A deep learning multi-attention Bi-GRU framework for kcat prediction with segmentation-based insights
Enzyme and Microbial Technology
Literature
Year
Journal mark
Research papers
Showing all 181 papers
95 papers
-
-
A General Harness for Protein Foundation Model Fitness Prediction
arXiv
-
A geometric foundation model for enzyme retrieval with evolutionary insights
Nature Catalysis
-
A Multimodal Ensemble Framework for Optimal Mutant Prediction and Computational Enzyme Engineering
Angewandte Chemie International Edition
-
A novel benchmark dataset for enzyme function prediction reveals the limitations of state-of-the-art models
bioRxiv
-
A trimodal protein language model enables advanced protein searches
Nature Biotechnology
-
Accelerating scientific discovery with Co-Scientist
Nature
-
Access to all stereoisomers of chiral alcohols with multiple stereocentres enabled by machine learning-empowered protein engineering
Nature Synthesis
-
Accurate enzyme specificity constant prediction with iESC
Bioresource Technology
-
Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools
arXiv
-
Agentic campaign control for high-throughput de novo binder design
bioRxiv
-
AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design
arXiv
-
AI-Guided Multi-Objective Engineering of Glucoamylase Enables Acidification-Free Starch Saccharification
bioRxiv
-
AI-redesigned starting points and outcomes enhance protein evolution
Nature
-
Aligning protein-generative models to experimental fitness with ProteinDPO
Nature Methods
-
An AI-Native Biofoundry for Autonomous Enzyme Engineering: Integrating Active Learning with Automated Experimentation
-
An AI-powered cloud biofoundry for autonomous biological research
bioRxiv
-
An enzyme-specific protein language model for catalytic property prediction
Nature Communications
-
Artificial Intelligence Platform EnzySFC for Enzyme Screening and Functional Conversion: Completely Redirecting Nitrilase to Nitrile Hydratase Function
Journal of Agricultural and Food Chemistry
-
Assay-Aware BindingDB: Curating Experimental Context for Binding Affinity Prediction
arXiv
-
Atom-level enzyme active site scaffolding using RFdiffusion2
Nature Methods
-
AUKAT: Conditional VAE-Driven Augmentation and Neural Modeling of Enzyme Turnover Numbers
Biomolecules
-
AutoBinder Agent: An MCP-Based Agent for End-to-End Protein Binder Design
arXiv
-
Autonomous biomedical research with an artificial intelligence agent
Science
-
Benchmarking and behavioral characterization of LLM agents for protein design
bioRxiv
-
CACLENS: A Multitask Deep Learning System for Enzyme Discovery
Advanced Science
-
CatESO: Differentiable Enzyme Sequence Optimization Guided by Substrate-Aware kcat Prediction
bioRxiv
-
Compressing the collective knowledge of ESM into a single protein language model
Nature Methods
-
Computational design of metallohydrolases
Nature
-
Computational enzyme design by catalytic motif scaffolding
Nature
-
Customizing Natural Products of Sesquiterpene Synthases by Mechanism-Based Design and DeEnzyme_Score Screening
ACS Catalysis
-
Customizing the structure of minimal TIM barrels to craft efficient de novo enzymes
Nature Chemical Biology
-
Data-driven construction of an imine reductase library capable of broad-scope reductive amination at equimolar substrate concentrations
Nature Communications
-
De novo Rubisco design with protein language models
bioRxiv
-
Decoding enzyme-substrate interaction topology reveals principles underlying catalytic efficiency and mutational outcomes
arXiv
-
Deep learning for enzyme kcat prediction: what works, what doesn't, and why?
Research Square
-
Deep Learning-Driven Discovery and Engineering of an Efficient PETase for Depolymerization and Detoxification of PET Microplastics Under Physiological Conditions
Advanced Science
-
Designing enzymes for new-to-nature chemistry and non-natural substrates with AlphaProtein Novo
bioRxiv
-
Differences between protein fitness models can be used to design variants of altered specificity
bioRxiv
-
Dual-encoder contrastive learning accelerates enzyme discovery
Proceedings of the National Academy of Sciences
-
Enhancing Enzyme Activity With Mutation Combinations Guided by Few-Shot Learning and Causal Inference
Angewandte Chemie International Edition
-
Enhancing kcat prediction through residue-aware attention mechanism and pre-trained representations
Communications Biology
-
EnzCast: Prediction of Patient-Specific Enzymatic Kinetics thrugh Multi-Modal Deep Learning and Isoform-Resolved Bayesian Inference based on Single-Cell Transcriptomics
bioRxiv
-
Enzyme Kinetic Parameter Prediction via Catalytic Pocket-Augmented Machine Learning
ACS Catalysis
-
ENZYME-UNIFIED: LEARNING HOLISTIC REPRESENTATIONS OF ENZYME FUNCTION WITH A HYBRID INTERACTION MODEL
-
EnzymeHunter: Achieving fine-grained enzyme function prediction with a hierarchically aware contrastive learning framework
Patterns
-
Evolution-inspired multi-objective Bayesian optimization for protein engineering
bioRxiv
-
Evolutionary profiles for protein fitness prediction
Bioinformatics
-
FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications
bioRxiv
-
Function-guided design of active enzymes
bioRxiv
-
Functional alignment of protein language models via reinforcement learning
Nature Communications
-
Functional Locality–Aligned Learning Reveals Structure–Function Causality in Enzyme Kinetics
bioRxiv
-
Functional protein design and enhancement with ontology reinforcement iteration
Nature Communications
-
GAPEK: A General Framework for Multiparameter Enzyme Kinetic Prediction with Adaptive Learning
Journal of Chemical Information and Modeling
-
Generative AI designs functional thiolation domains for reprogramming non-ribosomal peptide synthetases
Nature Communications
-
Generative Artificial Intelligence-Empowered Virtual Evolution of Enzyme with the VERnet Model
ACS Catalysis
-
Genolator enables protein function interpretation using a multimodal large language model fusing genomic and structural interpretation with natural language interaction
Genome Biology
-
GMSF: A Dual-PathMultimodal Framework for EnzymeFunction Prediction via Difference Graph Encoding and Multiscale SemanticFusion
Journal of Chemical Information and Modeling
-
GotEnzymes2: expanding coverage of enzyme kinetics and thermal properties
Nucleic Acids Research
-
Information Leakage in Enzyme Substrate Prediction
Bioinformatics
-
Integrating Arrhenius Constraints with Lineage-Aware Meta-Learning for Few-Shot Prediction of Temperature-Dependent Enzyme Kinetics
Journal of Chemical Information and Modeling
-
Katalyst: Knowledge-Guided Semantic Alignment via Contrastive Learning for Enzyme Turnover Prediction
Bioinformatics
-
KinEAGER: An Evidence-AwareMultitask Model with CalibratedUncertainty for Enzyme Kinetics Prediction
Journal of Chemical Information and Modeling
-
KinForm: kinetics-informed feature optimised representation models for enzyme kcat and KM prediction
npj Systems Biology and Applications
-
KmPred: prediction of Michaelis constants (Km) using an integrative machine learning framework
Frontiers in Artificial Intelligence
-
Language Modeling Materializes a World Model of Protein Biology
-
Learning protein function through autonomous experimental interaction
bioRxiv
-
Leveraging latent space models for enzyme discovery and sampling
Proceedings of the National Academy of Sciences
-
LLM sequential decision making under uncertainty in biochemical domains
arXiv
-
Mechanistic Interpretability of Fine-Tuned Protein Language Models for Nanobody Thermostability Prediction
Bioinformatics
-
MechFind: a computational framework for de novo prediction of enzyme mechanisms
Nature Communications
-
Metabolic engineering and deep learning-driven protein engineering for N-Acetylneuraminic acid biosynthesis in Escherichia coli
Nature Communications
-
Miniaturizing and modifying natural proteins with Raygun
Nature
-
Multimodal Protein Language Models for Enzyme Kinetic Parameters: From Substrate Recognition to Conformational Adaptation
arXiv
-
MutexaGPT: an intuition-to-design translator for physics-based enzyme engineering
Nature Computational Science
-
PDAgent: An LLM-Driven Autonomous Agent Framework Towards *In Silico* Protein Design via Directed Mutation
Proceedings of the 43rd International Conference on Machine Learning
-
Predicting Enzyme Turnover Numbers and Enabling Rational Enzyme Evolution
Advanced Science
-
Property guidance for protein sequence generative models with ProteinGuide
Nature Biotechnology
-
ProteinMCP: An agentic AI framework for autonomous protein engineering
Protein Science
-
ProtGPT3: an Open-source family of Promptable and Aligned Protein Language Models
bioRxiv
-
ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design
Findings of the Association for Computational Linguistics: ACL 2026
-
Pseudodata-Guided Invariant Representation Learning Boosts the Out-of-Distribution Generalization in Enzymatic Kinetic Parameter Prediction
Journal of Chemical Information and Modeling
-
Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Prediction
arXiv
-
Rank-guided learning accelerates automated enzyme engineering
Nature Communications
-
Rapid directed evolution guided by protein language models and epistatic interactions
Science
-
Reaction-Conditioned Enzyme Discovery with Multimodal Deep Learning
bioRxiv
-
Reframing enzyme function prediction as conditional generation
bioRxiv
-
Robust enzyme kinetics prediction through pairwise relative learning
-
Self-evolving AI agents for protein discovery and directed evolution
arXiv
-
Speak to a Protein: An Interactive Multimodal Co-Scientistfor Protein Analysis
Journal of Chemical Information and Modeling
-
Structure-aware Reinforcement Learning for Protein Directed Evolution
arXiv
-
Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation
Digital Discovery
-
Task- and dataset-specific information in protein language models
arXiv
-
Understanding language model scaling for protein fitness prediction
Nature Computational Science
-
UniKineG: Unified-Coordinate Geometric Graphs Enable Robust Enzyme Kinetic Prediction
International Journal of Molecular Sciences
43 papers
-
A Deep Learning-Based Approach for Predicting Michaelis Constants from Enzymatic Reactions
Applied Sciences
-
A generalized platform for artificial intelligence-powered autonomous enzyme engineering
Nature Communications
-
A multimodal deep learning framework for enzyme turnover prediction with missing modality
Computers in Biology and Medicine
-
A novel interpretability framework for enzyme turnover number prediction boosted by pre-trained enzyme embeddings and adaptive gate network
Methods
-
Accelerated enzyme engineering by machine-learning guided cell-free expression
Nature Communications
-
Accelerating protein engineering with fitness landscape modelling and reinforcement learning
Nature Machine Intelligence
-
Active learning-assisted directed evolution
Nature Communications
-
AI mirrors experimental science to uncover a mechanism of gene transfer crucial to bacterial evolution
Cell
-
Atomic context-conditioned protein sequence design using LigandMPNN
Nature Methods
-
AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering
Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
-
Biophysics-based protein language models for protein engineering
Nature Methods
-
Catalytic pocket-informed augmentation of enzyme kinetic parameters prediction via hierarchical graph learning
bioRxiv
-
CatPred: a comprehensive framework for deep learning in vitro enzyme kinetic parameters
Nature Communications
-
Complete computational design of high-efficiency Kemp elimination enzymes
Nature
-
Computational design of serine hydrolases
Science
-
Computational scoring and experimental evaluation of enzymes generated by neural networks
Nature Biotechnology
-
CPI-Pred: A deep learning framework for predicting functional parameters of compound-protein interactions
bioRxiv
-
DEKP: a deep learning model for enzyme kinetic parameter prediction based on pretrained models and graph neural networks
Briefings in Bioinformatics
-
EnzyCLIP: A Cross-Attention Dual Encoder Framework with Contrastive Learning for Predicting Enzyme Kinetic Constants
arXiv
-
Enzyme specificity prediction using cross-attention graph neural networks
Nature
-
ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties
Nature Communications
-
From high-throughput evaluation to wet-lab studies: advancing mutation effect prediction with a retrieval-enhanced model
Bioinformatics
-
Glycolysis-compatible urethanases for polyurethane recycling
Science
-
Harnessing protein language model for structure-based discovery of highly efficient and robust PET hydrolases
Nature Communications
-
IECata: interpretable bilinear attention network and evidential deep learning improve the catalytic efficiency prediction of enzymes
Briefings in Bioinformatics
-
Integrating protein language models and automatic biofoundry for enhanced protein evolution
Nature Communications
-
KcatNet: A Geometric Deep Learning Framework for Genome-Wide Prediction of Enzyme Catalytic Efficiency
bioRxiv
-
Machine learning prediction of enzyme optimum pH
Nature Machine Intelligence
-
Machine Learning-Guided Identification of PET Hydrolases from Natural Diversity
ACS Catalysis
-
NNKcat: deep neural network to predict catalytic constants (Kcat) by integrating protein sequence and substrate structure with enhanced data imbalance handling
Briefings in Bioinformatics
-
OmniESI: A unified framework for enzyme-substrate interaction prediction with progressive conditional deep learning
arXiv
-
PreTKcat: A pre-trained representation learning and machine learning framework for predicting enzyme turnover number
Computational Biology and Chemistry
-
ProteinCrow: A Language Model Agent That Can Design Proteins
ICML 2025 Generative AI and Biology (GenBio) Workshop
-
Robust enzyme discovery and engineering with deep learning using CataPro
Nature Communications
-
Robust Prediction of Enzyme Variant Kinetics with RealKcat
bioRxiv
-
SAKPE: A Site Attention Kinetic Parameters Prediction Method for Enzyme Engineering
bioRxiv
-
Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins
bioRxiv
-
Semantical and geometrical protein encoding toward enhanced bioactivity and thermostability
eLife
-
Simulating 500 million years of evolution with a language model
Science
-
Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy
Nature Communications
-
TCNeKP: A Novel Deep Learning Architecture for Enzyme Catalytic Activity Prediction
Journal of Chemical Information and Modeling
-
The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies
Nature
21 papers
-
A general temperature-guided language model to design proteins of enhanced stability and activity
Science Advances
-
A multimodal Transformer Network for protein-small molecule interactions enhances predictions of kinase inhibition and enzyme-substrate relationships
PLOS Computational Biology
-
CLIPZyme: Reaction-Conditioned Virtual Screening of Enzymes
-
Conditional language models enable the efficient design of proficient enzymes
bioRxiv
-
DeepEnzyme: a robust deep learning model for improved enzyme turnover number prediction by utilizing features of protein 3D-structures
Briefings in Bioinformatics
-
DLTKcat: deep learning-based prediction of temperature-dependent enzyme turnover rates
Briefings in Bioinformatics
-
EITLEM-Kinetics: A deep-learning framework for kinetic parameter prediction of mutant enzymes
Chem Catalysis
-
Enhancing efficiency of protein language models with minimal wet-lab data through few-shot learning
Nature Communications
-
ENKIE: a package for predicting enzyme kinetic parameter values and their uncertainties
Bioinformatics
-
GraphKM: machine and deep learning for KM prediction of wildtype and mutant enzymes
BMC Bioinformatics
-
Improving the prediction of protein stability changes upon mutations by geometric learning and a pre-training strategy
Nature Computational Science
-
Leveraging ancestral sequence reconstruction for protein representation learning
Nature Machine Intelligence
-
Machine learning-guided co-optimization of fitness and diversity facilitates combinatorial library design in enzyme engineering
Nature Communications
-
MPEK: a multitask deep learning framework based on pretrained language models for enzymatic reaction kinetic parameters prediction
Briefings in Bioinformatics
-
Multi-modal deep learning enables efficient and accurate annotation of enzymatic active sites
Nature Communications
-
Multi-Scale Representation Learning for Protein Fitness Prediction
arXiv
-
ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention
bioRxiv
-
ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning
Digital Discovery
-
Rapid in silico directed evolution by a protein language model with EVOLVEpro
Science
-
Self-driving laboratories to autonomously navigate the protein fitness landscape
Nature Chemical Engineering
-
Validation of an LLM-based Multi-Agent Framework for Protein Engineering in Dry Lab and Wet Lab
2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
11 papers
-
A general model to predict small molecule substrates of enzymes based on machine and deep learning
Nature Communications
-
De novo design of luciferases using deep learning
Nature
-
De novo design of protein structure and function with RFdiffusion
Nature
-
Enzyme function prediction using contrastive learning
Science
-
Functional annotation of enzyme-encoding genes using deep learning with transformer layers
Nature Communications
-
Large language models generate functional protein sequences across diverse families
Nature Biotechnology
-
ProGen2: Exploring the boundaries of protein language models
Cell Systems
-
ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers
bioRxiv
-
SaProt: Protein Language Modeling with Structure-aware Vocabulary
The Twelfth International Conference on Learning Representations
-
Turnover number predictions for kinetically uncharacterized enzymes using machine and deep learning
Nature Communications
-
UniKP: a unified framework for the prediction of enzyme kinetic parameters
Nature Communications
7 papers
-
Deep learning-based kcat prediction enables improved enzyme-constrained model reconstruction
Nature Catalysis
-
Evolutionary-scale prediction of atomic level protein structure with a language model
bioRxiv
-
Learning inverse folding from millions of predicted structures
bioRxiv
-
MLAGO: machine learning-aided global optimization for Michaelis constant estimation of kinetic modeling
BMC Bioinformatics
-
ProtGPT2 is a deep unsupervised language model for protein design
Nature Communications
-
Robust deep learning–based protein sequence design using ProteinMPNN
Science
-
TranceptEVE: Combining Family-specific and Family-agnostic Models of Protein Sequences for Improved Fitness Prediction
NeurIPS 2022 Workshop on Learning Meaningful Representations of Life
3 papers
-
Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences
Proceedings of the National Academy of Sciences
-
Deep learning allows genome-scale prediction of Michaelis constants from structural features
PLOS Biology
-
ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Learning
bioRxiv
1 paper
-
Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models
Nature Communications
No papers match the current filters.