Biology & Life Sciences

274 verified cases, highest-rated first.

Industries: protein science 37, drug discovery 21, genomics 14, gene editing 10, genome editing 8, protein design 7, wildlife conservation 7, bioinformatics 6, protein engineering 5, structural biology 5, synthetic biology 5, bioimaging microscopy 5

• Structure Prediction and Computational Protein Design for Efficient Biocatalysts and Bioactive Proteins

  Predicting protein structures and designing functional proteins (efficient biocatalysts, bioactive proteins) is key to medicine, diagnostics and sustainable chemical manufacture. The paper reviews computational tools addressing this.

  Biology & Life Sciences · 2024 · ai assisted · 9/10 importance

• Evolutionary-scale prediction of atomic-level protein structure with a language model

  Predicting the 3D structures of the exponentially growing catalog of protein sequences was too slow with existing methods, requiring a breakthrough in folding speed.

  Biology & Life Sciences · 2023 · solved · 9/10 importance

• De novo design of protein structure and function with RFdiffusion

  Designing new proteins with specified structures and functions (binders, symmetric assemblies, enzyme scaffolds) lacked a general deep-learning framework.

  Biology & Life Sciences · 2023 · solved · 9/10 importance

• AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models

  Structural coverage of known protein-sequence space was limited; the paper delivers an openly accessible database of high-accuracy predicted protein structures.

  Biology & Life Sciences · 2021 · solved · 9/10 importance

• Accurate prediction of protein structures and interactions using a three-track neural network

  Predicting accurate 3D protein structures and protein-protein complexes from sequence information alone remained a major challenge.

  Biology & Life Sciences · 2021 · solved · 9/10 importance

• A generalized platform for artificial intelligence-powered autonomous enzyme engineering

  Engineering proteins with desired functions is slow, expensive, and dependent on specialist expertise.

  Biology & Life Sciences · 2025 · solved · 8/10 importance

• Deep-learning-based single-domain and multidomain protein structure prediction with D-I-TASSER

  Accurately predicting atomic-level 3D structures of large multidomain proteins remains challenging for deep-learning methods alone.

  Biology & Life Sciences · 2025 · partially solved · 8/10 importance

• Accurate structure prediction of biomolecular interactions with AlphaFold 3

  Predicting the joint 3D structures of biomolecular complexes (proteins with ligands, nucleic acids, ions and antibodies) previously required separate specialized tools with limited accuracy. AlphaFold 3 addresses this unified modelling problem.

  Biology & Life Sciences · 2024 · solved · 8/10 importance

• De novo protein design—From new structures to programmable functions

  Designing new proteins with shapes and molecular functions not found in nature, requiring precise control over conformation and molecular recognition.

  Biology & Life Sciences · 2024 · partially solved · 8/10 importance

• AI-Driven Deep Learning Techniques in Protein Structure Prediction

  Predicting protein 3D structure from sequence is a long-standing computational challenge important for understanding function.

  Biology & Life Sciences · 2024 · partially solved · 8/10 importance

• Protein Design Using Structure-Prediction Networks: AlphaFold and RoseTTAFold as Protein Structure Foundation Models

  Designing proteins with tailored structures and functions is a long-standing unsolved goal in bioengineering.

  Biology & Life Sciences · 2024 · partially solved · 8/10 importance

• Illuminating protein space with a programmable generative model

  The space of possible protein molecules is vastly larger than the space of functional ones, making it hard for computation and experiments to access proteins with desired properties and functions.

  Biology & Life Sciences · 2023 · ai assisted · 8/10 importance

• Deep learning for protein complex structure prediction

  Predicting the 3D structures of protein complexes accurately, a long-standing bottleneck in structural biology.

  Biology & Life Sciences · 2023 · partially solved · 8/10 importance

• Robust deep learning–based protein sequence design using ProteinMPNN

  Designing amino acid sequences that fold into target protein structures relied on physically based approaches such as Rosetta rather than deep learning.

  Biology & Life Sciences · 2022 · solved · 8/10 importance

• Applications of machine learning in computer-aided drug discovery

  Drug discovery needs predictive models for de novo drug design, binding site prediction, and binding affinity of small molecules.

  Biology & Life Sciences · 2022 · ai assisted · 8/10 importance

• Deep Machine Learning for Computer-Aided Drug Design

  Computer-aided drug design faces new challenges and opportunities from recent deep learning advances in molecular modeling.

  Biology & Life Sciences · 2022 · ai assisted · 8/10 importance

• Protein structure prediction using deep learning distance and hydrogen‐bonding restraints in CASP14

  Predicting 3D protein structures from sequence, especially hard free-modelling (FM) targets without templates, in CASP14.

  Biology & Life Sciences · 2021 · partially solved · 8/10 importance

• Deep Learning for SARS COV-2 Genome Sequences

  During a novel virus outbreak, authorities must quickly determine whether the epidemic stems from a novel or a known virus; this work addresses classifying SARS-CoV-2 among coronaviruses from genome sequences.

  Biology & Life Sciences · 2021 · ai assisted · 8/10 importance

• Genome-Scale Metabolic Models and Machine Learning Reveal Genetic Determinants of Antibiotic Resistance in Escherichia coli and Unravel the Underlying Metabolic Adaptation Mechanisms

  Understanding which genes drive antibiotic resistance in E. coli and how the bacterium's metabolism adapts to resist drugs.

  Biology & Life Sciences · 2021 · ai assisted · 8/10 importance

• Protein tertiary structure prediction and refinement using deep learning and Rosetta in CASP14

  Predicting and refining protein 3D tertiary structures from sequence remains difficult and computationally expensive.

  Biology & Life Sciences · 2021 · partially solved · 8/10 importance

• Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction

  Predicting proteins' 3D structures from sequence is difficult; deep learning methods were applied to interpret how sequences and homology govern inter-residue contacts and structural organization.

  Biology & Life Sciences · 2021 · partially solved · 8/10 importance

• Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13

  Predicting protein 3D structures from sequence, including template-free (ab initio) cases where no similar known structure exists.

  Biology & Life Sciences · 2019 · partially solved · 8/10 importance

• Analysis of distance‐based protein structure prediction by deep learning in CASP13

  Predicting 3D protein structures from sequence alone, especially for free-modeling targets without templates, was a major unsolved challenge.

  Biology & Life Sciences · 2019 · partially solved · 8/10 importance

• Atomic context-conditioned protein sequence design using LigandMPNN

  Designing protein sequences that correctly interact with small molecules, nucleotides and metals — essential for enzymes, binders and sensors — which prior deep-learning methods could not model.

  Biology & Life Sciences · 2025 · solved · 7/10 importance

• Accurate de novo design of high-affinity protein-binding macrocycles using deep learning

  Designing macrocyclic binders to therapeutic proteins relies on resource-intensive screening with little control over binding mode, and no robust de novo design approaches existed.

  Biology & Life Sciences · 2025 · solved · 7/10 importance

• Target sequence-conditioned design of peptide binders using masked language modeling

  Designing de novo linear peptide binders for disease targets, including 'undruggable' ones, is difficult without stable structural information.

  Biology & Life Sciences · 2025 · partially solved · 7/10 importance

• RNA-protein interaction prediction using network-guided deep learning

  Predicting which RNAs bind which proteins is computationally hard, especially for RNAs and proteins with no known data.

  Biology & Life Sciences · 2025 · partially solved · 7/10 importance

• Crowdsourced Protein Design: Lessons From the Adaptyv EGFR Binder Competition

  Designing proteins that bind EGFR, a key cancer drug target, is difficult and lacks standardized benchmarks.

  Biology & Life Sciences · 2025 · partially solved · 7/10 importance

• Improving deep learning protein monomer and complex structure prediction using DeepMSA2 with huge metagenomics data

  Protein tertiary and quaternary structure prediction loses accuracy when multiple-sequence alignments (MSAs) are poorly constructed, especially for complexes.

  Biology & Life Sciences · 2024 · partially solved · 7/10 importance

• Biosensor and machine learning-aided engineering of an amaryllidaceae enzyme

  Industrial biomanufacturing of therapeutic Amaryllidaceae alkaloids like the Alzheimer's drug galantamine is slow, and supply relies on extraction from low-yielding daffodils.

  Biology & Life Sciences · 2024 · partially solved · 7/10 importance

• Structure-based, deep-learning models for protein-ligand binding affinity prediction

  Predicting protein-ligand binding affinity from structure is a key open problem in computational drug discovery needing better methods.

  Biology & Life Sciences · 2024 · ai assisted · 7/10 importance

• RoboEM: automated 3D flight tracing for synaptic-resolution connectomics

  Reconstructing neuronal networks from 3D electron microscopy data requires costly manual proofreading, especially for thin axons.

  Biology & Life Sciences · 2024 · solved · 7/10 importance

• Deep learning approaches for non-coding genetic variant effect prediction: current progress and future prospects

  Most genetic variants are non-coding and their effects on gene regulation are hard to interpret; deep learning tools have been developed to predict these effects.

  Biology & Life Sciences · 2024 · ai assisted · 7/10 importance

• Accurate de novo design of high-affinity protein binding macrocycles using deep learning

  No robust method existed for de novo design of macrocyclic peptide binders against therapeutic protein targets.

  Biology & Life Sciences · 2024 · partially solved · 7/10 importance

• The Application of Machine Learning on Antibody Discovery and Optimization

  Traditional antibody discovery and optimization is time-consuming and resource-intensive, slowing development of antibody diagnostics and therapeutics.

  Biology & Life Sciences · 2024 · ai assisted · 7/10 importance

• Efficient evolution of human antibodies from general protein language models

  Efficiently improving human antibodies by finding rare beneficial mutations in a vast sequence landscape, normally requiring costly screening.

  Biology & Life Sciences · 2023 · solved · 7/10 importance

• De novo design of luciferases using deep learning

  Designing entirely new enzymes from scratch has been limited by a lack of suitable protein structures and the complexity of protein sequence-structure relationships.

  Biology & Life Sciences · 2023 · solved · 7/10 importance

• Improving de novo protein binder design with deep learning

  De novo design of high-affinity protein binders from target structure alone had a low overall success rate.

  Biology & Life Sciences · 2023 · partially solved · 7/10 importance

• Rapid protein stability prediction using deep learning representations

  Predicting how mutations change protein thermodynamic stability is needed in protein engineering and disease research, but biophysics-based methods are slow.

  Biology & Life Sciences · 2023 · solved · 7/10 importance

• Integrating deep learning, threading alignments, and a multi‐MSA strategy for high‐quality protein monomer and complex structure prediction in CASP15

  Predicting 3D structures of proteins and complexes, especially hard free-modeling targets, remains difficult.

  Biology & Life Sciences · 2023 · partially solved · 7/10 importance

• Design of Cyclic Peptides Targeting Protein–Protein Interactions Using AlphaFold

  Predicting structures of protein–cyclic peptide complexes and designing cyclic peptides that bind target proteins was computationally infeasible, blocking cyclic peptides as a modality for protein-protein interaction drug targets.

  Biology & Life Sciences · 2023 · partially solved · 7/10 importance

• Multi-domain and complex protein structure prediction using inter-domain interactions from deep learning

  Predicting 3D structures of multi-domain proteins and protein complexes, where AlphaFold2 still underperforms.

  Biology & Life Sciences · 2023 · partially solved · 7/10 importance

• Design of prime-editing guide RNAs with deep transfer learning

  Designing effective prime-editing guide RNAs (pegRNAs) is difficult due to lack of accurate, broadly applicable efficiency prediction and design optimization methods.

  Biology & Life Sciences · 2023 · solved · 7/10 importance

• Cross-protein transfer learning substantially improves disease variant prediction

  Most human missense genetic variants have unknown disease effects, leaving clinicians unable to interpret them.

  Biology & Life Sciences · 2023 · ai assisted · 7/10 importance

• High-throughput deep learning variant effect prediction with Sequence UNET

  The vast space of coding mutations cannot be experimentally characterised, and existing variant effect predictors are computationally intensive and difficult to scale.

  Biology & Life Sciences · 2023 · ai assisted · 7/10 importance

• Improved prediction of protein-protein interactions using AlphaFold2

  Predicting the structures of heterodimeric protein complexes, fundamental for understanding protein function, was unreliable with existing methods.

  Biology & Life Sciences · 2022 · partially solved · 7/10 importance

• Deep learning-based kcat prediction enables improved enzyme-constrained model reconstruction

  Experimentally measured enzyme turnover numbers (kcat) are sparse and noisy, limiting genome-scale metabolic modeling across organisms.

  Biology & Life Sciences · 2022 · solved · 7/10 importance

• Structure-Aware Multimodal Deep Learning for Drug–Protein Interaction Prediction

  Predicting which drugs interact with which proteins is crucial for drug discovery, but existing methods use biased datasets and weak protein representations.

  Biology & Life Sciences · 2022 · ai assisted · 7/10 importance

• Fast and accurate Ab Initio Protein structure prediction using deep learning potentials

  Predicting 3D protein structures ab initio remains inaccurate for proteins lacking sequence or structural homologs.

  Biology & Life Sciences · 2022 · partially solved · 7/10 importance

• Evaluating GPCR modeling and docking strategies in the era of deep learning-based protein structure prediction

  It was unclear whether deep learning-based protein structure predictions could actually improve docking and virtual screening for GPCR drug discovery compared to pre-deep-learning tools.

  Biology & Life Sciences · 2022 · ai assisted · 7/10 importance

• De novo design of high-affinity protein binders to bioactive helical peptides

  Designing proteins that bind short helical peptides (such as peptide hormones) with high affinity was an unmet challenge in de novo protein design.

  Biology & Life Sciences · 2022 · solved · 7/10 importance

• Data-driven enzyme engineering to identify function-enhancing enzymes

  Identifying function-enhancing enzyme variants is a 'holy grail' challenge in protein science.

  Biology & Life Sciences · 2022 · ai assisted · 7/10 importance

• Computational Tools and Resources for CRISPR/Cas Genome Editing

  Designing effective and specific sgRNAs for CRISPR/Cas genome editing while avoiding undesired off-target effects.

  Biology & Life Sciences · 2022 · ai assisted · 7/10 importance

• Genomic Prediction of Wheat Grain Yield Using Machine Learning

  Breeders need to predict wheat grain yield from genetic markers, but the best algorithms are unclear.

  Biology & Life Sciences · 2022 · ai assisted · 7/10 importance

• Prediction of evolutionary constraint by genomic annotations improves functional prioritization of genomic variants in maize

  Identifying which maize genetic variants are functionally important, at high resolution, to support crop improvement via genomic prediction and genome editing.

  Biology & Life Sciences · 2022 · ai assisted · 7/10 importance

• Deep learning and alignment of spatially resolved single-cell transcriptomes with Tangram

  Single-cell RNA-seq loses spatial information while spatial technologies have limited resolution, sensitivity, or gene throughput, blocking full organ atlases.

  Biology & Life Sciences · 2021 · partially solved · 7/10 importance

• gapseq: informed prediction of bacterial metabolic pathways and reconstruction of accurate metabolic models

  Automated reconstruction of microbial metabolic models often fails to recapitulate known metabolic processes, limiting phenotype prediction from genomes.

  Biology & Life Sciences · 2021 · solved · 7/10 importance

• InteractionGraphNet: A Novel and Efficient Deep Graph Representation Learning Framework for Accurate Protein–Ligand Interaction Predictions

  Predicting how strongly small molecules bind to target proteins is a key bottleneck in structure-based drug design, and traditional ML descriptors struggle with 3D molecular interactions.

  Biology & Life Sciences · 2021 · ai assisted · 7/10 importance

• Deep generative modeling for protein design

  Designing novel proteins with desired structures, stability and function is slow and difficult; generative models are being applied to accelerate it.

  Biology & Life Sciences · 2021 · ai assisted · 7/10 importance

• Easy-Prime: a machine learning–based prime editor design tool

  Designing highly efficient prime editors for making precise DNA edits remains challenging.

  Biology & Life Sciences · 2021 · partially solved · 7/10 importance

• Improving protein tertiary structure prediction by deep learning and distance prediction in CASP14

  Predicting protein 3D structure from sequence, especially for template-free (ab initio) targets, remains difficult.

  Biology & Life Sciences · 2021 · partially solved · 7/10 importance

• Prioritizing non-coding regions based on human genomic constraint and sequence context with deep learning

  Identifying which non-coding regions of the human genome are functional and disease-relevant is a key challenge in genomics.

  Biology & Life Sciences · 2021 · partially solved · 7/10 importance

• Deep learning suggests that gene expression is encoded in all parts of a co-evolving interacting gene regulatory structure

  It was unclear how coding and non-coding regions of the gene regulatory structure interact to determine mRNA expression levels.

  Biology & Life Sciences · 2020 · ai assisted · 7/10 importance

• Combining Docking Pose Rank and Structure with Deep Learning Improves Protein–Ligand Binding Mode Prediction over a Baseline Docking Approach

  Predicting how drug-like ligands bind to target proteins (binding mode and activity) is difficult, and standard docking approaches alone are inaccurate.

  Biology & Life Sciences · 2020 · partially solved · 7/10 importance

• Leveraging Uncertainty in Machine Learning Accelerates Biological Discovery and Design

  Machine learning models fail when predicting beyond their training distribution, hindering biological discovery such as finding active compounds from very small datasets.

  Biology & Life Sciences · 2020 · solved · 7/10 importance

• Deep‐learning contact‐map guided protein structure prediction in CASP13

  Predicting 3D protein structures for targets that lack homologous templates, where conventional pipelines performed poorly.

  Biology & Life Sciences · 2019 · partially solved · 7/10 importance

• An overview and metanalysis of machine and deep learning-based CRISPR gRNA design tools

  Predicting the on-target activity and off-target specificity of CRISPR-Cas9 guide RNAs is difficult, yet decisive for safe and effective gene editing.

  Biology & Life Sciences · 2019 · ai assisted · 7/10 importance

• Novel antimicrobial peptide discovery using machine learning and biophysical selection of minimal bacteriocin domains

  Discovering new bacteriocin-derived antimicrobial peptides as antibiotic alternatives is difficult due to diverse mechanisms of action, narrow activity spectra, and challenges isolating natural products.

  Biology & Life Sciences · 2019 · ai assisted · 7/10 importance

• Sequential regulatory activity prediction across chromosomes with convolutional neural networks

  Predicting which DNA sequences act as regulatory elements and how genetic variants influence gene expression in specific cell types, from sequence alone.

  Biology & Life Sciences · 2018 · solved · 7/10 importance

• Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning

  Predicting which DNA and RNA sequences are bound by proteins is needed to model gene regulation and identify causal disease variants.

  Biology & Life Sciences · 2015 · solved · 7/10 importance

• NEURD offers automated proofreading and feature extraction for connectomics

  Reconstructing neurons in millimeter-scale electron microscopy volumes requires laborious post-hoc proofreading to fix merge/split errors, and extracting morphological features demands stitching custom tool workflows.

  Biology & Life Sciences · 2025 · ai assisted · 6/10 importance

• Machine Learning-Driven Enzyme Mining: Opportunities, Challenges, and Future Perspectives

  Finding useful enzymes with desired functions among vast numbers of uncharacterized proteins is slow and difficult.

  Biology & Life Sciences · 2025 · ai assisted · 6/10 importance

• Bayesian deep-learning structured illumination microscopy enables reliable super-resolution imaging with uncertainty quantification

  Deep-learning reconstructions of structured illumination microscopy can produce unreliable super-resolution images, risking biological misinterpretation.

  Biology & Life Sciences · 2025 · solved · 6/10 importance

• Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design

  Finding novel small-molecule ligands for the adenosine A2A receptor from protein structure alone, without prior knowledge of ligand chemistry.

  Biology & Life Sciences · 2025 · solved · 6/10 importance

• Deep learning enhanced light sheet fluorescence microscopy for in vivo 4D imaging of zebrafish heart beating

  Time-resolved volumetric fluorescence imaging over extended durations is limited by the trade-off among imaging speed, light exposure, illumination power and image quality.

  Biology & Life Sciences · 2025 · solved · 6/10 importance

• Deep Learning in Image-Based Plant Phenotyping

  Manually measuring crop traits is slow and labor-intensive, and extracting meaningful information from large plant image datasets is difficult.

  Biology & Life Sciences · 2024 · ai assisted · 6/10 importance

• Inferring gene regulatory networks from single-cell multiome data using atlas-scale external data

  Accurate context-specific gene regulatory network inference is impeded by limited independent data points and reliance on expression data alone.

  Biology & Life Sciences · 2024 · ai assisted · 6/10 importance

• Deep learning the cis-regulatory code for gene expression in selected model plants

  Understanding how non-coding regulatory DNA sequences determine gene expression levels in four plant species, including linking genetic variation to expression changes.

  Biology & Life Sciences · 2024 · partially solved · 6/10 importance

• Accurate Prediction of Protein Structural Flexibility by Deep Learning Integrating Intricate Atomic Structures and Cryo-EM Density Information

  Computationally predicting protein structural flexibility/dynamics was challenging and existing methods were inaccurate.

  Biology & Life Sciences · 2024 · partially solved · 6/10 importance

• Machine learning-guided co-optimization of fitness and diversity facilitates combinatorial library design in enzyme engineering

  Designing combinatorial mutation libraries that balance fitness and diversity is difficult, especially for poorly characterized or unknown enzyme functions.

  Biology & Life Sciences · 2024 · solved · 6/10 importance

• Deep learning enhancing guide RNA design for CRISPR/Cas12a‐based diagnostics

  Designing effective crRNA guides for Cas12a-based nucleic acid detection is challenging and time-consuming, slowing development of rapid pathogen tests.

  Biology & Life Sciences · 2024 · ai assisted · 6/10 importance

• Diffusion-based deep learning method for augmenting ultrastructural imaging and volume electron microscopy

  Electron microscopy of large biological volumes faces a trade-off between imaging speed and quality, leaving isotropic 3D nanoscale imaging unachievable.

  Biology & Life Sciences · 2024 · partially solved · 6/10 importance

• Machine Learning-Guided Optimization of p -Coumaric Acid Production in Yeast

  Optimizing microbial cell factories (p-coumaric acid production in yeast) through DBTL cycles is slow without effective links between phases.

  Biology & Life Sciences · 2024 · solved · 6/10 importance

• Deep model predictive control of gene expression in thousands of single cells

  Researchers could only passively observe natural gene expression dynamics in cells; they needed a way to actively impose specific, cell-specific expression dynamics in individual live cells.

  Biology & Life Sciences · 2024 · solved · 6/10 importance

• De novo design of buttressed loops for sculpting protein functions

  Designing multiple structured loops at protein functional sites was extremely difficult because loops are intrinsically flexible and irregular.

  Biology & Life Sciences · 2024 · solved · 6/10 importance

• Learning to quantify uncertainty in off-target activity for CRISPR guide RNAs

  Off-target effects limit CRISPR clinical use, and current point predictions do not capture the range of possible outcomes.

  Biology & Life Sciences · 2024 · ai assisted · 6/10 importance

• Protein structure prediction with in-cell photo-crosslinking mass spectrometry and deep learning

  Predicting accurate structures for challenging proteins, such as those undergoing conformational changes or with few homologous sequences, where AlphaFold2 underperforms.

  Biology & Life Sciences · 2023 · partially solved · 6/10 importance

• Instance segmentation of mitochondria in electron microscopy images with a generalist deep learning model trained on a diverse dataset

  Automatically annotating each mitochondrion accurately in any 2D or volume electron microscopy image was an unsolved computational challenge.

  Biology & Life Sciences · 2023 · solved · 6/10 importance

• Modeling CRISPR-Cas13d on-target and off-target effects using machine learning approaches

  Accurately predicting the on-target efficiency and off-target effects of guide RNAs in the CRISPR-Cas13d RNA editing system.

  Biology & Life Sciences · 2023 · ai assisted · 6/10 importance

• Deep self-learning enables fast, high-fidelity isotropic resolution restoration for volumetric fluorescence microscopy

  Fluorescence microscopes capture 3D images with much poorer depth-axis than lateral resolution, degrading the quality, reconstruction and analysis of 3D volume images.

  Biology & Life Sciences · 2023 · partially solved · 6/10 importance

• Deep Learning-Based Modeling of Drug–Target Interaction Prediction Incorporating Binding Site Information of Proteins

  Predicting unknown interactions between candidate drugs and protein targets in early drug discovery is slow and computationally costly.

  Biology & Life Sciences · 2023 · ai assisted · 6/10 importance

• Data-driven strategies for the computational design of enzyme thermal stability: trends, perspectives, and prospects

  Designing thermally stable enzymes for industry traditionally requires costly, arduous experiments (directed evolution, rational design) across an enormous protein sequence space.

  Biology & Life Sciences · 2023 · ai assisted · 6/10 importance

• Prediction of base editor off-targets by deep learning

  Base editors frequently induce unwanted Cas9-dependent off-target DNA mutations, and researchers lacked tools to predict where these off-targets occur.

  Biology & Life Sciences · 2023 · partially solved · 6/10 importance

• CRISPR–Cas9 gRNA efficiency prediction: an overview of predictive tools and the role of deep learning

  Designing efficient and specific guide RNAs for CRISPR-Cas9 gene editing is difficult, and many predictive computational tools exist but their performance and best-use scenarios are unclear.

  Biology & Life Sciences · 2022 · ai assisted · 6/10 importance

• Ig-VAE: Generative modeling of protein structure by direct 3D coordinate generation

  Designing class-specific protein backbones, such as immunoglobulins, for structure-based design tasks like binding interfaces was lacking generative methods.

  Biology & Life Sciences · 2022 · ai assisted · 6/10 importance

• LM-GVP: an extensible sequence and structure informed deep learning framework for protein property prediction

  Predicting protein properties such as fluorescence, protease stability, and function from sequence and structure, to speed protein engineering and drug development.

  Biology & Life Sciences · 2022 · partially solved · 6/10 importance

• SDNN-PPI: self-attention with deep neural network effect on protein-protein interaction prediction

  Identifying protein-protein interactions by wet-lab experiments is costly and time-consuming.

  Biology & Life Sciences · 2022 · ai assisted · 6/10 importance

• Deep learning enables reference-free isotropic super-resolution for volumetric fluorescence microscopy

  Volumetric fluorescence microscopy produces images with worse axial than lateral resolution (anisotropy), degrading 3D imaging of biological samples.

  Biology & Life Sciences · 2022 · solved · 6/10 importance

• Deep learning for protein secondary structure prediction: Pre and post-AlphaFold

  Predicting protein secondary structure from amino acid sequence is a long-standing computational biology challenge.

  Biology & Life Sciences · 2022 · partially solved · 6/10 importance

• Learning deep representations of enzyme thermal adaptation

  The relationship between protein sequences and thermal adaptation is poorly understood, hindering engineering of thermostable enzymes.

  Biology & Life Sciences · 2022 · ai assisted · 6/10 importance

• HyperAttentionDTI: improving drug–protein interaction prediction by sequence-based deep learning with attention mechanism

  Identifying drug-target interactions experimentally is slow and costly; accurate in-silico prediction could shorten drug development and repurposing timelines.

  Biology & Life Sciences · 2021 · ai assisted · 6/10 importance

• Robust ecological analysis of camera trap data labelled by a machine learning model

  Labelling the millions of images generated by camera trap arrays is too slow, causing long delays between data collection and ecological inference, which impedes conservation.

  Biology & Life Sciences · 2021 · partially solved · 6/10 importance

• DockStream: a docking wrapper to enhance de novo molecular design

  Generative molecular design models struggle to produce compounds that are actually active against a biological target.

  Biology & Life Sciences · 2021 · ai assisted · 6/10 importance

• Enhancing CRISPR-Cas9 gRNA efficiency prediction by data integration and deep learning

  Designing CRISPR gRNAs requires accurate on-target efficiency predictions, which existing tools could not provide well enough.

  Biology & Life Sciences · 2021 · solved · 6/10 importance

• Deep learning-based enhancement of epigenomics data with AtacWorks

  Low cell count, low-coverage or noisy ATAC-seq data limits detection of active regulatory regions in the genome.

  Biology & Life Sciences · 2021 · solved · 6/10 importance

• A deep learning approach to automate whole‐genome prediction of diverse epigenomic modifications in plants

  Multiple factors limit the scientific utility of plant epigenomic datasets, making whole-genome prediction of diverse epigenomic modifications difficult.

  Biology & Life Sciences · 2021 · solved · 6/10 importance

• An effective self-supervised framework for learning expressive molecular global representations to drug discovery

  Producing expressive molecular representations for drug discovery is hard because labeled data is scarce and supervised models generalize poorly.

  Biology & Life Sciences · 2021 · ai assisted · 6/10 importance

• EDLMFC: an ensemble deep learning framework with multi-scale features combination for ncRNA–protein interaction prediction

  Predicting interactions between non-coding RNAs and proteins computationally, since experimental methods are time-consuming and labor-intensive.

  Biology & Life Sciences · 2021 · ai assisted · 6/10 importance

• C-SVR Crispr: Prediction of CRISPR/Cas12 guideRNA activity using deep learning models

  CRISPR gene editing is limited by low guide RNA activity, and predicting gRNA activity (indel frequency) in advance is difficult.

  Biology & Life Sciences · 2021 · ai assisted · 6/10 importance

• Application of machine learning and genetic optimization algorithms for modeling and optimizing soybean yield using its component traits

  Predicting total soybean seed yield from yield component traits to support breeding higher-yielding varieties.

  Biology & Life Sciences · 2021 · ai assisted · 6/10 importance

• Deep learning enables structured illumination microscopy with low light levels and enhanced speed

  Structured illumination microscopy needs intense illumination and many acquisitions per image, causing photobleaching and limiting live-cell super-resolution imaging.

  Biology & Life Sciences · 2020 · solved · 6/10 importance

• Cross-species regulatory sequence activity prediction

  Regulatory sequence activity models were trained mostly on human data, leaving model organism genomes underused for gene regulation analysis.

  Biology & Life Sciences · 2020 · ai assisted · 6/10 importance

• DeepWAS: Multivariate genotype-phenotype associations by directly integrating regulatory information using deep learning

  GWAS identify disease-associated genetic variants but do not directly link them to regulatory mechanisms, which are only inferred in post-hoc analyses.

  Biology & Life Sciences · 2020 · ai assisted · 6/10 importance

• A Novel Hybrid CNN-SVR for CRISPR/Cas9 Guide RNA Activity Prediction

  Accurately predicting CRISPR/Cas9 guide RNA on-target efficacy is critical for effective genome editing, but existing methods need improvement.

  Biology & Life Sciences · 2020 · ai assisted · 6/10 importance

• DNSS2 : Improved ab initio protein secondary structure prediction using advanced deep learning architectures

  Accurately predicting protein secondary structure (alpha-helix, beta-strand, coil) from sequence is a crucial step for contact and ab initio tertiary structure prediction.

  Biology & Life Sciences · 2020 · partially solved · 6/10 importance

• Expansion of RiPP biosynthetic space through integration of pan-genomics and machine learning uncovers a novel class of lanthipeptides

  Biosynthetic gene clusters for new natural product classes escape attention in genome sequences; known RiPP subclasses may be only the tip of an iceberg.

  Biology & Life Sciences · 2020 · solved · 6/10 importance

• Deep learning-enabled efficient image restoration for 3D microscopy of turbid biological specimens

  Light scattering by biological specimens blurs deep-tissue images, limiting 3D fluorescence microscopy in live imaging.

  Biology & Life Sciences · 2020 · partially solved · 6/10 importance

• Identifying Regulatory Elements via Deep Learning

  Identifying gene regulatory elements such as protein-DNA binding sites from DNA/RNA sequence and epigenomic data.

  Biology & Life Sciences · 2020 · ai assisted · 6/10 importance

• Deep learning for inferring transcription factor binding sites

  Identifying where transcription factors bind on DNA, which is difficult and costly to determine experimentally.

  Biology & Life Sciences · 2020 · ai assisted · 6/10 importance

• Brain age prediction using deep learning uncovers associated sequence variants

  Predicting brain age from structural MRI and identifying genetic sequence variants associated with the gap between predicted and chronological age.

  Biology & Life Sciences · 2019 · solved · 6/10 importance

• Optimized CRISPR guide RNA design for two high-fidelity Cas9 variants by deep learning

  High-fidelity Cas9 variants are valuable for genome editing but their use is hampered by lack of knowledge governing guide RNA activity.

  Biology & Life Sciences · 2019 · solved · 6/10 importance

• SpCas9 activity prediction by DeepSpCas9, a deep learning–based model with high generalization performance

  Predicting SpCas9 gene-editing activity at arbitrary target sequences was unreliable, limiting CRISPR-based editing.

  Biology & Life Sciences · 2019 · solved · 6/10 importance

• MMSplice: modular modeling improves the predictions of genetic variant effects on splicing

  Predicting how genetic variants affect splicing (exon skipping, splice site choice, pathogenicity) is difficult but highly relevant to human genetics.

  Biology & Life Sciences · 2019 · solved · 6/10 importance

• Unlocking HDR-mediated nucleotide editing by identifying high-efficiency target sites using machine learning

  Precise single-nucleotide editing via HDR is inefficient, hampering validation of genomic disease associations.

  Biology & Life Sciences · 2019 · partially solved · 6/10 importance

• Comparing two deep learning sequence-based models for protein-protein interaction prediction

  Predicting which human proteins interact with each other is difficult and costly to determine experimentally, and existing deep learning PPI predictors risk overfitting and information leak.

  Biology & Life Sciences · 2019 · ai assisted · 6/10 importance

• DeepPVP: phenotype-based prioritization of causative variants using deep learning

  Identifying the causative variant among thousands of candidates in a patient's whole exome or genome sequence is a major challenge.

  Biology & Life Sciences · 2019 · ai assisted · 6/10 importance

• Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning

  Extracting information from millions of camera-trap wildlife images is expensive, time-consuming manual work.

  Biology & Life Sciences · 2018 · solved · 6/10 importance

• DeepCRISPR: optimized CRISPR guide RNA design by deep learning

  Accurately predicting sgRNA on-target knockout efficacy and off-target profile is a major challenge for effective CRISPR application.

  Biology & Life Sciences · 2018 · ai assisted · 6/10 importance

• Machine learning to classify animal species in camera trap images: Applications in ecology

  Camera trap studies produce millions of images that normally must be inspected manually to identify animal species.

  Biology & Life Sciences · 2018 · partially solved · 6/10 importance

• Predicting protein–protein interactions through sequence-based deep learning

  Experimental protein-protein interaction (PPI) data has low coverage and is noisy, so new PPIs and errors in existing data are hard to identify.

  Biology & Life Sciences · 2018 · partially solved · 6/10 importance

• A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data

  Bioengineers could not accurately predict how modifying an organism's genotype changes metabolic pathway behavior, and classical kinetic models are slow and expertise-intensive to build.

  Biology & Life Sciences · 2018 · partially solved · 6/10 importance

• Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome Reconstruction

  Reconstructing connectomes requires accurately segmenting neurons in large-scale electron microscopy images, which existing methods could not do with sufficient accuracy and scalability.

  Biology & Life Sciences · 2018 · partially solved · 6/10 importance

• Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models

  Experimental data on enzyme turnover numbers is sparse and noisy, limiting quantitative understanding of organism growth, proteome composition and physiology.

  Biology & Life Sciences · 2018 · partially solved · 6/10 importance

• Off-target predictions in CRISPR-Cas9 gene editing using deep learning

  Existing methods for predicting off-target mutations in CRISPR-Cas9 gene editing rely on mismatch scores, cannot scale with growing data, and lack clinical-level precision.

  Biology & Life Sciences · 2018 · ai assisted · 6/10 importance

• DeepPPI: Boosting Prediction of Protein–Protein Interactions with Deep Neural Networks

  Predicting which proteins physically interact is difficult, and most disease-associated protein variants have unknown interaction mechanisms.

  Biology & Life Sciences · 2017 · ai assisted · 6/10 importance

• A machine learning approach for predicting CRISPR-Cas9 cleavage efficiencies and patterns underlying its mechanism of action

  CRISPR-Cas9 sgRNAs can cleave unintended off-target genomic sites, and existing design tools poorly predict cleavage propensity.

  Biology & Life Sciences · 2017 · partially solved · 6/10 importance

• Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks

  The functional mechanisms of most disease-associated noncoding genetic variants are unknown, and the regulatory code of gene expression is incompletely understood.

  Biology & Life Sciences · 2016 · ai assisted · 6/10 importance

• Deep Learning in Label-free Cell Classification

  Label-free cell assays rely on single features, lack sufficient differentiation, and have low throughput, limiting cancer diagnostics and drug development.

  Biology & Life Sciences · 2016 · solved · 6/10 importance

• Deep Contextual Networks for Neuronal Structure Segmentation

  Reconstructing the connectome from electron microscopy images is infeasible by hand, as human annotation of the massive data could take decades.

  Biology & Life Sciences · 2016 · ai assisted · 6/10 importance

• Crowdsourcing the creation of image segmentation algorithms for connectomics

  Automating reconstruction of neural circuits via 2D segmentation of electron microscopic brain images.

  Biology & Life Sciences · 2015 · partially solved · 6/10 importance

• A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction

  Ab initio prediction of protein secondary structure, where accuracy had stagnated around 80 percent.

  Biology & Life Sciences · 2014 · ai assisted · 6/10 importance

• Deep learning–based approaches for weed detection in crops

  Detecting weeds in crops is difficult for traditional machine vision, which lacks robustness, scalability and recognition accuracy in variable field conditions.

  Biology & Life Sciences · 2026 · ai assisted · 5/10 importance

• Accelerated enzyme engineering by machine-learning guided cell-free expression

  Engineering enzymes is slow because generating large sequence-function datasets for predictive design is difficult.

  Biology & Life Sciences · 2025 · solved · 5/10 importance

• Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy

  Engineering industrial enzymes that combine high activity with thermostability is difficult due to the stability-activity trade-off.

  Biology & Life Sciences · 2025 · ai assisted · 5/10 importance

• Deep learning-based aberration compensation improves contrast and resolution in fluorescence microscopy

  Optical aberrations reduce signal, contrast, and resolution when imaging thick samples in fluorescence microscopy.

  Biology & Life Sciences · 2025 · solved · 5/10 importance

• Spatial gene expression at single-cell resolution from histology using deep learning with GHIST

  Spatially resolved transcriptomics is costly and complex, and existing methods to predict gene expression from histology images have limited accuracy and spatial resolution.

  Biology & Life Sciences · 2025 · ai assisted · 5/10 importance

• DeepEnzyme: a robust deep learning model for improved enzyme turnover number prediction by utilizing features of protein 3D-structures

  Experimentally measuring enzyme turnover numbers (kcat) is time-consuming, and existing deep learning predictors lack accuracy and robustness especially for enzymes with low sequence similarity to training data.

  Biology & Life Sciences · 2024 · ai assisted · 5/10 importance

• Machine Learning to Predict Enzyme–Substrate Interactions in Elucidation of Synthesis Pathways: A Review

  Experimentally determining enzyme-substrate interactions is slow and costly, and physics-based simulations are too slow for large search spaces.

  Biology & Life Sciences · 2024 · ai assisted · 5/10 importance

• A new paradigm for applying deep learning to protein–ligand interaction prediction

  Predicting how small molecules dock into protein targets and how strongly they bind is slow and error-prone in drug design.

  Biology & Life Sciences · 2024 · ai assisted · 5/10 importance

• HydraProt: A New Deep Learning Tool for Fast and Accurate Prediction of Water Molecule Positions for Protein Structures

  Accurately predicting the precise positions of water molecules around protein structures remains a significant challenge.

  Biology & Life Sciences · 2024 · partially solved · 5/10 importance

• Using deep learning to quantify neuronal activation from single-cell and spatial transcriptomic data

  Measuring neuronal activation from single-cell and spatial transcriptomic data was difficult; researchers needed a way to estimate activity-induced gene expression at cellular resolution.

  Biology & Life Sciences · 2024 · ai assisted · 5/10 importance

• Deep learning in fluorescence imaging and analysis

  Fluorescence imaging faces challenges in efficiently acquiring high signal-to-noise ratio images, improving spatiotemporal resolution, and conducting precise quantitative analysis.

  Biology & Life Sciences · 2024 · ai assisted · 5/10 importance

• Antibody design using deep learning: from sequence and structure design to affinity maturation

  Developing antibodies is slow and costly; the paper reviews how deep learning can streamline antibody sequence/structure design, docking and affinity maturation.

  Biology & Life Sciences · 2024 · ai assisted · 5/10 importance

• Testing the reliability of an AI-based large language model to extract ecological information from the scientific literature

  Manually extracting ecological data from scientific literature is slow, limiting the creation of large ecological databases.

  Biology & Life Sciences · 2024 · partially solved · 5/10 importance

• Single-frame deep-learning super-resolution microscopy for intracellular dynamics imaging

  Single-molecule localization microscopy needs thousands of frames, making imaging slow and phototoxic and blocking observation of fast intracellular dynamics.

  Biology & Life Sciences · 2023 · solved · 5/10 importance

• Enhancing image resolution of confocal fluorescence microscopy with deep learning

  Super-resolution fluorescence microscopy requires special fluorophores, sophisticated optics, or long acquisition and computational times.

  Biology & Life Sciences · 2023 · solved · 5/10 importance

• Inferring single-cell transcriptomic dynamics with structured latent gene expression dynamics

  Inferring developmental trajectories and gene expression dynamics from single-cell RNA sequencing data, where traditional RNA velocity assumptions fail with multiple lineages or time-dependent rates.

  Biology & Life Sciences · 2023 · ai assisted · 5/10 importance

• A Novel Machine-Learning Approach to Predict Stress-Responsive Genes in Arabidopsis

  Identifying key stress-responsive genes in Arabidopsis under salt, heat, cold, high-light and flagellin stress to enhance crop tolerance.

  Biology & Life Sciences · 2023 · ai assisted · 5/10 importance

• DeepBacs for multi-task bacterial image analysis using open-source deep learning approaches

  Analysing bacterial microscopy images (segmentation, growth-stage classification, phenotyping) is laborious, and live-cell imaging is limited by phototoxicity.

  Biology & Life Sciences · 2022 · ai assisted · 5/10 importance

• DeLTA 2.0: A deep learning pipeline for quantifying single-cell spatial and temporal dynamics

  Analyzing time-lapse microscopy images of single cells is a major bottleneck because existing segmentation and tracking tools require human input, are setup-specific, or lack accuracy.

  Biology & Life Sciences · 2022 · solved · 5/10 importance

• Human vs. machine: Detecting wildlife in camera trap images

  Ecologists must review enormous volumes of camera trap images to identify wildlife, which delays research and actionable insights.

  Biology & Life Sciences · 2022 · ai assisted · 5/10 importance

• Therapeutic enzyme engineering using a generative neural network

  Finding enzyme variants that improve mRNA therapeutic potency is extremely slow because the possible sequence space is too vast to search experimentally or accurately computationally.

  Biology & Life Sciences · 2022 · ai assisted · 5/10 importance

• Can CNN‐based species classification generalise across variation in habitat within a camera trap survey?

  Manually annotating vast numbers of camera trap images is extremely time-consuming, and automated classifiers may fail to generalise across habitats with different disturbance levels.

  Biology & Life Sciences · 2022 · partially solved · 5/10 importance

• dynDeepDRIM: a dynamic deep learning model to infer direct regulatory interactions using time-course single-cell gene expression data

  Reconstructing cell-type-specific gene regulatory networks from time-course single-cell RNA-seq data, which existing tools could not do while handling multiple time points and scRNA-seq characteristics.

  Biology & Life Sciences · 2022 · ai assisted · 5/10 importance

• A novel deep learning-based 3D cell segmentation framework for future image-based disease detection

  Accurately segmenting densely packed cells in 3D cell membrane images is difficult, and existing deep learning methods require many manually selected hyperparameters tuned per dataset.

  Biology & Life Sciences · 2022 · ai assisted · 5/10 importance

• Microbiome meta-analysis and cross-disease comparison enabled by the SIAMCAT machine learning toolbox

  Machine learning on human microbiome data lacked dedicated software and suffered from overoptimistic evaluation and poor cross-study generalization.

  Biology & Life Sciences · 2021 · solved · 5/10 importance

• A deep-learning framework for multi-level peptide–protein interaction prediction

  Identifying which peptides bind which proteins is essential for designing peptide therapeutics, but most existing computational predictors depend on high-resolution structural data.

  Biology & Life Sciences · 2021 · solved · 5/10 importance

• Unsupervised content-preserving transformation for optical microscopy

  Supervised deep learning for optical microscopy image transformation requires laborious, error-prone paired annotated training data, limiting wider use.

  Biology & Life Sciences · 2021 · partially solved · 5/10 importance

• Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production

  Fatty acyl reductase enzymes were a bottleneck to high-flux microbial production of fatty alcohols, limiting bioproduction yields.

  Biology & Life Sciences · 2021 · solved · 5/10 importance

• Deep learning of gene relationships from single cell time-course expression data

  Inferring regulatory and signaling relationships between genes from single-cell time-course RNA-Seq data lacked methods, as existing tools were built for bulk data.

  Biology & Life Sciences · 2021 · ai assisted · 5/10 importance

• DEEPsc: A Deep Learning-Based Map Connecting Single-Cell Transcriptomics and Spatial Imaging Data

  Single-cell RNA sequencing loses the spatial arrangement of cells within tissue, and existing methods to map spatial information back lack comprehensive accuracy and robustness analysis.

  Biology & Life Sciences · 2021 · ai assisted · 5/10 importance

• Fluorescence microscopy datasets for training deep neural networks

  Deep learning methods that improve fluorescence microscopy signal-to-noise (allowing shorter exposures and less photobleaching/phototoxicity) require large paired training datasets that were lacking.

  Biology & Life Sciences · 2021 · ai assisted · 5/10 importance

• DeepComplex: A Web Server of Predicting Protein Complex Structures by Deep Learning Inter-chain Contact Prediction and Distance-Based Modelling

  Predicting the quaternary structure of dimeric protein complexes, which is useful for function analysis, protein engineering and drug design.

  Biology & Life Sciences · 2021 · ai assisted · 5/10 importance

• TransformerCPI: improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments

  Predicting compound-protein interactions from protein sequence alone, while avoiding dataset pitfalls and hidden ligand bias that overestimate performance.

  Biology & Life Sciences · 2020 · partially solved · 5/10 importance

• A machine learning Automated Recommendation Tool for synthetic biology

  Engineering microbes to produce valuable molecules (biofuels, drugs) is slow because traditional synthetic biology relies on ad-hoc trial-and-error practices.

  Biology & Life Sciences · 2020 · ai assisted · 5/10 importance

• Solo: Doublet Identification in Single-Cell RNA-Seq via Semi-Supervised Deep Learning

  In single-cell RNA sequencing, 'doublets' (two or more cells sharing one barcode) violate the technology's premise and can lead to incorrect biological inferences.

  Biology & Life Sciences · 2020 · solved · 5/10 importance

• Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism

  Predicting which genetic designs improve yeast tryptophan production is difficult, making metabolic engineering slow and inefficient.

  Biology & Life Sciences · 2020 · partially solved · 5/10 importance

• Deep learning–based cell composition analysis from tissue expression profiles

  Inferring the cellular composition of bulk tissue from gene expression profiles was difficult and sensitive to noise and bias.

  Biology & Life Sciences · 2020 · solved · 5/10 importance

• DeLTA: Automated cell segmentation, tracking, and lineage reconstruction using deep learning

  Analyzing time-lapse microscopy movies of E. coli cells in a mother machine required slow, human-supervised segmentation, tracking and lineage reconstruction, limiting accuracy and throughput.

  Biology & Life Sciences · 2020 · solved · 5/10 importance

• Generalizable sgRNA design for improved CRISPR/Cas9 editing efficiency

  Existing sgRNA design tools lacked potency and generalizability across experimental conditions, limiting CRISPR/Cas9 editing efficiency.

  Biology & Life Sciences · 2020 · ai assisted · 5/10 importance

• Imputation of single‐cell gene expression with an autoencoder neural network

  High dropout rates in single-cell RNA-seq produce many false zero gene counts that complicate downstream analyses.

  Biology & Life Sciences · 2020 · solved · 5/10 importance

• mAML: an automated machine learning pipeline with a microbiome repository for human disease classification

  Building machine learning models from human microbiome data for disease classification is tedious and requires manual ML expertise.

  Biology & Life Sciences · 2020 · ai assisted · 5/10 importance

• DISC: a highly scalable and accurate inference of gene expression and structure for single-cell transcriptomes using semi-supervised deep learning

  Dropouts distort gene expression and misclassify cell types in single-cell transcriptome data.

  Biology & Life Sciences · 2020 · partially solved · 5/10 importance

• Microbiome meta-analysis and cross-disease comparison enabled by the SIAMCAT machine-learning toolbox

  Machine-learning models built on human microbiome data suffered from scarce metagenomics-specific software, overoptimistic evaluation, and poor generalization across studies.

  Biology & Life Sciences · 2020 · partially solved · 5/10 importance

• Forecasting severe grape downy mildew attacks using machine learning

  Grape downy mildew in Bordeaux vineyards requires repetitive fungicide spraying (average 10.1 treatments in 2013); growers need to identify heavily attacked vineyards to target treatments.

  Biology & Life Sciences · 2020 · ai assisted · 5/10 importance

• Deep learning for inferring gene relationships from single-cell expression data

  Inferring gene-gene relationships (coexpression, functional assignment, pathway reconstruction, causality) from single-cell expression data.

  Biology & Life Sciences · 2019 · ai assisted · 5/10 importance

• Cryo-CARE: Content-Aware Image Restoration for Cryo-Transmission Electron Microscopy Data

  Cryo-transmission electron microscopy images are extremely noisy and low-contrast, making the acquired biological data hard to interpret and process.

  Biology & Life Sciences · 2019 · ai assisted · 5/10 importance

• Protein Function Prediction: From Traditional Classifier to Deep Learning

  Predicting the biological function of proteins from sequence and interaction data, a task where traditional classifiers underperform.

  Biology & Life Sciences · 2019 · partially solved · 5/10 importance

• Can Machine Learning Revolutionize Directed Evolution of Selective Enzymes?

  Directed evolution of enzymes generates huge numbers of variants, making it slow to find enzymes with improved stereoselectivity and activity.

  Biology & Life Sciences · 2019 · ai assisted · 5/10 importance

• Wildlife surveillance using deep learning methods

  Screening still and video camera surveillance of wild animals for species of interest is laborious and expensive, hindering wildlife conflict management such as bovine tuberculosis control.

  Biology & Life Sciences · 2019 · ai assisted · 5/10 importance

• Combined network analysis and machine learning allows the prediction of metabolic pathways from tomato metabolomics data

  Detecting metabolic pathways traditionally relied on gene annotation; prediction from metabolomics data was needed.

  Biology & Life Sciences · 2019 · partially solved · 5/10 importance

• MRCNN: a deep learning model for regression of genome-wide DNA methylation

  Accurately predicting genome-wide DNA methylation levels is difficult; existing methods require many features or only handle hyper/hypomethylation.

  Biology & Life Sciences · 2019 · partially solved · 5/10 importance

• Digitaldlsorter: Deep-Learning on scRNA-Seq to Deconvolute Gene Expression Data

  Bulk RNA-Seq cannot distinguish whether observed expression changes come from shifting cell-type proportions or aberrant behavior of a specific cell type, while single-cell experiments remain complex and expensive.

  Biology & Life Sciences · 2019 · ai assisted · 5/10 importance

• CRISPRLearner: A Deep Learning-Based System to Predict CRISPR/Cas9 sgRNA On-Target Cleavage Efficiency

  Predicting the on-target cleavage efficiency of CRISPR/Cas9 sgRNA sequences so researchers can evaluate and redesign inefficient guides before experiments.

  Biology & Life Sciences · 2019 · ai assisted · 5/10 importance

• Learned protein embeddings for machine learning

  Converting protein sequences into vector representations that let machine-learning models predict biological properties of unseen sequences.

  Biology & Life Sciences · 2018 · ai assisted · 5/10 importance

• Single‐sequence‐based prediction of protein secondary structures and solvent accessibility by deep whole‐sequence learning

  Predicting protein secondary structure and solvent accessibility from a single sequence alone, without relying on evolutionary information from multiple sequence alignments.

  Biology & Life Sciences · 2018 · partially solved · 5/10 importance

• Protein–Protein Interactions Prediction via Multimodal Deep Polynomial Network and Regularized Extreme Learning Machine

  Predicting which proteins interact with which others, a key task in understanding cellular processes, using computational methods instead of costly experiments.

  Biology & Life Sciences · 2018 · ai assisted · 5/10 importance

• Sequence-based prediction of protein protein interaction using a deep-learning algorithm

  Accurate high-throughput identification of protein-protein interactions is needed to understand protein function, disease occurrence and therapy design, but the robustness of existing computational methods on external datasets was unknown.

  Biology & Life Sciences · 2017 · partially solved · 5/10 importance

• Deep learning of the regulatory grammar of yeast 5′ untranslated regions from 500,000 random sequences

  Predicting protein expression from DNA sequence alone remains poor due to limited understanding of cis-regulatory grammar, hampering design of engineered genes for synthetic biology.

  Biology & Life Sciences · 2017 · partially solved · 5/10 importance

• Imputation for transcription factor binding predictions based on deep learning

  ChIP-seq data covers only a small fraction of possible transcription factor–cell line combinations, leaving most cell-specific TF binding patterns unknown.

  Biology & Life Sciences · 2017 · partially solved · 5/10 importance

• DeepInteract: Deep Neural Network Based Protein-Protein Interaction Prediction Tool

  Predicting which proteins physically interact is slow and costly to determine experimentally, yet essential for understanding cellular mechanisms.

  Biology & Life Sciences · 2017 · partially solved · 5/10 importance

• Protein-Protein Interaction Interface Residue Pair Prediction Based on Deep Learning Architecture

  Correctly predicting which residue pairs form the interface between two interacting proteins remains an open question.

  Biology & Life Sciences · 2017 · ai assisted · 5/10 importance

• DeepChrome: deep-learning for predicting gene expression from histone modifications

  Predicting gene expression levels from histone modification signals to understand combinatorial effects in gene regulation.

  Biology & Life Sciences · 2016 · ai assisted · 5/10 importance

• PEDLA: predicting enhancers with a deep learning-based algorithmic framework

  Systematically and precisely predicting transcriptional enhancers from massively heterogeneous genomic data remained a major challenge.

  Biology & Life Sciences · 2016 · partially solved · 5/10 importance

• Improving prediction of secondary structure, local backbone angles and solvent accessible surface area of proteins by iterative deep learning

  Predicting protein structural features (secondary structure, backbone angles, solvent accessibility) directly from sequence is a challenging problem.

  Biology & Life Sciences · 2015 · partially solved · 5/10 importance

• Automated identification of animal species in camera trap images

  Manually identifying animal species in the huge volumes of images generated by camera traps is too slow for biodiversity monitoring.

  Biology & Life Sciences · 2013 · ai assisted · 5/10 importance

• A novel strategy for classifying the output from an in silicovaccine discovery pipeline for eukaryotic pathogens using machine learning algorithms

  In silico vaccine candidate pipelines for eukaryotic pathogens produce many false candidates that would require expensive laboratory validation.

  Biology & Life Sciences · 2013 · ai assisted · 5/10 importance

• Effects of data transformation and model selection on feature importance in microbiome classification data

  Classifying healthy versus diseased individuals from gut microbiome data is difficult due to data sparsity, compositionality, and population-specificity.

  Biology & Life Sciences · 2025 · ai assisted · 4/10 importance

• Generative machine learning produces kinetic models that accurately characterize intracellular metabolic states

  Determining kinetic parameters for large-scale metabolic models is difficult, hindering integration of omics data and broader adoption of these models.

  Biology & Life Sciences · 2024 · ai assisted · 4/10 importance

• Being confident in confidence scores: calibration in deep learning models for camera trap image sequences

  Automated deep learning classifiers for camera trap images produce confidence scores that may not be interpretable as true probabilities, limiting their use in ecological tasks like occupancy estimation.

  Biology & Life Sciences · 2024 · ai assisted · 4/10 importance

• Ensemble deep learning model for protein secondary structure prediction using NLP metrics and explainable AI

  Predicting protein secondary structure accurately is difficult, and better predictions are needed to understand protein function.

  Biology & Life Sciences · 2024 · partially solved · 4/10 importance

• Cross-modality transformations in biological microscopy enabled by deep learning

  Deep-learning methods can virtually transform microscopy images across optical modalities, but biologists lack a unified overview, limiting adoption in daily research and clinical trials.

  Biology & Life Sciences · 2024 · ai assisted · 4/10 importance

• Deep learning classification method for boar sperm morphology analysis

  Boar semen morphology and acrosome health lack fast, objective analysis methods; manual microscope counting is subjective.

  Biology & Life Sciences · 2024 · ai assisted · 4/10 importance

• Advancing Enzyme’s Stability and Catalytic Efficiency through Synergy of Force-Field Calculations, Evolutionary Analysis, and Machine Learning

  Industrial enzymes require thermostability, but designing stable variants of haloalkane dehalogenase DhaA115 is challenging.

  Biology & Life Sciences · 2023 · ai assisted · 4/10 importance

• Simulated Design–Build–Test–Learn Cycles for Consistent Comparison of Machine Learning Methods in Metabolic Engineering

  No framework existed to consistently test machine learning methods across multiple design-build-test-learn cycles in combinatorial strain optimization.

  Biology & Life Sciences · 2023 · partially solved · 4/10 importance

• Deep learning enables fast, gentle STED microscopy

  STED super-resolution microscopy damages and bleaches samples because of long pixel dwell times, limiting live-cell imaging.

  Biology & Life Sciences · 2023 · solved · 4/10 importance

• GeneSegNet: a deep learning framework for cell segmentation by integrating gene expression and imaging

  Identifying cell boundaries and assigning RNA reads to cells in in situ RNA detection data, complicated by noisy training labels.

  Biology & Life Sciences · 2023 · partially solved · 4/10 importance

• A deep learning-based stripe self-correction method for stitched microscopic images

  Stitched fluorescence microscope images contain stripes and artifacts from optics or specimens that degrade image quality and ruin downstream quantitative analysis.

  Biology & Life Sciences · 2023 · solved · 4/10 importance

• Macrocyclization of linear molecules by deep learning to facilitate macrocyclic drug candidates discovery

  Generating macrocyclic analogues of bioactive acyclic molecules is difficult due to vast chemical space.

  Biology & Life Sciences · 2023 · ai assisted · 4/10 importance

• Deep Learning-Based Weed Detection Using UAV Images: A Comparative Study

  Farmers need to automatically detect weeds in crop fields from drone images so they can protect yields.

  Biology & Life Sciences · 2023 · ai assisted · 4/10 importance

• Prediction of pasture yield using machine learning-based optical sensing: a systematic review

  Accurate and reliable predictions of biomass yield are needed for pasture management decisions such as fertilization, irrigation, grazing, and mowing.

  Biology & Life Sciences · 2023 · partially solved · 4/10 importance

• Trends in forensic microbiology: From classical methods to deep learning

  Traditional microbial culture methods in forensic microbiology are slow, costly, and poorly quantitative for tasks like postmortem interval estimation.

  Biology & Life Sciences · 2023 · ai assisted · 4/10 importance

• Insights into Cottonseed Cultivar Identification Using Raman Spectroscopy and Explainable Machine Learning

  Traditional cottonseed cultivar identification is slow and difficult, risking inauthentic seed reaching farmers.

  Biology & Life Sciences · 2023 · ai assisted · 4/10 importance

• Deep Learning-Based TEM Image Analysis for Fully Automated Detection of Gold Nanoparticles Internalized Within Tumor Cell

  Detecting gold nanoparticles inside tumor cells in TEM images is manual, slow, and error-prone with thresholding methods.

  Biology & Life Sciences · 2023 · solved · 4/10 importance

• An evaluation of platforms for processing camera‐trap data using artificial intelligence

  Processing the large volumes of images generated by camera traps is so time-consuming that it limits the efficiency of wildlife surveys.

  Biology & Life Sciences · 2022 · ai assisted · 4/10 importance

• Generative and interpretable machine learning for aptamer design and analysis of in vitro sequence selection

  Obtaining aptamer binders via SELEX requires multiple rounds of experimental selection, and predicting which sequences will bind is difficult.

  Biology & Life Sciences · 2022 · ai assisted · 4/10 importance

• DNAcycP: a deep learning tool for DNA cyclizability prediction

  Measuring intrinsic DNA cyclizability/bendability experimentally (via loop-seq) is laborious; a fast computational predictor was needed.

  Biology & Life Sciences · 2022 · solved · 4/10 importance

• Machine learning phenomics (MLP) combining deep learning with time-lapse-microscopy for monitoring colorectal adenocarcinoma cells gene expression and drug-response

  Monitoring how colorectal cancer cells respond to therapy and linking gene expression to cell behaviour required new high-throughput phenotyping methods.

  Biology & Life Sciences · 2022 · ai assisted · 4/10 importance

• Deep learning based domain adaptation for mitochondria segmentation on EM volumes

  Deep learning models for mitochondria segmentation in electron microscopy volumes need large annotated datasets and perform poorly on EM data from different tissues or species (domain shift).

  Biology & Life Sciences · 2022 · partially solved · 4/10 importance

• Early yield prediction in different grapevine varieties using computer vision and machine learning

  Predicting grapevine yield early in the season across different varieties to support wine industry yield assessment.

  Biology & Life Sciences · 2022 · partially solved · 4/10 importance

• Machine-Learning-Guided Library Design Cycle for Directed Evolution of Enzymes: The Effects of Training Data Composition on Sequence Space Exploration

  Directed evolution of enzymes is slow, and it was unclear how machine-learning training data composition affects guidance of sequence-space exploration.

  Biology & Life Sciences · 2021 · ai assisted · 4/10 importance

• Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

  Noisy raw images in super-resolution structured illumination microscopy (SR-SIM), e.g. from low excitation power or short exposure, cause reconstruction artifacts.

  Biology & Life Sciences · 2021 · solved · 4/10 importance

• Imaging in focus: An introduction to denoising bioimages in the era of deep learning

  Live-sample fluorescence microscopy must use low light to avoid phototoxicity, producing very noisy images that severely complicate interpretation.

  Biology & Life Sciences · 2021 · ai assisted · 4/10 importance

• AptaNet as a deep learning approach for aptamer–protein interaction prediction

  Identifying which short DNA/RNA aptamers bind to which target proteins is slow and costly to do experimentally. AptaNet was built to predict aptamer-protein interaction pairs computationally.

  Biology & Life Sciences · 2021 · ai assisted · 4/10 importance

• Protein Secondary Structure Prediction With a Reductive Deep Learning Method

  Determining protein secondary structures experimentally via X-ray, cryo-EM or NMR is time-consuming and expensive.

  Biology & Life Sciences · 2021 · ai assisted · 4/10 importance

• A First Step Towards Automated Species Recognition from Camera Trap Images of Mammals Using AI in a European Temperate Forest

  Manually labeling camera trap images of mammals for wildlife monitoring is slow and hard to scale; the paper automates species identification in Białowieża Forest, Poland.

  Biology & Life Sciences · 2021 · partially solved · 4/10 importance

• Deep learning-based real-time detection of neurons in brain slices for in vitro physiology

  Finding a healthy neuron in acute brain slices for patch clamp recording is done manually, is slow, and challenges novices.

  Biology & Life Sciences · 2021 · ai assisted · 4/10 importance

• Enhancement of protein thermostability by three consecutive mutations using loop-walking method and machine learning

  Improving the heat stability of Burkholderia cepacia lipase without assaying all 8,000 possible triple mutants.

  Biology & Life Sciences · 2021 · solved · 4/10 importance

• Learning cis-regulatory principles of ADAR-based RNA editing from CRISPR-mediated mutagenesis

  It was poorly understood how RNA sequence and structure determine the efficiency and specificity of A-to-I RNA editing, hindering interpretation of known editing events and engineering of desired edits.

  Biology & Life Sciences · 2021 · partially solved · 4/10 importance

• Exploration of Machine Learning Approaches for Paddy Yield Prediction in Eastern Part of Tamilnadu

  Predicting paddy yield in the Cauvery Delta Zone, Tamil Nadu, is difficult because yields depend on interacting genotype, environmental and management factors; statistical methods were inaccurate.

  Biology & Life Sciences · 2021 · ai assisted · 4/10 importance

• Automatic improvement of deep learning-based cell segmentation in time-lapse microscopy by neural architecture search

  Deep learning networks for segmenting live cells in time-lapse microscopy are hard and slow to design, requiring expert knowledge.

  Biology & Life Sciences · 2021 · ai assisted · 4/10 importance

• EM-stellar: benchmarking deep learning for electron microscopy image segmentation

  Segmenting cellular ultrastructures in low-contrast, high-resolution electron microscopy datasets is slow and difficult to automate.

  Biology & Life Sciences · 2021 · ai assisted · 4/10 importance

• A Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems

  Machine-learning disease classifiers in microbiome studies are often overoptimistic, irreproducible, and hard to interpret.

  Biology & Life Sciences · 2020 · ai assisted · 4/10 importance

• AutoGrow4: an open-source genetic algorithm for de novo drug design and lead optimization

  Generating novel drug-like molecules and optimizing existing lead compounds is slow and costly in drug discovery.

  Biology & Life Sciences · 2020 · ai assisted · 4/10 importance

• Innovations in Camera Trapping Technology and Approaches: The Integration of Citizen Science and Artificial Intelligence

  Camera traps now collect enormous quantities of footage that researchers struggle to classify, and the paper reviews how citizen science and AI are being integrated to handle this.

  Biology & Life Sciences · 2020 · ai assisted · 4/10 importance

• Automated facial recognition for wildlife that lack unique markings: A deep learning approach for brown bears

  There was no objective visual method to identify individual animals of species lacking unique body markings, such as brown bears.

  Biology & Life Sciences · 2020 · solved · 4/10 importance

• A Hybrid Flux Balance Analysis and Machine Learning Pipeline Elucidates Metabolic Adaptation in Cyanobacteria

  How the cyanobacterium Synechococcus sp. PCC 7002 metabolically adapts to fluctuations in light intensity and salinity was not well understood.

  Biology & Life Sciences · 2020 · ai assisted · 4/10 importance

• neu Print: Analysis Tools for EM Connectomics

  New large-scale connectome reconstructions (tens of thousands of neurons, tens of millions of connections) need easy, efficient analysis tools usable by non-specialists.

  Biology & Life Sciences · 2020 · ai assisted · 4/10 importance

• Automated detection of European wild mammal species in camera trap images with an existing and pre-trained computer vision model

  Camera trap studies generate thousands of images that are expensive and time-consuming to analyze manually.

  Biology & Life Sciences · 2020 · partially solved · 4/10 importance

• Machine learning for faster and smarter fluorescence lifetime imaging microscopy

  Fluorescence lifetime imaging microscopy (FLIM) is useful for biomedical research, but its calculation, analysis and interpretation are complex, slow and computationally expensive.

  Biology & Life Sciences · 2020 · ai assisted · 4/10 importance

• Learning and interpreting the gene regulatory grammar in a deep learning framework

  Limited knowledge of how combinatorial transcription factor binding (regulatory grammar) drives enhancer activity, and difficulty interpreting what deep neural networks learn about regulatory sequences.

  Biology & Life Sciences · 2020 · ai assisted · 4/10 importance

• Practical fluorescence reconstruction microscopy for large samples and low-magnification imaging

  Fluorescence reconstruction microscopy reduces phototoxicity and simplifies sample prep, but is complex to implement and existing benchmarks do not reflect practical value.

  Biology & Life Sciences · 2020 · ai assisted · 4/10 importance

• DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences

  Identifying drug-target interactions experimentally is costly and labor-intensive, and conventional protein descriptors were insufficiently informative for accurate in silico prediction.

  Biology & Life Sciences · 2019 · ai assisted · 4/10 importance

• Fast fit-free analysis of fluorescence lifetime imaging via deep learning

  Fluorescence lifetime imaging requires slow, complex data-fitting to extract quantitative lifetime parameters from images.

  Biology & Life Sciences · 2019 · solved · 4/10 importance

• Optimization of Molecules via Deep Reinforcement Learning

  Optimizing molecules for drug discovery, including maximizing drug-likeness while maintaining similarity to an original molecule during medicinal chemistry lead optimization.

  Biology & Life Sciences · 2019 · partially solved · 4/10 importance

• Comprehensive evaluation of deep learning architectures for prediction of DNA/RNA sequence binding specificities

  The relative merit of CNN, RNN, and hybrid deep learning architectures for predicting DNA- and RNA-binding specificity was unclear from existing studies.

  Biology & Life Sciences · 2019 · ai assisted · 4/10 importance

• Insights and approaches using deep learning to classify wildlife

  Conservationists need to automatically identify and classify wildlife species in large camera-trap image datasets, which is slow and error-prone manually.

  Biology & Life Sciences · 2019 · partially solved · 4/10 importance

• RPITER: A Hierarchical Deep Learning Framework for ncRNA–Protein Interaction Prediction

  Identifying interactions between non-coding RNAs and RNA-binding proteins experimentally is expensive and time-consuming, and computational prediction remains challenging.

  Biology & Life Sciences · 2019 · ai assisted · 4/10 importance

• Prediction of 8-state protein secondary structures by a novel deep learning architecture

  Accurately predicting 8-state protein secondary structure, which serves as an information bridge between primary sequence and tertiary structure for structure-based analysis.

  Biology & Life Sciences · 2018 · partially solved · 4/10 importance

• A Deep Learning Framework for Robust and Accurate Prediction of ncRNA-Protein Interactions Using Evolutionary Information

  Identifying which proteins bind specific non-coding RNAs with wet-lab high-throughput techniques is expensive and time-consuming, so computational prediction is needed.

  Biology & Life Sciences · 2018 · ai assisted · 4/10 importance

• Machine Learning of Designed Translational Control Allows Predictive Pathway Optimization in Escherichia coli

  Optimizing multigene production pathways in microbes requires screening huge combinatorial ribosome binding site (RBS) libraries, and methods to predict optimal RBS combinations were lacking.

  Biology & Life Sciences · 2018 · solved · 4/10 importance

• q2-sample-classifier: machine-learning tools for microbiome classification and regression

  Microbiome researchers need to predict outcomes or differentiate samples from microbial composition, but supervised learning methods were not easily accessible or systematically benchmarked.

  Biology & Life Sciences · 2018 · ai assisted · 4/10 importance

• A Machine Learning Approach for Using the Postmortem Skin Microbiome to Estimate the Postmortem Interval

  Forensic investigators need to estimate the postmortem interval (time since death) for cadavers found after unknown time periods, and current methods have substantial limitations.

  Biology & Life Sciences · 2016 · ai assisted · 4/10 importance

• Machine learning approaches in microbiome research: challenges and best practices

  Microbiome ML workflows suffer domain-specific pitfalls in preprocessing, feature selection, modeling, and interpretation, risking unreliable disease diagnosis and biomarker discovery.

  Biology & Life Sciences · 2023 · ai assisted · 3/10 importance

• Physics-based generative model of curvature sensing peptides; distinguishing sensors from binders

  Distinguishing membrane curvature-sensing peptides from general membrane binders is difficult because of their chemical diversity.

  Biology & Life Sciences · 2023 · ai assisted · 3/10 importance

• Crop Yield Prediction Using Hybrid Machine Learning Approach: A Case Study of Lentil (Lens culinaris Medik.)

  Predicting lentil grain yield, a multifactorial nonlinear phenomenon, from numeric agronomic traits.

  Biology & Life Sciences · 2023 · ai assisted · 3/10 importance

• Identification of Milk Adulteration in Camel Milk Using FT-Mid-Infrared Spectroscopy and Machine Learning Models

  Camel milk is adulterated with cheaper cow milk, threatening food quality and safety, and a rapid detection method was needed.

  Biology & Life Sciences · 2023 · solved · 3/10 importance

• NIR Spectroscopy Oranges Origin Identification Framework Based on Machine Learning

  Identifying the geographic origin of oranges from NIR spectral data is needed for food authentication and quality control.

  Biology & Life Sciences · 2022 · partially solved · 3/10 importance

• Innovations in movement and behavioural ecology from camera traps: Day range as model parameter

  Estimating animal day range from camera-trap data is biased when different movement behaviours are not accounted for.

  Biology & Life Sciences · 2021 · ai assisted · 3/10 importance

• Microbiome Preprocessing Machine Learning Pipeline

  Raw 16S microbiome feature counts may be a suboptimal representation for machine learning classification tasks.

  Biology & Life Sciences · 2021 · partially solved · 3/10 importance

• A Deep Learning Approach for Weed Detection in Lettuce Crops Using Multispectral Images

  Farmers and experts have long struggled to estimate the amount and location of weeds in lettuce crops, which is key to crop productivity.

  Biology & Life Sciences · 2020 · partially solved · 3/10 importance

• Test-time augmentation for deep learning-based cell segmentation on microscopy images

  Deep learning-based cell segmentation on microscopy images requires massive annotated training sets to reach high accuracy; the paper addresses improving accuracy without more annotated data.

  Biology & Life Sciences · 2020 · ai assisted · 3/10 importance

• A large-scale optical microscopy image dataset of potato tuber for deep learning based plant cell assessment

  Researchers lacked a large annotated microscopy image dataset for deep-learning-based assessment of plant cell microstructures in potato tubers.

  Biology & Life Sciences · 2020 · ai assisted · 3/10 importance

• SNNRice6mA: A Deep Learning Method for Predicting DNA N6-Methyladenine Sites in Rice Genome

  Identifying DNA N6-methyladenine (6mA) sites in the rice genome experimentally is time-consuming and laborious, and existing machine learning predictors had room for improvement.

  Biology & Life Sciences · 2019 · ai assisted · 3/10 importance

Search within Biology & Life Sciences →