Machine Learning in Bioinformatics

GOProFormer: A Multi-modal Transformer Method for Gene Ontology Protein Function Prediction

This paper introduces GOProFormer, a transformer-based method for Gene Ontology protein function prediction, showing superior performance over existing methods and proposing a new benchmark dataset.

Nearest neighbor search on embeddings rapidly identifies distant protein relations

The paper explores using protein embeddings for nearest neighbor search to detect remote homology, highlighting challenges with multi-domain proteins and proposing solutions.

Prediction of RNA-interacting residues in a protein using CNN and evolutionary profile

The paper introduces Pprint2, a method using convolutional neural networks and evolutionary profiles to predict RNA-interacting residues in proteins, achieving an AUC of 0.82.

Contrastive learning of protein representations with graph neural networks for structural and functional annotations

PenLight improves protein annotation by integrating 3D structure and sequence data using graph neural networks and contrastive learning.

Using machine learning to predict quantitative phenotypes from protein and nucleic acid sequences

The paper uses machine learning to predict quantitative phenotypes like optimal growth temperature, pH, and oxygen tolerance from protein and nucleic acid sequences.

Succinylated lysine residue prediction revisited

The paper proposes deep learning models for predicting succinylated lysine residues using biochemical and physicochemical properties, achieving improved sensitivity and specificity through threshold tuning.

The geometry of hidden representations of protein language models

The paper analyzes the geometric properties of hidden representations in protein language models and identifies three distinct phases that reveal a general strategy for reconstructing missing data.

Learning deep representations of enzyme thermal adaptation

The paper trains a deep learning model to predict enzyme thermal adaptation using a dataset of enzymes labeled with optimal growth temperatures.

Computing wide range of protein/peptide features from their sequence and structure

The paper introduces a software package that computes over 50,000 features for protein/peptide function prediction, including residue-level annotations.

Automated Protein Function Description for NovelClass Discovery

This paper introduces a neural machine translation model to generate natural language descriptions of protein functions, enabling the discovery of novel functions beyond existing label spaces.

Optimal feature selection and software tool development for bacteriocin prediction

This work identifies optimal features and develops a machine learning tool for predicting bacteriocin sequences with high accuracy.

ProteinGLUE: A multi-task benchmark suite for self-supervised protein modeling.

The paper introduces ProteinGLUE, a benchmark suite for evaluating self-supervised protein models, showing pre-training improves downstream tasks but smaller models perform better than larger ones.

Alignment-free metal ion-binding site prediction from protein sequence through pretrained language model and multi-task learning

LMetalSite predicts metal ion-binding sites from protein sequences using a pretrained language model and multi-task learning, achieving higher accuracy than structure-based methods.

Refining Embedding-Based Binding Predictions by Leveraging AlphaFold2 Structures

The paper introduces bindAdjust, a method that improves binding predictions by incorporating structural information from AlphaFold2, enhancing recall for small molecule binding and expanding predictions to larger binding sites.

DistilProtBert: A distilled protein language model used to distinguish between real proteins and their randomly shuffled counterparts

The paper introduces DistilProtBert, a distilled version of ProtBert, which effectively distinguishes real proteins from shuffled sequences with high accuracy.

3-D structure based prediction of SUMOylation sites

The paper introduces a 3-D structure-based method to predict SUMOylation sites with 81% accuracy and a Matthews Correlation Coefficient of 0.4.

Predicting the specific substrate for transmembrane transport proteins using BERT language model

The paper uses a fine-tuned BERT model to predict specific substrates of transmembrane transport proteins with high accuracy.

Optimizing InterProScan feature processing generates a surprisingly good protein function prediction method

The paper tests preprocessing methods and classifiers for protein function prediction using InterProScan data, finding that preprocessing and stacking improve performance, outperforming CAFA3 competitors.

From proteins to nanoparticles: domain-agnostic predictions of nanoscale interactions.

This paper introduces NeCLAS, a machine learning pipeline that predicts nanoscale interactions across domains, outperforming existing models and showing cross-domain validity.

TMbed - Transmembrane proteins predicted through Language Model embeddings

TMbed predicts transmembrane regions using protein language model embeddings, achieving high accuracy and low false positives for proteome-wide analysis.

DBpred: A deep learning method for the prediction of DNA interacting residues in protein sequences

DBpred predicts DNA-interacting residues in proteins using deep learning, achieving improved AUROC scores compared to existing methods.

Accurate Prediction of Virus-Host Protein-Protein Interactions via a Siamese Neural Network Using Deep Protein Sequence Embeddings

This paper introduces a deep learning method called STEP to predict virus-host protein-protein interactions using protein sequence embeddings and a Siamese neural network, demonstrating its effectiveness on SARS-CoV-2 and JCV proteins.

DBP2Vec: Predicting DNA-binding proteins directly using pre-trained protein language model

DBP2Vec predicts DNA-binding proteins using a pre-trained protein language model, outperforming existing methods on benchmark datasets.

A Method for Computationally Constructing Eukaryotic Synthetic Signal Peptide Sequences

The paper presents a computational method to generate synthetic eukaryotic signal peptides using building blocks, validated by Signal-BLAST showing 88% of generated sequences were identified as signal peptides.

Multi-Head Attention-based U-Nets for Predicting Protein Domain Boundaries Using 1D Sequence Features and 2D Distance Maps

This paper introduces DistDom, a deep learning method that predicts protein domain boundaries using 1D sequence features and 2D distance maps, achieving higher accuracy than existing methods on CASP14 data.

Integrating Self-Attention Transformer with Triplet Neural Networks for Protein Gene Ontology Prediction

The paper introduces ATGO, a deep-learning method that improves Gene Ontology prediction for proteins using self-attention transformers and triplet networks, achieving higher accuracy than existing methods.

KinasePhos 3.0: Redesign and Expansion of the Prediction on Kinase-specific Phosphorylation Sites

KinasePhos 3.0 improves phosphorylation site prediction by expanding kinase classification and building 771 models, achieving average accuracy of 87.2%.

Protein sequence profile prediction using ProtAlbert transformer

This paper predicts protein sequence profiles using a ProtAlbert transformer without alignment, showing high similarity to HSSP profiles.

OrganelX Web Server for Sub-Peroxisomal and Sub-Mitochondrial protein localisation

The paper introduces a web server with three algorithms for predicting sub-peroxisomal and sub-mitochondrial protein localisation and PTS1 signals, aiming to accelerate research in peroxisomal biology.

Deep embeddings to comprehend and visualize microbiome protein space

The paper uses a deep learning model to represent microbial proteins for alignment-free analysis and visualization, showing it can capture structural and functional features.