Science & Research

24 verified cases, highest-rated first.

Industries: computational chemistry 6, drug discovery 5, complex systems science 1, chemical synthesis 1, research data tools 1, scientific machine learning 1, biomedical research 1, microscopy imaging 1, materials science 1, bioimaging microscopy 1, mineral exploration 1, biomedical imaging 1

• Learning interpretable network dynamics via universal neural symbolic regression

  Discovering the governing equations of complex network dynamics from data, across fields like physics, ecology and epidemiology.

  Science & Research · 2025 · ai assisted · 7/10 importance

• Data-driven Chemical Reaction Prediction and Retrosynthesis

  Predicting organic chemical reactions and designing synthesis routes, which traditionally requires chemists with years of knowledge and experience.

  Science & Research · 2019 · ai assisted · 7/10 importance

• Neural‐Symbolic Machine Learning for Retrosynthesis and Reaction Prediction

  Rule-based expert systems for reaction prediction and retrosynthesis often fail because they ignore molecular context, causing reactivity conflicts.

  Science & Research · 2017 · partially solved · 7/10 importance

• SciDaSynth: Interactive Structured Data Extraction From Scientific Literature With Large Language Model

  Extracting structured, standardized data from the explosion of scientific literature across text, tables and figures is slow and error-prone.

  Science & Research · 2025 · ai assisted · 6/10 importance

• Interpretable scientific discovery with symbolic regression: a review

  Scientists need interpretable mathematical expressions learned directly from data, traditionally tackled with genetic programming.

  Science & Research · 2024 · ai assisted · 6/10 importance

• Leveraging Large Language Models for Enhancing Literature-Based Discovery

  Biomedical literature is growing too fast for researchers to manually uncover hidden relationships and generate novel hypotheses.

  Science & Research · 2024 · ai assisted · 6/10 importance

• Prediction of transition state structures of gas-phase chemical reactions via machine learning

  Predicting transition state structures of chemical reactions is challenging because constructing initial structures is difficult and computational costs are heavy.

  Science & Research · 2023 · solved · 6/10 importance

• Incorporating the image formation process into deep learning improves network performance

  Deconvolution of 3D fluorescence microscopy images is slow and artifact-prone with existing methods.

  Science & Research · 2022 · solved · 6/10 importance

• Generative and reinforcement learning approaches for the automated de novo design of bioactive compounds

  Deep generative models with reinforcement learning for designing bioactive molecules suffer from sparse rewards, since most generated molecules are predicted inactive.

  Science & Research · 2022 · partially solved · 6/10 importance

• Limits of Prediction for Machine Learning in Drug Discovery

  Drug discovery uses ML to extrapolate molecular property predictions during optimization, but the effectiveness and limits of extrapolation had not been systematically analyzed.

  Science & Research · 2022 · ai assisted · 6/10 importance

• Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias

  Machine-learning models for organic reaction prediction are opaque black boxes, so it is unclear whether predictions reflect real chemistry or dataset bias.

  Science & Research · 2021 · ai assisted · 6/10 importance

• Fitting potential energy surfaces with fundamental invariant neural network. II. Generating fundamental invariants for molecular systems with up to ten atoms

  Neural-network fitting of permutationally invariant potential energy surfaces was limited to small molecules because generating fundamental invariants was computationally too slow.

  Science & Research · 2020 · solved · 6/10 importance

• Machine learning in chemical reaction space

  Chemical reaction space is vastly larger than compound space, and existing machine-learning concepts could not directly handle its hub-based topology.

  Science & Research · 2020 · ai assisted · 6/10 importance

• Exploring Deep Recurrent Models with Reinforcement Learning for Molecule Design

  Designing small molecules with bespoke properties for drug discovery is hard, and results across computational methods are difficult to compare.

  Science & Research · 2018 · ai assisted · 6/10 importance

• CGBVS‐DNN: Prediction of Compound‐protein Interactions Based on Deep Learning

  SVM-based compound-protein interaction prediction could not scale to training sets of more than a million CPIs due to exponential time and memory costs.

  Science & Research · 2016 · solved · 6/10 importance

• Accelerating scientific discovery with generative knowledge extraction, graph-based representation, and multimodal intelligent graph reasoning

  Knowledge spread across thousands of scientific papers is hard to connect, limiting interdisciplinary insight and materials discovery.

  Science & Research · 2024 · ai assisted · 5/10 importance

• Deep learning-driven adaptive optics for single-molecule localization microscopy

  Tissue-induced aberrations blur and distort single-molecule emission patterns, limiting resolution in single-molecule localization microscopy, and conventional sensorless adaptive optics is slow and inconsistent.

  Science & Research · 2023 · solved · 5/10 importance

• Intelligent Identification and Prediction Mineral Resources Deposit Based on Deep Learning

  Predicting ore deposit locations is hindered by scarce labeled geological images, small irregular features with high image similarity, and hard-to-quantify prospecting factors.

  Science & Research · 2023 · partially solved · 5/10 importance

• Deep-Learning-Based Image Reconstruction and Enhancement in Optical Microscopy

  Images from optical microscopes often need computational reconstruction or enhancement, and many inverse problems in microscopy are hard to solve with traditional methods.

  Science & Research · 2019 · ai assisted · 5/10 importance

• RetroRanker: leveraging reaction changes to improve retrosynthesis prediction through re-ranking

  Data-driven retrosynthesis models suffer frequency bias, producing low-ranked, chemically unreasonable reactant predictions.

  Science & Research · 2023 · ai assisted · 4/10 importance

• 3D Mineral Prospectivity Mapping of Zaozigou Gold Deposit, West Qinling, China: Deep Learning-Based Mineral Prediction

  Quantitative prediction of gold mineralization at large depth in the Zaozigou gold deposit, west Qinling, China, to guide future exploration.

  Science & Research · 2022 · partially solved · 4/10 importance

• Quantifying the effects of environment and population diversity in multi-agent reinforcement learning

  Reinforcement learning agents often perform poorly when placed in novel environments or with unfamiliar co-players; the study quantified how training diversity affects this generalization problem.

  Science & Research · 2022 · partially solved · 4/10 importance

• Impact of non-normal error distributions on the benchmarking and ranking of quantum machine learning models

  Benchmarking quantum machine learning models with Mean Absolute Error learning curves can misrepresent true performance when error distributions are non-normal.

  Science & Research · 2020 · partially solved · 3/10 importance

• Rate coefficients of the H + H2O2 → H2 + HO2 reaction on an accurate fundamental invariant-neural network potential energy surface

  Experimental rate coefficients for the H + H2O2 → H2 + HO2 reaction varied widely, especially at low temperatures, so accurate values were needed.

  Science & Research · 2018 · solved · 2/10 importance

Search within Science & Research →