Machine Learning in Bioinformatics

DRPBind: prediction of DNA, RNA and protein binding residues in intrinsically disordered protein sequences

DRPbind predicts DNA, RNA, and protein-binding residues in disordered protein sequences using SVM and features from evolutionary, physicochemical, and structural data.

PromoR and PromoS for E. coli promoter recognition and classification

This study introduces two models, PromoR and PromoS, for promoter recognition and classification in E. coli, achieving accuracies of 0.887 and 0.781 respectively.

Evaluating Tuning Strategies for Sequence Generation with Protein Language Models

This paper evaluates prompt tuning as a cost-efficient alternative to fine-tuning protein language models for sequence generation, finding it more efficient in resource usage but less effective than fine-tuning in sequence quality.

ProteInfer: deep networks for protein functional inference

ProteInfer uses deep convolutional neural networks to predict protein functions from amino acid sequences, offering efficient and accurate predictions with a lightweight software interface.

MsPBRsP: Multi-scale Protein Binding Residues Prediction Using Language Model

MsPBRsP predicts protein binding residues using a language model without MSA tools, achieving higher accuracy and faster performance than existing methods.

Retrieved Sequence Augmentation for Protein Representation Learning

This paper introduces a method to improve protein representation learning by retrieving and integrating similar sequences without alignment, achieving faster and more accurate predictions than traditional methods.

HMMSTRTM: A hidden Markov model for local structure prediction in globular and membrane associated proteins

HMMSTRTM predicts transmembrane protein topology using a Hidden Markov Model, achieving high accuracy in residue prediction.

GO Bench: Shared-hub for Universal Benchmarking of Machine Learning-Based Protein Functional Annotations

GO Bench provides a benchmarking hub for evaluating machine learning models in protein function annotation using Gene Ontology terms.

On Pre-trained Language Models for Antibody

The paper evaluates pre-trained language models for antibody tasks, introduces an evaluation benchmark, and investigates their performance and benefits in real-world applications.

Protein Representation Learning via Knowledge Enhanced Primary Structure Modeling

The paper introduces KeAP, a knowledge-enhanced auto-encoder for protein representation learning that outperforms existing methods on multiple downstream tasks.

DeepBIO is an automated and interpretable deep-learning platform for biological sequence prediction, functional annotation, and visualization analysis

DeepBIO is a deep-learning platform that automates biological sequence analysis, offering 42 algorithms and visualization tools for functional prediction and annotation.

A hybrid approach for predicting multi-label subcellular localization of mRNA at genome scale

This paper develops a fast method for predicting multi-label subcellular localization of mRNA at genome scale, achieving high AUROC scores using hybrid techniques.

Ankh : Optimized Protein Language Model Unlocks General-Purpose Modelling

Protein-specific tuning of masking, depth and positional embeddings, rather than more parameters, yields an encoder-decoder model that tops structure and function benchmarks at a fraction of the compute.

ISPRED-SEQ: Deep neural networks and embeddings for predicting interaction sites in protein sequences.

ISPRED-SEQ predicts protein-protein interaction sites from sequences using deep neural networks and outperforms existing methods.

Ensemble Machine Learning to Boost Ubiquitination-sites Prediction

This study compares ensemble and non-ensemble machine learning methods for predicting ubiquitination sites, finding ensemble methods generally outperform non-ensemble ones.

MetaLLM: Residue-wise Metal ion Prediction UsingDeep Transformer Model

MetaLLM predicts metal binding sites in proteins using a transformer-based model trained on protein sequences, achieving over 90% precision for common metal ions.

Hist2Vec: Kernel-Based Embeddings for Biological Sequence Classification

Hist2Vec is a kernel-based embedding method for biological sequence classification that outperforms existing methods with >76% and >83% accuracy on DNA and protein datasets, respectively.

CATHe: Detection of remote homologues for CATH superfamilies using embeddings from protein language models

The paper introduces CATHe, a method using protein language model embeddings to detect remote homologues for CATH superfamilies, achieving high accuracy and validating predictions with AlphaFold structures.

ProteinNPT: Improving Protein Property Predictionand Design with Non-Parametric Transformers

This paper introduces ProteinNPT, a non-parametric transformer for protein property prediction and design, showing improved performance in label-scarce and multi-task settings.

Imbalanced classification for protein subcellularlocalisation with multilabel oversampling

The paper addresses imbalanced multilabel classification for protein subcellular localization using oversampling techniques to improve minority class prediction performance.

PROSTATA: Protein Stability Assessment using Transformers

PROSTATA predicts protein stability changes from point mutations using a transformer-based model, outperforming existing neural network approaches.

WUREN: Whole-modal fUsion Representation for protein interaction interfacE predictioN

WUREN is a multimodal model that fuses sequence, graph, and structural features to predict protein interaction interfaces and antigen epitopes, achieving state-of-the-art performance.

Protein Language Model for Prediction of Subcellular Localization of Protein Sequences from Gram-negative bacteria (ProtLM.SCL)

ProtLM.SCL is a protein language model that improves subcellular localization prediction for Gram-negative bacteria proteins, outperforming PSORTb in accuracy and precision.

Codon language embeddings provide strong signals for protein engineering

The paper shows that codon-based language models outperform amino acid sequence models in protein engineering tasks like species recognition and melting point estimation.

Nucleotide augmentation for machine learning-guided protein engineering

This paper introduces nucleotide augmentation (NTA) to improve machine learning models for protein engineering by generating biologically meaningful sequence data, achieving performance gains even with limited training data.

Dysfunctional analysis of the pre-training model on nucleotide sequences and the evaluation of different k-mer embeddings

The paper analyzes how a pre-trained BERT model processes nucleotide sequences, identifies k-mer embeddings as key, and proposes an accelerated pre-training method.

LambdaPP: Fast and accessible protein-specific phenotype predictions

LambdaPP provides fast, accessible protein feature predictions including structure and function, using AI models and embeddings from protein Language Models.

Improving Protein Subcellular Localization Prediction with Structural Prediction & Graph Neural Networks

The paper improves protein subcellular localization prediction by combining sequence-based language models and structure-based graph neural networks, achieving better performance with lower computational cost.

A study on experimental bias in post-translational modification predictors

This study evaluates PTM predictors using protein language models, revealing a training bias from proteomics data that overestimates prediction accuracy and suggests a solution through negative sample filtering.

PRESGENE: A web server for PRediction of ESsential GENE using integrative machine learning strategies

PRESGENE is a web server that predicts essential genes in non-model organisms using machine learning, addressing dataset imbalance and limited labeled data challenges.