homologous regions and resolving annotation conflicts, improving machine learning model integrity.

Improving the prediction of protein stability changes upon mutations by geometric learning and a pre-training strategy

The paper introduces three geometric learning models for predicting protein stability changes upon mutations, achieving improved performance over existing methods.

SpatialPPI 2.0: Enhancing Protein-Protein Interaction Prediction through Inter-Residue Analysis in Graph Attention Networks

SpatialPPI 2.0 predicts protein-protein interactions using graph neural networks and inter-residue analysis, outperforming existing methods and working with AlphaFold-predicted structures.

Integration of protein and coding sequences enables mutual augmentation of the language model

This paper introduces a dual-language foundation model that integrates protein and coding sequences, showing improved performance in discriminative tasks and generating coding sequences with higher protein yield.

Pre-training with a rational approach for antibody sequence representation

This study introduces PARA, a pre-trained model for antibody sequences that outperforms existing models on various tasks by incorporating antibody-specific features.

A Framework for Accurate Prediction of Plastic-Degrading Enzymes using Convolutional Neural Networks

This paper develops a CNN-based framework to predict plastic-degrading enzymes from environmental sequences, achieving high accuracy and F1 score.

BBATProt: A Framework Predicting Biological Function with Enhanced Feature Extraction via Explainable Deep Learning

BBATProt predicts protein and peptide functions using explainable deep learning, outperforming existing models in hydrolytic catalysis, peptide activity, and post-translational modification site prediction.

Bridging biomolecular modalities for knowledge transfer in bio-language models

This paper adapts DNA and protein bio-language models for mRNA-focused tasks through various finetuning techniques, showing that medium-scale models perform best for cross-modal knowledge transfer.

Exploring Protein-DNA Binding Residue Prediction and Consistent Interpretability Analysis Using Deep Learning

This study introduces a sequence-based deep learning method for predicting DNA-binding residues, outperforming existing models and demonstrating interpretability through contrastive learning and graph neural networks.

Sitetack: A Deep Learning Model that Improves PTM Predictionby Using Known PTMs

The paper introduces a deep learning model that improves PTM prediction by incorporating known PTM sites into the training process, resulting in better performance than existing models.

Recursive Cleaning for Large-scale Protein Data via Multimodal Learning

The paper introduces ProtAC, a framework for cleaning large protein datasets using multimodal learning, achieving improved function prediction and a cleaned UniRef50 dataset.

ProteinAligner: A Multi-modal Pretraining Framework for Protein Foundation Models

ProteinAligner improves protein function and property prediction by integrating sequence, structure, and literature text modalities in a multi-modal pretraining framework.

How to select the best zero-shot model for the viral proteins?

This paper introduces ProPEC, a perplexity-based ensemble model for zero-shot prediction of viral protein fitness, showing improved performance over individual models.

pLM-DBPs: Enhanced DNA-Binding Protein Prediction in Plants Using Embeddings From Protein Language Models

The paper develops pLM-DBPs, a tool for predicting DNA-binding proteins in plants using protein language model embeddings, achieving 83.8% MCC on an independent test set.

BioLLMNet: Enhancing RNA-Interaction Prediction with a Specialized Cross-LLM Transformation Network

BioLLMNet improves RNA-interaction prediction by combining multi-modal language model features using a gating mechanism, achieving state-of-the-art results in RNA-protein, RNA-small molecule, and RNA-RNA interactions.

Unlearning Virus Knowledge Toward Safe and Responsible Mutation Effect Predictions

This paper introduces PROEDIT, a method to remove virus-related knowledge from pre-trained protein models to improve safety in mutation effect predictions without affecting performance on non-virus proteins.

Recurrent Neural Network-based Prediction of O-GlcNAcylation Sites in Mammalian Proteins

The paper develops RNN and MLP models to predict O-GlcNAcylation sites in mammalian proteins, achieving significantly better performance metrics than previous models.

Pair-EGRET: enhancing the prediction of protein-proteininteraction sites through graph attention networks and protein language models

Pair-EGRET predicts protein-protein interaction sites using graph attention networks and protein language models, outperforming existing methods on experimental data.

Allo-Allo: Data-efficient prediction of allosteric sites

Allo-Allo predicts allosteric sites using a data-efficient sequence-based method, achieving higher performance than existing approaches and showing translational potential in disease risk association.

MetalPrognosis: a Biological Language Model-based Approach for Disease-Associated Mutations in Metal-Binding Site prediction

MetalPrognosis predicts disease-associated mutations in metal-binding sites using a biological language model and convolutional neural network, outperforming existing methods.