sequence-to-function modeling

Running ahead of evolution - AI based simulation for predicting future high-risk SARS-CoV-2 variants

This paper develops an AI-based simulation method to predict future high-risk SARS-CoV-2 variants by simulating RBD mutations and screening potential variants efficiently.

Deep mutational scanning and machine learning uncover antimicrobial peptide features driving membrane selectivity

The paper uses deep mutational scanning and machine learning to identify sequence features in antimicrobial peptides that enhance bacterial membrane selectivity while reducing mammalian toxicity.

Kmer-Node2Vec: a Fast and Efficient Method for Kmer Embedding from the Kmer Co-occurrence Graph, with Applications to DNA Sequences

The paper introduces Kmer-Node2Vec, a fast graph-based method for kmer embedding in DNA sequences, achieving faster training times than DNA2Vec while maintaining comparable accuracy.

Guiding Discovery of Protein Sequence-Structure-Function Modeling

The paper develops an in silico sequence-structure-function pipeline using AlphaFold2 and FFT docking to predict protein function, validated against experimental data on fungal monooxygenases.

xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein

A 100-billion-parameter protein language model trained with masked and autoregressive objectives together, topping prior results on 15 of 18 benchmarks and powering a fast structure predictor.

Generating Interacting Protein Sequences using Domain-to-Domain Translation

The paper develops a method to generate protein domain sequences that interact with another domain, outperforming existing approaches and exploring fine-tuning and structure prediction.

Machine learning prediction of enzyme optimum pH

This study develops and evaluates machine learning models to predict enzyme optimum pH, finding that language model embeddings significantly improve prediction accuracy, leading to the release of the EpHod model.

Cross-reactivity of antibodies against T cell markers in the Bank vole (Myodes glareolus)

The paper tests monoclonal antibody cross-reactivity against T cell markers in bank voles and provides sequence analysis of relevant molecules in Cricetidae rodents.

DNA Structure Design Is Improved Using an Artificially Expanded Alphabet of Base Pairs Including Loop and Mismatch Thermodynamic Parameters

This paper improves DNA structure design by introducing a new base pair alphabet with P-Z pairs and thermodynamic parameters, enhancing design accuracy and reducing off-target folding.

An intrinsically interpretable neural network architecture for sequence to function learning

The paper introduces tiSFM, an interpretable neural network for sequence-to-function learning, which outperforms existing models in predicting open chromatin and transcription factor activities.

NTpred: A robust and precise machine learningframework for in-silico identification of Tyrosine nitration sites in protein sequences

NTpred improves the identification of tyrosine nitration sites in protein sequences using advanced feature extraction and ensemble classifiers, achieving better performance than existing methods on benchmark datasets.

ESMFold Hallucinates Native-Like Protein Sequences

This paper demonstrates that inverting ESMFold can generate more native-like and expressive protein sequences compared to AFDesign, but with higher memory usage.

Direct prediction of intrinsically disordered protein conformational properties from sequence

This paper develops ALBATROSS, a deep learning model that predicts ensemble conformational properties of intrinsically disordered proteins from sequence, enabling proteome-wide analysis.

The Flip-flop neuron - A memory efficient alternative for solving challenging sequence processing and decision making problems

The paper introduces a JK flip-flop neuron model for sequence processing tasks, showing it outperforms LSTMs with fewer parameters.

Genomic Benchmarks: A Collection of Datasets for Genomic Sequence Classification

The paper introduces a collection of genomic sequence classification datasets and a baseline CNN model, distributed as a Python package to improve reproducibility in genomics machine learning.

Automated Protein Affinity Optimization using a 1D-CNN Deep Learning Model

This paper introduces ZymeSwapNet, a 1D-CNN model for protein sequence prediction that optimizes design objectives like stability and binding specificity in antibody domains.

High quality single amplicon sequencing method for illumina platforms using N (0-10) spacer primer pool without PhiX spik-in

The paper introduces a method to improve sequencing quality for amplicon libraries by using N spacers in primers, eliminating the need for PhiX spike-in and enabling multiplexing.

Two sequence- and two structure-based ML models have learned different aspects of protein biochemistry

The paper compares sequence- and structure-based ML models for predicting protein residue properties, finding they excel at different tasks and that combining them improves accuracy.

Mycobacterial RNase E cleaves with a distinct sequence preference and controls the degradation rates of most Mycolicibacterium smegmatis mRNAs

This study defines the role of RNase E in mRNA degradation in Mycolicibacterium smegmatis, showing it limits degradation of 89% of protein-coding genes and has distinct sequence preferences compared to gram-negative bacteria.

Long-term reliable neural decoding based on flexible implantable microelectronics and machine learning for seizure prediction application

This study combines flexible implantable microelectronics with machine learning to achieve reliable long-term neural decoding for seizure prediction in epileptic mice.

Sequence-based prediction of the solubility of peptides containing non-natural amino acids

The paper presents CamSol-PTM, a computational method to predict solubility of peptides with non-natural amino acids, validated through experimental testing of 30 variants.

Identifying promising sequences for protein engineering using a deep Transformer Protein Language Model

This paper introduces a deep Transformer Protein Language Model to identify promising protein sequences for engineering by calculating a PROMISE SCORE based on predicted interactions with binding partners.

Deep learning-based codon optimization with large-scale synonymous variant datasets enables generalized tunable protein expression

The paper develops deep learning models trained on synonymous variant datasets to predict and optimize protein expression in E. coli.

Generative power of a protein language model trained on multiple sequence alignments

The paper demonstrates that MSA Transformer can generate protein sequences that perform as well as natural sequences in homology, coevolution, and structure-based measures, outperforming Potts models in some cases.

The Master Database of All Possible RNA Sequences and Its Integration with RNAcmap for RNA Homology Search

The paper builds a large RNA sequence database (MARS) and integrates it with RNAcmap to improve homology search and RNA structure/function inference.

Bacterial toxin-antitoxin system MazEF as a native defense mechanism against RNA phages in Escherichia coli

This study shows that the MazEF toxin-antitoxin system in E. coli protects against RNA phages by cleaving their genomes, with MazF targeting specific sequences in phage genomes.

Prediction of SARS-CoV-2 spike protein mutations using Sequence-to-Sequence and Transformer models

The paper uses Seq2Seq and Transformer models to predict SARS-CoV-2 spike protein mutations and finds some generated sequences match known variants from 2021 and 2022.

PC_sim: An integrated measure of protein sequence and structure similarity for improved alignments and evolutionary inference

The paper introduces PC_sim, a hybrid measure combining sequence and structure similarity for better alignments and evolutionary inference, showing improved results over individual measures.

Deep autoregressive generative models capture the intrinsics embedded in T-cell receptor repertoires

This paper introduces TCRpeg, a deep autoregressive generative model for TCR repertoires, achieving higher accuracy in probability estimation and improving multiple TCR-related tasks.

RNA sequence to structure analysis from comprehensive pairwise mutagenesis of multiple self-cleaving ribozymes

The paper analyzes RNA sequence to structure relationships using comprehensive mutagenesis data from self-cleaving ribozymes to identify structural features and functional critical nucleotides.