Papers

Field

Top tools here

Open problems in Molecular property prediction

Scalable uncertainty quantification for ML interatomic potentials1 paper raises it · 0 address it
Current methods fail to provide comparable uncertainty scores across different system sizes, limiting reliability for out-of-distribution detection and active learning.
- Does System Size Matter in Uncertainty Quantification for Machine Learning Interatomic Potentials?raises
Physics-grounded generative design for complex molecules1 paper raises it · 1 addresses it
Generative models often ignore physical constraints or explicit conditioning on molecular targets, leading to unrealistic or suboptimal designs.
- TACFormer: Transformer-Based Generative Model for Target-Conditioned De Novo PROTAC Designraises · addresses
Accurate electron density prediction without self-consistency1 paper raises it · 1 addresses it
Bypassing self-consistent iterations in DFT requires highly accurate and transferable electron density models, which are still rare.
- Transformer-inspired architectures make machine-learned electron densities accurate and transferable enough to bypass self-consistencyraises · addresses
Leveraging lineage context for multicellular dynamics1 paper raises it · 1 addresses it
Existing models struggle to incorporate lineage context to predict cell state dynamics, missing key biological signals.
- Learning developmental dynamics from lineage contextraises · addresses
Structure-free binding prediction for protein complexes1 paper raises it · 1 addresses it
Traditional methods rely on docked complex structures, introducing placement errors that propagate into predictions.
- EMBER: Predicting TCR--pMHC Binding Without a Docked Complexraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

learning interatomic potentials · machine learned interatomic · learned interatomic potentials75 papers14 this week
molecular property prediction · molecular optimization · molecular design112 papers11 this week
protein optimization · protein structures · protein language models91 papers8 this week
crystal structure prediction · crystal generation · crystal structures44 papers2 this week

Topics in this field

Active contributors · 90 days

Stefano MartinianiFramework-Conditional Open Materials Generation4
Philipp HöllmerFramework-Conditional Open Materials Generation3
Han LiuTowards Generalizing Pretrained All-Atom Representations to Unified Binder Design3
Wengong JinBeyond Static Structures: Linking Protein Dynamics to Function via DynaReason-Pro3
Anima AnandkumarMLIPDiff: Guiding Denoising Diffusion Models for Structure-Based Drug Design via Machine-Learned Interatomic Potentials3
Khadidja HenniA curated multi-endpoint drug-protein bioactivity dataset with construct-aware protein targets3

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.LGOct 16
An important Bottleneck in LLM Optimizers: Principle-Level Local Optima
Nian Ran, Tianhe Jia, Zhengyang Mu, Yue Wang, Sebastian Brulin +4
Feedback-driven LLM optimizers are increasingly used for evolutionary search, Bayesian optimization, heuristic design, and scientific discovery. Yet rapid initial gains often give way to prolonged plateaus despite substantial remaining evaluation budgets. We investigate \emph{principle-level search collapse}, where an optimizer's search becomes confined to a narrow set of design principles, even though it may continue to generate distinct candidates and achieve small improvements. We assemble a diagnostic benchmark spanning molecular optimization, network sentinel-node selection, and GPU-kernel optimization, and introduce a decision-tree protocol combining principle narrowing, prolonged performance plateaus, and gaps to attainable reference solutions. Across 161 assessable runs on the three problem domains, 78.3\% receive support for collapse, including 55.3\% with strong support. Candidate-level variation can nevertheless conceal restricted search at the principle level. We then test \emph{diversity injection}, a common response to search stagnation, such as higher t, multiple LLMs, and web search, and show that it provides limited and inconsistent benefits: among 65 molecular…
PDF arXiv
arXiv cs.LGOct 16
On the Selectivity of Generative Models in Structure-Based Drug Design
Ella Miray Rajaonson, Jungyoon Lee, William Chau, Alan Aspuru-Guzik, Benjamin Sanchez-Lengeling +3
Designing small-molecule drugs that selectively bind to a target protein while avoiding unintended interactions with other proteins is essential for reducing side effects that contribute substantially to clinical attrition. Although structure-based drug design (SBDD) has advanced rapidly with deep learning, most generative models still optimize binding to a single target and disregard selectivity due to limited training data and unknown off-target interactions. Motivated by this gap, we introduce SELECTBENCH, a comprehensive benchmark assessing the selectivity of generative SBDD models. SELECTBENCH provides three curated evaluation tasks reflecting different real-world drug discovery scenarios: literature-based case studies, safety screening panels used in pharmaceutical development, and large-scale structure-based evaluation sets. We further introduce a suite of metrics to quantify selectivity and conduct a systematic evaluation of nine representative SBDD models, including methods explicitly trained for selectivity and widely-used inference-time guidance techniques. Our results show that even selectivity-trained models achieve only modest off-target discrimination and…
PDF arXiv
arXiv cs.LGOct 16
CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning
Tianmeng Hu, Biao Luo, Ke Li
Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computational problem. We propose CocoRNA, a cooperative multi-agent reinforcement learning framework for RNA inverse design. CocoRNA simplifies the design task by decomposing it into smaller sub-problems, each solved collaboratively by multiple agents. This approach reduces the complexity of the problem and improves the exploration of design policies. During training, a centralized critic uses global structural information to guide the agents, enabling them to jointly optimize their design strategies. As a result, CocoRNA learns high-quality RNA design policies that generalize effectively to unseen structures without additional training. Experiments on the Rfam dataset demonstrate that CocoRNA substantially outperforms state-of-the-art methods in both success rate and design speed. Further experiments on other biological sequence design tasks highlight the effectiveness and broad potential of CocoRNA for complex design tasks.
PDF arXiv
arXiv cond-mat.dis-nnOct 16
Sampling the XY model with an attention-based neural network
Piotr Białas, Christian D. Morales, Tomasz Stebel, Dawid Zapolski
We present a transformer-based variational autoregressive network for sampling lattice systems with continuous degrees of freedom and apply it to the two-dimensional XY model near the Berezinskii-Kosterlitz-Thouless transition. The architecture is combined with physics-informed ingredients: locality-informed attention and approximate probabilities. The resulting sampler significantly outperforms existing neural samplers. We train the model on lattices up to $96\times96$, verify with a mode-dropping estimator that no parts of the configuration space are missed, and reproduce the energy, magnetization and helicity modulus obtained with the traditional Markov Chain Monte Carlo algorithm.
PDF arXiv
arXiv cs.LGOct 16
Blitz: Accelerating the Diffusion Modules of AlphaFold3 and Boltz-2
Vinay Saji Mathew, Soundar Kumara, Gretta Kellogg, William K. M. Lai
Diffusion-based protein structure prediction models produce all-atom structures in about 200 denoising steps, and that cost has driven a number of few-step samplers. We present Blitz, a few-step distillation framework that uses a geometric noise schedule to distribute steps more evenly across noise scales, then learns those updates through multistep consistency training. Physical steering and target-free candidate selection help reduce the remaining geometric defects at inference. We apply Blitz to AlphaFold 3 and Boltz-2, reducing denoising from 200 steps to eight. Because published few-step results use different benchmarks and scoring procedures, we compare both distilled models with their teachers and other few-step methods under a common evaluation protocol covering structural accuracy, interface quality, ligand placement, and stereochemical validity. Blitz retains teacher-level structural accuracy, with AF3-Blitz outperforming all evaluated few-step baselines and exceeding its teacher on several accuracy metrics.
PDF arXiv
arXiv cond-mat.mtrl-sciOct 16
Scalable long-range machine learning interatomic potentials with electrical response for atomistic material modeling
Yicheng Chen, Xiaoyun Yu, Hyejeong Song, Xintian Wang, Zihui Li +3
Accurate atomistic simulations of materials under electric fields require long-range electrostatics and electrical-response modeling at length scales beyond the reach of conventional first-principles methods. Yet these capabilities remain difficult to reconcile with the scalability of machine-learning interatomic potentials (MLIPs). Strictly local models enable efficient spatial parallelization but neglect long-range interactions, whereas existing electrostatic extensions introduce global dependencies that hinder distributed computation. Here, we overcome this limitation by analytically separating the long-range electrostatic forces and Born effective charges (BECs) into a global electrostatics calculation and strictly local derivatives of learned latent charges. This formulation preserves the spatial decomposability of equivariant MLIPs while enabling distributed evaluation of energies, forces, stresses, and BECs across different boundary conditions. Implemented as DPA4C-LR on the \texttt{nvalchemi} platform, the framework scales to 5.2 million atoms on four GPUs at approximately twice the computational cost of its short-range backbone. Trained on energies and forces, DPA4C-LR…
PDF arXiv

Papers

Topics in this field

learning interatomic potentials · machine learned interatomic · learned interatomic potentials75 papers14 this week
molecular property prediction · molecular optimization · molecular design112 papers11 this week
protein optimization · protein structures · protein language models91 papers8 this week
crystal structure prediction · crystal generation · crystal structures44 papers2 this week

Active contributors · 90 days

Stefano MartinianiFramework-Conditional Open Materials Generation4
Philipp HöllmerFramework-Conditional Open Materials Generation3
Han LiuTowards Generalizing Pretrained All-Atom Representations to Unified Binder Design3
Wengong JinBeyond Static Structures: Linking Protein Dynamics to Function via DynaReason-Pro3
Anima AnandkumarMLIPDiff: Guiding Denoising Diffusion Models for Structure-Based Drug Design via Machine-Learned Interatomic Potentials3
Khadidja HenniA curated multi-endpoint drug-protein bioactivity dataset with construct-aware protein targets3

Recent papers

All papers in Research

arXiv cs.LGOct 16
An important Bottleneck in LLM Optimizers: Principle-Level Local Optima
Nian Ran, Tianhe Jia, Zhengyang Mu, Yue Wang, Sebastian Brulin +4
Feedback-driven LLM optimizers are increasingly used for evolutionary search, Bayesian optimization, heuristic design, and scientific discovery. Yet rapid initial gains often give way to prolonged plateaus despite substantial remaining evaluation budgets. We investigate \emph{principle-level search collapse}, where an optimizer's search becomes confined to a narrow set of design principles, even though it may continue to generate distinct candidates and achieve small improvements. We assemble a diagnostic benchmark spanning molecular optimization, network sentinel-node selection, and GPU-kernel optimization, and introduce a decision-tree protocol combining principle narrowing, prolonged performance plateaus, and gaps to attainable reference solutions. Across 161 assessable runs on the three problem domains, 78.3\% receive support for collapse, including 55.3\% with strong support. Candidate-level variation can nevertheless conceal restricted search at the principle level. We then test \emph{diversity injection}, a common response to search stagnation, such as higher t, multiple LLMs, and web search, and show that it provides limited and inconsistent benefits: among 65 molecular…
PDF arXiv
arXiv cs.LGOct 16
On the Selectivity of Generative Models in Structure-Based Drug Design
Ella Miray Rajaonson, Jungyoon Lee, William Chau, Alan Aspuru-Guzik, Benjamin Sanchez-Lengeling +3
Designing small-molecule drugs that selectively bind to a target protein while avoiding unintended interactions with other proteins is essential for reducing side effects that contribute substantially to clinical attrition. Although structure-based drug design (SBDD) has advanced rapidly with deep learning, most generative models still optimize binding to a single target and disregard selectivity due to limited training data and unknown off-target interactions. Motivated by this gap, we introduce SELECTBENCH, a comprehensive benchmark assessing the selectivity of generative SBDD models. SELECTBENCH provides three curated evaluation tasks reflecting different real-world drug discovery scenarios: literature-based case studies, safety screening panels used in pharmaceutical development, and large-scale structure-based evaluation sets. We further introduce a suite of metrics to quantify selectivity and conduct a systematic evaluation of nine representative SBDD models, including methods explicitly trained for selectivity and widely-used inference-time guidance techniques. Our results show that even selectivity-trained models achieve only modest off-target discrimination and…
PDF arXiv
arXiv cs.LGOct 16
CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning
Tianmeng Hu, Biao Luo, Ke Li
Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computational problem. We propose CocoRNA, a cooperative multi-agent reinforcement learning framework for RNA inverse design. CocoRNA simplifies the design task by decomposing it into smaller sub-problems, each solved collaboratively by multiple agents. This approach reduces the complexity of the problem and improves the exploration of design policies. During training, a centralized critic uses global structural information to guide the agents, enabling them to jointly optimize their design strategies. As a result, CocoRNA learns high-quality RNA design policies that generalize effectively to unseen structures without additional training. Experiments on the Rfam dataset demonstrate that CocoRNA substantially outperforms state-of-the-art methods in both success rate and design speed. Further experiments on other biological sequence design tasks highlight the effectiveness and broad potential of CocoRNA for complex design tasks.
PDF arXiv
arXiv cond-mat.dis-nnOct 16
Sampling the XY model with an attention-based neural network
Piotr Białas, Christian D. Morales, Tomasz Stebel, Dawid Zapolski
We present a transformer-based variational autoregressive network for sampling lattice systems with continuous degrees of freedom and apply it to the two-dimensional XY model near the Berezinskii-Kosterlitz-Thouless transition. The architecture is combined with physics-informed ingredients: locality-informed attention and approximate probabilities. The resulting sampler significantly outperforms existing neural samplers. We train the model on lattices up to $96\times96$, verify with a mode-dropping estimator that no parts of the configuration space are missed, and reproduce the energy, magnetization and helicity modulus obtained with the traditional Markov Chain Monte Carlo algorithm.
PDF arXiv
arXiv cs.LGOct 16
Blitz: Accelerating the Diffusion Modules of AlphaFold3 and Boltz-2
Vinay Saji Mathew, Soundar Kumara, Gretta Kellogg, William K. M. Lai
Diffusion-based protein structure prediction models produce all-atom structures in about 200 denoising steps, and that cost has driven a number of few-step samplers. We present Blitz, a few-step distillation framework that uses a geometric noise schedule to distribute steps more evenly across noise scales, then learns those updates through multistep consistency training. Physical steering and target-free candidate selection help reduce the remaining geometric defects at inference. We apply Blitz to AlphaFold 3 and Boltz-2, reducing denoising from 200 steps to eight. Because published few-step results use different benchmarks and scoring procedures, we compare both distilled models with their teachers and other few-step methods under a common evaluation protocol covering structural accuracy, interface quality, ligand placement, and stereochemical validity. Blitz retains teacher-level structural accuracy, with AF3-Blitz outperforming all evaluated few-step baselines and exceeding its teacher on several accuracy metrics.
PDF arXiv
arXiv cond-mat.mtrl-sciOct 16
Scalable long-range machine learning interatomic potentials with electrical response for atomistic material modeling
Yicheng Chen, Xiaoyun Yu, Hyejeong Song, Xintian Wang, Zihui Li +3
Accurate atomistic simulations of materials under electric fields require long-range electrostatics and electrical-response modeling at length scales beyond the reach of conventional first-principles methods. Yet these capabilities remain difficult to reconcile with the scalability of machine-learning interatomic potentials (MLIPs). Strictly local models enable efficient spatial parallelization but neglect long-range interactions, whereas existing electrostatic extensions introduce global dependencies that hinder distributed computation. Here, we overcome this limitation by analytically separating the long-range electrostatic forces and Born effective charges (BECs) into a global electrostatics calculation and strictly local derivatives of learned latent charges. This formulation preserves the spatial decomposability of equivariant MLIPs while enabling distributed evaluation of energies, forces, stresses, and BECs across different boundary conditions. Implemented as DPA4C-LR on the \texttt{nvalchemi} platform, the framework scales to 5.2 million atoms on four GPUs at approximately twice the computational cost of its short-range backbone. Trained on energies and forces, DPA4C-LR…
PDF arXiv

Activity · 12 weeks

Fields · AI · updated 55m ago

Molecular property prediction

Found by the topic model: molecular property prediction, protein optimization, learning interatomic potentials.

35papers this week−12.5% vs last week

All papers · 322 With code · 3

Newest Most relevant

196 papers this month

Open problems in Molecular property prediction

Scalable uncertainty quantification for ML interatomic potentials1 paper raises it · 0 address it
Current methods fail to provide comparable uncertainty scores across different system sizes, limiting reliability for out-of-distribution detection and active learning.
- Does System Size Matter in Uncertainty Quantification for Machine Learning Interatomic Potentials?raises
Physics-grounded generative design for complex molecules1 paper raises it · 1 addresses it
Generative models often ignore physical constraints or explicit conditioning on molecular targets, leading to unrealistic or suboptimal designs.
- TACFormer: Transformer-Based Generative Model for Target-Conditioned De Novo PROTAC Designraises · addresses
Accurate electron density prediction without self-consistency1 paper raises it · 1 addresses it
Bypassing self-consistent iterations in DFT requires highly accurate and transferable electron density models, which are still rare.
- Transformer-inspired architectures make machine-learned electron densities accurate and transferable enough to bypass self-consistencyraises · addresses
Leveraging lineage context for multicellular dynamics1 paper raises it · 1 addresses it
Existing models struggle to incorporate lineage context to predict cell state dynamics, missing key biological signals.
- Learning developmental dynamics from lineage contextraises · addresses
Structure-free binding prediction for protein complexes1 paper raises it · 1 addresses it
Traditional methods rely on docked complex structures, introducing placement errors that propagate into predictions.
- EMBER: Predicting TCR--pMHC Binding Without a Docked Complexraises · addresses

Named by an AI from these papers' abstracts.