Machine Learning in Bioinformatics

Information Leakage in Enzyme Substrate Prediction

This study identifies information leakage in enzyme-substrate prediction models and datasets, showing performance drops when leakage is removed.

Evo 2 as a classification machine: evidence from in-context learning and mechanistic interpretability

This paper evaluates Evo 2's in-context learning capabilities on genomic sequences, finding strong performance on short sequences but degradation with length, and no benefit from model scaling.

GraPPI: A Self-Supervised Graph Encoder for Transferable Protein--Protein Interaction Modeling

GraPPI develops a self-supervised graph encoder for protein-protein interaction modeling, achieving high performance in binding interface prediction and affinity prediction.

Fast structural search for classification of gut bacterial mucin O-glycan degrading enzymes

This paper introduces DEFT, a method that combines sequence- and structure-based approaches to improve EC number prediction accuracy and enable high-throughput enzyme repertoire annotation.

SurfGraphPro: Integrating Protein Language Models with Geometric Deep Learning On Coarse Protein Surfaces for Binding Site Prediction

SurfGraphPro predicts protein binding sites by integrating protein language models with geometric deep learning on coarse protein surfaces, achieving faster performance than existing methods.

NeoToxPred: a fine-tuned protein language model with orthologous and length-stratified negative controls for robust toxicity classification

NeoToxPred improves toxicity classification by using a protein language model with carefully curated negative controls, outperforming existing methods on both internal and external benchmarks.

StackHPpred: A Stacking-based ensemble learning framework for the identification of peptide hormones using multi-view feature representations

StackHPpred identifies peptide hormones from amino acid sequences using a stacking-based ensemble framework, achieving high accuracy on independent datasets.

Pep-PU-GAN: Positive-Unlabeled Adversarial Learning for Peptide Function Prediction

Pep-PU-GAN improves peptide function prediction using PU learning and GANs with graph neural networks, achieving high F1 and AUROC scores on neuropeptide classification.

Mechanistic Interpretability of Fine-Tuned Protein Language Models for Nanobody Thermostability Prediction

This paper fine-tunes a protein language model on nanobody thermostability data and uses sparse autoencoders to uncover biophysical rules governing stability, identifying both known and novel stabilizing features.

Self-Architecting Protein Transformers: An Empirical Study

This paper evaluates a self-architecting transformer for protein representation, showing it achieves better performance than existing models with a smaller dataset.

Learning the Language of the Microbiome with Transformers

The paper introduces Atlas, a microbiome dataset, and Waypoint, a series of transformer-based models, showing improvements in downstream tasks through pretraining.

ProteinSage: From implicit learning to explicit structural constraints for efficient protein language modeling

ProteinSage uses structural constraints during pretraining to improve protein language modeling with less data, achieving competitive performance on structure-aware tasks.

BioGraphX-RNA: A Universal Physicochemical Graph Encoding for Interpretable RNA Subcellular Localization Prediction

BioGraphX-RNA predicts RNA subcellular localization using physicochemical graph encoding, showing competitive performance and interpretability across mRNA, miRNA, and lncRNA.

Developing SCL2205 : A Protein Sequence-based Spatial Modelling Dataset for the Protein Language Model Frontier

The paper develops a high-quality dataset for protein sub-cellular localisation prediction, showing performance improvements and highlighting data leakage issues in existing models.

FuncSeek: Multi-PLM contrastive learning for protein functional similarity search

FuncSeek improves enzyme function prediction by using contrastive learning with multiple PLMs, outperforming existing methods on benchmark datasets.

DeepTMHMM2 enables accurate prediction of transmembrane protein topology and subcellular location

DeepTMHMM2 predicts transmembrane protein topology and subcellular location, including re-entrant regions and interfacial helices, and identifies localization across 17 membranes.

TaHL-PTM: Post-Translational Modification Prediction in Proteins via Target-Hooked Discriminative Fine-Tuning of Decoder-only Protein Language Models

TaHL-PTM improves PTM prediction by addressing tokenization issues in decoder-only PLMs, achieving better performance on residue-level tasks.

ProtEnrich: Residual Multimodal Enrichment of Protein Sequence Embeddings

ProtEnrich enhances protein sequence embeddings with biophysical properties without disrupting their semantic structure, improving performance on structure-related tasks.

InterPET: A Curated Benchmark of Sequence Embeddings and Graph Architectures with Interpretability and Biological Validation for PETase Activity Prediction

The paper introduces InterPET, a benchmark for predicting PETase activity using sequence embeddings and graph architectures, showing that model performance and biological validity are interdependent.

Sparse autoencoder features from InterPLM predict neuropeptide precursors among secreted proteins

The paper introduces a method using sparse autoencoder features from InterPLM to predict neuropeptide precursors from secreted proteins across species.

A novel benchmark dataset for enzyme function prediction reveals the limitations of state-of-the-art models

This paper introduces a benchmark dataset for enzyme function prediction and shows that current models struggle to distinguish non-functional enzyme variants from functional ones.

PG-LLM: Benchmarking General-Purpose Language Models for Protein Variant Ranking

PG-LLM benchmarks language models for protein variant ranking, showing they outperform many sequence-based predictors but fall short of specialized models.

Cryptic binding sites are detected but not ranked: coverage, conversion, and the limits of detector consensus

The paper evaluates cryptic binding site detection methods by separating coverage from ranking, showing that ranking improvements can significantly enhance recovery.

ETAP-CLF: an ESM3-based transformer attention framework for binary protein classification

ETAP-CLF uses ESM3 embeddings and transformer attention to classify proteins into binary categories, achieving high AUROC scores across different biological processes.

ICFinder: ion channel identification and ion permeation residue prediction using protein language models

ICFinder uses protein language models to identify ion channels and predict permeation residues, outperforming existing methods and providing a public resource.

A Two-Stage ESM-Based Machine Learning Pipeline for Robust Hierarchical Enzyme Function Prediction

ESM-ECForest uses ESM-2 embeddings and Random Forest classifiers to predict enzyme functions with high accuracy across EC levels.

Cross-attention and language models reveal the interpretability of functional predictions for the human olfactory receptor family

This study introduces CrossVOI, a framework for VOC-OR interaction prediction using protein language models and cross-attention, showing improved performance and interpretability of attention mechanisms in human olfactory receptors.

Protein language models and the long tail of functional diversity

The paper examines the role of singleton protein sequences in training protein language models, finding they contain valuable functional diversity and should be included in training.

Interpretable biophysical neural networks of transcriptional activation domains separate roles of protein abundance and coactivator binding

This paper develops interpretable biophysical neural networks to predict transcriptional activation domains from protein sequences, revealing how residue properties influence both activation strength and protein abundance.

CLASPP: A unified model for predicting post-translational modifications

CLASPP is a unified deep learning model that predicts multiple PTM types from protein sequences, addressing data imbalance and improving prediction performance across organisms.