Machine Learning in Bioinformatics

Protein Function Prediction from Three-Dimensional Feature Representations Using Space-Filling Curves

The paper predicts enzyme substrate selectivity using space-filling curve-based structural representations of proteins, achieving high accuracy with gradient-boosted classifiers.

Markonv: a novel convolutional layer with inter-positional correlations modeled

The paper introduces Markonv, a convolutional layer that models inter-positional correlations using Markov transition matrices, showing effectiveness in analyzing omics data and decoding electrical signals.

mebipred: identifying metal-binding potential in protein sequences.

The paper introduces mebipred, a machine learning tool for predicting metal-binding proteins from sequence data, achieving 90% accuracy and outperforming existing methods.

CELL-E: Biological zero-shot text-to-image synthesis for protein localization prediction

CELL-E generates 2D probability density maps of protein localization using text-to-image transformers, avoiding discrete class annotations.

PepNN: a deep attention model for the identification of peptide binding sites

PepNN introduces deep attention models for predicting peptide binding sites on proteins using sequence and structural data, achieving high performance on benchmark tests.

The substrate scopes of enzymes: a general prediction model based on machine and deep learning

This paper introduces ESP, a machine learning model predicting enzyme-substrate pairs with over 90% accuracy, outperforming existing models for specific enzyme families.

LiGIoNs: A Computational Method for the Detection and Classification of Ligand-Gated Ion Channels

LiGIoNs is a pHMM-based method for detecting and classifying ligand-gated ion channels, outperforming existing methods and enabling subfamily classification.

Prediction of coronavirus 3C-like protease cleavage sites using machine-learning algorithms

This study develops a random forest model to predict coronavirus 3CL protease cleavage sites, achieving high accuracy on both viral and host protein datasets.

DeepGOZero: Improving protein function prediction from sequence and zero-shot learning based on ontology axioms

DeepGOZero improves protein function prediction by using ontology axioms and zero-shot learning to predict functions with few or no annotations.

DeepTMHMM predicts alpha and beta transmembrane proteins using deep neural networks

Combining an ESM-1b encoder with a conditional random field decoder, DeepTMHMM classifies alpha-helical and beta-barrel transmembrane proteins and their topology, outperforming most compared tools, including on signal-peptide cleavage sites.

ENNGene: an Easy Neural Network model building tool for Genomics

ENNGene is a tool that simplifies deep learning model building for genomics data, achieving state-of-the-art results on the RBP24 dataset by incorporating evolutionary conservation and custom network tuning.

ME-ACP: Multi-view Neural Networks with Ensemble Model for Identification of Anticancer Peptides

ME-ACP uses multi-view neural networks and ensemble models to identify anticancer peptides from protein sequences with competitive performance on evaluation metrics.

Predicting Residues Involved in Anti-DNA Autoantibodies with Limited Neural Networks

The paper uses LSTM and CNN models to predict DNA-binding sites in autoantibodies from primary sequences, finding that LSTM highlights sub-sequences correlated with binding sites.

Protein Language Model Performs Efficient Homology Detection

PLAST uses protein language models and discrete cosine transforms to efficiently detect homologs with high accuracy and speed.

Using Deep Learning to Annotate the Protein Universe

This paper uses deep learning to improve protein function annotation by training on Pfam data, achieving better accuracy and efficiency than BLASTp.

LazyPair: scalable prediction of protein-protein interactions and interaction types

LazyPair predicts protein-protein interactions and their types using random forests trained on residue properties, outperforming existing methods in accuracy and scalability.

EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning

EMBER predicts kinase-substrate phosphorylation events using a deep learning model that integrates motif and phylogeny information, improving phosphorylation network mapping.

An explainable unsupervised framework for alignment-free protein classification using sequence embeddings

This paper introduces an alignment-free protein classification framework using sequence embeddings to infer evolutionary relationships and functional motifs across diverse protein superfamilies.

Fine-Tuning Transformers For Genomic Tasks

This study evaluates Transformer models for genomic sequence classification, comparing pre-trained and from-scratch approaches on benchmark datasets.

Specific Peptides Predict Protein Classification.

The paper introduces a method to predict protein classification using specific peptides, achieving high precision and recall on enzyme sequences and applying it to GPCR and ZF families.

PIPENN: Protein Interface Prediction with an Ensemble of Neural Nets

The paper introduces an ensemble of deep learning models (PIPENNs) for predicting protein interface residues, showing improved performance over existing methods across different interaction types.

Machine Learning for the Identification of Viral Attachment Machinery from Respiratory Virus Sequences

This paper develops machine learning models to identify viral spike proteins and classify respiratory virus families from sequence data with high accuracy.

TooT-SC: Predicting Eleven Substrate Classes of Transmembrane Transport Proteins

TooT-SC predicts eleven substrate classes of transmembrane transport proteins using a combination of amino acid composition and evolutionary information, achieving high performance.

Enhancing the prediction of protein coding regions in biological sequence via a deep learningframework with hybrid encoding

This paper introduces a deep learning framework with hybrid encoding to improve protein coding region prediction in biological sequences, achieving better performance than existing methods.

ProtFinder: finding subcellular locations of proteins using protein interaction networks

ProtFinder predicts multiple subcellular locations of proteins using protein interaction networks and biological priors, achieving high accuracy on held-out data.

ProteinBERT: A universal deep-learning model of protein sequence and function

A ~16M-parameter protein language model, pretrained on ~106M UniRef90 proteins by denoising sequences and Gene Ontology annotations, rivals larger TAPE models using linear-cost global attention.

SignalP 6.0 achieves signal peptide prediction across all types using protein language models

SignalP 6.0 predicts all five types of signal peptides with improved accuracy and applies to metagenomic data.

ProteinPrompt: a webserver for predicting protein-protein interactions

ProteinPrompt predicts protein-protein interactions using machine learning, offering two methods and consensus predictions for reliable results.

Cross-attention PHV: Prediction of human and virus protein-protein interactions using cross-attention-based neural networks

The paper introduces cross-attention PHV, a computational predictor for human-virus protein-protein interactions, which outperforms existing models and accurately predicts interactions for unknown viruses.

Semi-supervised Retrieval of Functional Residues Through the Integration of Protein Language Models and Gene Ontology Data

The paper develops function-conditioned generative models to predict functionally important protein residues using Gene Ontology data and protein language models.