Spotlight

Papers

Field

Top tools here

Open problems in Machine learned interatomic

Reliable geometric reasoning over protein structures1 paper raises it · 2 address it
Frontier models excel at metadata lookup but struggle with numeric geometry tasks, limiting their use in structural biology.
Integration of foundation model inputs in biological reasoning1 paper raises it · 0 address it
Biological reasoning models often ignore foundation model inputs and rely on text, reducing their effectiveness.
- When Do Biological Reasoning Models Use Their Biological Inputs?raises
Scalable and durable pretraining data filtering for protein models1 paper raises it · 0 address it
Filtering pretraining data degrades performance on filtered domains but is easily undone by fine-tuning, limiting its long-term utility.
- The Effectiveness and Durability of Pretraining Data Filtering in Protein Language Modelsraises
Stable evaluation metrics for gene perturbation models1 paper raises it · 0 address it
Heterogeneous metrics and DE gene subsets lead to unstable rankings, obscuring true model performance.
- A Pitfall in the Evaluation of Gene Perturbation Modelsraises
Autoregressive generation of protein sequences and structures1 paper raises it · 2 address it
Autoregressive transformers underperform in protein sequence and structure generation due to weak target representations.
- Learning Latent Protein Languages for Autoregressive Generationraises · addresses
- recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Modelsaddresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

molecular optimization · molecular design · molecular generation99 papers21 this week
protein language models · protein language · protein structure101 papers12 this week
machine learned interatomic · crystal structure prediction · learned interatomic potentials96 papers8 this week

Topics in this field

Active contributors · 90 days

Ke LiREFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge3
Tianmeng HuREFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge3
Yuqiang LiDrugHarness: An Evolvable Agent Harness for Computational Drug Discovery3
Yatao BianMolLean: A Process-Verifiable Language for Chemical Reasoning3
Frazier N. BakerMFG: Multi-turn Feedback Guided Molecular Optimization3
Xia NingMFG: Multi-turn Feedback Guided Molecular Optimization3

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

★ Spotlight this month

arXiv cs.CLOct 14

MolLean: A Process-Verifiable Language for Chemical Reasoning

Jiatong Li, Yatao Bian

Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular state. A layered Lean-based kernel checks state transitions and assertions over molecular readouts, from primitive graph edits to compound transformations. Meanwhile, a typed witness protocol separates native structural checks from externally supplied measurements. We further introduce MolLean-MCP, a stateful tool interface that exposes these transitions, checks, and readouts during generation: the model receives feedback to decide its next action, and rejected actions leave the state unchanged. MolLean supports one-pass trace execution, whole-trace refinement, and interactive reasoning through MolLean-MCP. We evaluate these three modes with direct chain-of-thought on 8,800 matched examples across 12 tasks spanning molecular generation, editing, optimization, and reactions. With Qwen3.6-27B, whole-trace refinement outperforms direct chain-of-thought on all 12 tasks. MolLean-MCP complements whole-trace refinement with stepwise verification feedback, reaching better performance in…

PDF arXiv page Details

Spotlight

Recent papers

All in Research →

arXiv cs.AIOct 19
ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry
Matt Turk, Brandon L. Neel, Diana M. Lopez, Zachary D. Smith, Grace N. Johnecheck +1
Frontier agents retrieve structural metadata well and compute geometry from coordinates less reliably. We ask how much of a benchmark score reflects that gap and how much reflects the evaluation configuration around the model. We study ProteinGeoBench, a suite of 131 protein-structure tasks, using 4,249 rollouts from four frontier models and 4,486 further trials across 26 models. Three of the four frontier models fall within 0.031 of one another (0.785 to 0.816) with no difference between them resolved, while the fourth scores 0.707 and all three gaps to it exclude zero. Three of the four do better on metadata lookup than on numeric calculation. The fourth is slightly better on numeric. Numeric tasks are 28 of the 131 but half of the twelve tasks that all four models fail. The ranking also depends on the evaluation budget: with one run per task, 23.9% of bootstrap replicates put a different model first. On a selected 15-task slice, removing network access lowers scores more than blocking eight structural-database domains, but the two contrasts were graded in different passes and cannot be cleanly decomposed. Swapping in each model's own command-line agent changes scores by -0.071…
PDF arXiv
arXiv cs.LGOct 19
recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Models
Saurav Jha, Qianli Liao, Robert Vernon, Sarath Chandar, Quentin Fournier
Protein language models (pLMs) are powerful tools for protein annotation and mutation-effect prediction, but progress has largely depended on scaling model size and data, making them expensive and prone to memorization. Test-time scaling offers a complementary path, but methods developed for autoregressive LLMs do not transfer directly: masked encoders lack a generation loop, and amino acids do not verbalize in a reasoning language. Instead, we adapt recursive pretraining to masked pLMs, where a weight-tied Transformer core refines residue-aligned hidden states over an adjustable number of cycles. We instantiate this recipe as recAMPLIFY, a pLM with 155M unique parameters trained on the same 2T tokens as AMPLIFY-350M. Despite 56% fewer parameters, it improves CASP contact recovery and three out of four supervised tasks, notably raising fold accuracy by 22.5%. Because optimal depth for recAMPLIFY varies across tasks and assays, we then introduce Gated Mixture Recurrence (GMR), a framework that decodes each protein from a probability-weighted mixture of hidden states visited during recursion. GMR employs a learned residual gate at scalar, low-rank, or per-dimension resolution to…
PDF arXiv
arXiv cs.LGOct 19
The Effectiveness and Durability of Pretraining Data Filtering in Protein Language Models
Aaron Maiwald, Roderick McNeill, Jaeyoung Lee, Matthew A. Clarke, Lennart Justen +7
Pretraining filtering is one of the most common safeguards for open-weight language models. Here we study its effectiveness, durability and scalability using the ESM-2 family of protein language models. We find that filtering viral proteins from the pretraining data meaningfully degrades masked language modelling, mutation effect prediction and long-range contact prediction on viral proteins, while largely preserving performance on non-viral proteins. These effects are concentrated among proteins from human-infecting viruses, and grow as we scale models from 8M to 3B parameters. As models increase in size, we find that stringent filtering becomes more effective. However, fine-tuning on sequences from the removed viral families restores the lost performance. Although the cost to recover performance increases with model scale, even for the largest models it costs about 80 USD of H100 time. This work establishes pretraining filtering as moderately effective at selectively degrading performance on viral proteins, but not durable against fine-tuning with modest computational resources and access to relevant data.
PDF arXiv
arXiv stat.APOct 19
A Pitfall in the Evaluation of Gene Perturbation Models
George Panagopoulos, Saman Omidi, Tsz Pan Tong, Jun Pang
Gene perturbation models aim to predict transcriptional responses to unseen genetic interventions, but comparisons rely on heterogeneous evaluation metrics and differentially-expressed (DE) gene subsets. We investigate the consequences of these choices using eight methods across six single-gene perturbation datasets under a unified evaluation protocol. Varying the number of top DE genes reveals substantial instability in Precision-based rankings, with the winning method changing $86.7\%$ of the time, while rankings based on the rest of the metrics remain comparatively stable. Investigating this discrepancy exposes that repeating a single predicted expression profile across cell-level rows, a standard practice for many methods, can inflate significance estimates and produce excessively large predicted significant-DE sets. Specifically we found that $67.1\%$ of tested perturbation--gene pairs pass the significance threshold despite some of them having minuscule effects. We derive an inflation factor showing that replicated predictions can amplify the standardized Mann--Whitney statistic even after correction for tied ranks, without adding independent information. This artifact…
PDF arXiv
arXiv cs.AIOct 19
REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
Wanli Ma, Tianmeng Hu, Ke Li
RNA molecules often function through multiple experimentally observed conformational states. A central challenge is to capture ensemble diversity without sacrificing structural fidelity: samples may collapse toward averaged representative structures or drift into unsupported conformational regions. We introduce REFLEX (RNA Ensemble generation calibrated by FLEXibility), a sequence-conditioned generator for RNA backbone-frame ensembles based on a heteroscedastic stochastic bridge on SE(3). During training, experimental B-factors calibrate residue-wise bridge widths, exposing each observed conformer through local perturbation neighborhoods with residue-specific scales while keeping constrained regions sharper. A learned flexibility condition guides the bridge-field network to recover target conformer-specific frames from these calibrated noisy states. At inference, REFLEX uses only the input sequence, requiring no MSA-subsampling heuristics. On a multi-conformer RNA benchmark, REFLEX achieves the best precision-recall trade-off for ensemble coverage across evaluation thresholds, while recovery-stress ablations indicate gains in target-frame recovery under stronger perturbations.
PDF arXiv
arXiv cs.LGOct 19
ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model
Minghao Xu, Jiaze Song, Jinyu Wang, Wentao Zhang
Performing accurate protein-glycan docking is critical to understanding protein-glycan interactions which govern many biological processes. However, this important task is hampered by the lack of tailored datasets, benchmarks and models for protein-glycan docking. To fill this blank, we first curate a standard benchmark ProtGlycanDock for training and evaluating protein-glycan docking models under both protein and glycan generalization settings. On this benchmark, we evaluate ten models in three categories, physics-based docking methods, machine-learning-based docking models and molecular structure prediction models. To obtain more precise binding poses, we further propose two finetuning techniques to inject the knowledge of glycan conformations into a general-purpose molecular structure prediction model. These two techniques respectively augment model inputs with glycan topological features and refine glycan binding pose with a glycan energy loss. Benchmark results show the superiority of AlphaFold 3 among existing methods, and the two proposed finetuning techniques can be well combined to achieve a state-of-the-art model for protein-glycan docking. Also, we perform stratified…
PDF arXiv

Papers

Topics in this field

molecular optimization · molecular design · molecular generation99 papers21 this week
protein language models · protein language · protein structure101 papers12 this week
machine learned interatomic · crystal structure prediction · learned interatomic potentials96 papers8 this week

Active contributors · 90 days

Ke LiREFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge3
Tianmeng HuREFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge3
Yuqiang LiDrugHarness: An Evolvable Agent Harness for Computational Drug Discovery3
Yatao BianMolLean: A Process-Verifiable Language for Chemical Reasoning3
Frazier N. BakerMFG: Multi-turn Feedback Guided Molecular Optimization3
Xia NingMFG: Multi-turn Feedback Guided Molecular Optimization3

★ Spotlight this month

arXiv cs.CLOct 14

MolLean: A Process-Verifiable Language for Chemical Reasoning

Jiatong Li, Yatao Bian

Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular state. A layered Lean-based kernel checks state transitions and assertions over molecular readouts, from primitive graph edits to compound transformations. Meanwhile, a typed witness protocol separates native structural checks from externally supplied measurements. We further introduce MolLean-MCP, a stateful tool interface that exposes these transitions, checks, and readouts during generation: the model receives feedback to decide its next action, and rejected actions leave the state unchanged. MolLean supports one-pass trace execution, whole-trace refinement, and interactive reasoning through MolLean-MCP. We evaluate these three modes with direct chain-of-thought on 8,800 matched examples across 12 tasks spanning molecular generation, editing, optimization, and reactions. With Qwen3.6-27B, whole-trace refinement outperforms direct chain-of-thought on all 12 tasks. MolLean-MCP complements whole-trace refinement with stepwise verification feedback, reaching better performance in…

PDF arXiv page Details

Recent papers

All in Research →

arXiv cs.AIOct 19
ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry
Matt Turk, Brandon L. Neel, Diana M. Lopez, Zachary D. Smith, Grace N. Johnecheck +1
Frontier agents retrieve structural metadata well and compute geometry from coordinates less reliably. We ask how much of a benchmark score reflects that gap and how much reflects the evaluation configuration around the model. We study ProteinGeoBench, a suite of 131 protein-structure tasks, using 4,249 rollouts from four frontier models and 4,486 further trials across 26 models. Three of the four frontier models fall within 0.031 of one another (0.785 to 0.816) with no difference between them resolved, while the fourth scores 0.707 and all three gaps to it exclude zero. Three of the four do better on metadata lookup than on numeric calculation. The fourth is slightly better on numeric. Numeric tasks are 28 of the 131 but half of the twelve tasks that all four models fail. The ranking also depends on the evaluation budget: with one run per task, 23.9% of bootstrap replicates put a different model first. On a selected 15-task slice, removing network access lowers scores more than blocking eight structural-database domains, but the two contrasts were graded in different passes and cannot be cleanly decomposed. Swapping in each model's own command-line agent changes scores by -0.071…
PDF arXiv
arXiv cs.LGOct 19
recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Models
Saurav Jha, Qianli Liao, Robert Vernon, Sarath Chandar, Quentin Fournier
Protein language models (pLMs) are powerful tools for protein annotation and mutation-effect prediction, but progress has largely depended on scaling model size and data, making them expensive and prone to memorization. Test-time scaling offers a complementary path, but methods developed for autoregressive LLMs do not transfer directly: masked encoders lack a generation loop, and amino acids do not verbalize in a reasoning language. Instead, we adapt recursive pretraining to masked pLMs, where a weight-tied Transformer core refines residue-aligned hidden states over an adjustable number of cycles. We instantiate this recipe as recAMPLIFY, a pLM with 155M unique parameters trained on the same 2T tokens as AMPLIFY-350M. Despite 56% fewer parameters, it improves CASP contact recovery and three out of four supervised tasks, notably raising fold accuracy by 22.5%. Because optimal depth for recAMPLIFY varies across tasks and assays, we then introduce Gated Mixture Recurrence (GMR), a framework that decodes each protein from a probability-weighted mixture of hidden states visited during recursion. GMR employs a learned residual gate at scalar, low-rank, or per-dimension resolution to…
PDF arXiv
arXiv cs.LGOct 19
The Effectiveness and Durability of Pretraining Data Filtering in Protein Language Models
Aaron Maiwald, Roderick McNeill, Jaeyoung Lee, Matthew A. Clarke, Lennart Justen +7
Pretraining filtering is one of the most common safeguards for open-weight language models. Here we study its effectiveness, durability and scalability using the ESM-2 family of protein language models. We find that filtering viral proteins from the pretraining data meaningfully degrades masked language modelling, mutation effect prediction and long-range contact prediction on viral proteins, while largely preserving performance on non-viral proteins. These effects are concentrated among proteins from human-infecting viruses, and grow as we scale models from 8M to 3B parameters. As models increase in size, we find that stringent filtering becomes more effective. However, fine-tuning on sequences from the removed viral families restores the lost performance. Although the cost to recover performance increases with model scale, even for the largest models it costs about 80 USD of H100 time. This work establishes pretraining filtering as moderately effective at selectively degrading performance on viral proteins, but not durable against fine-tuning with modest computational resources and access to relevant data.
PDF arXiv
arXiv stat.APOct 19
A Pitfall in the Evaluation of Gene Perturbation Models
George Panagopoulos, Saman Omidi, Tsz Pan Tong, Jun Pang
Gene perturbation models aim to predict transcriptional responses to unseen genetic interventions, but comparisons rely on heterogeneous evaluation metrics and differentially-expressed (DE) gene subsets. We investigate the consequences of these choices using eight methods across six single-gene perturbation datasets under a unified evaluation protocol. Varying the number of top DE genes reveals substantial instability in Precision-based rankings, with the winning method changing $86.7\%$ of the time, while rankings based on the rest of the metrics remain comparatively stable. Investigating this discrepancy exposes that repeating a single predicted expression profile across cell-level rows, a standard practice for many methods, can inflate significance estimates and produce excessively large predicted significant-DE sets. Specifically we found that $67.1\%$ of tested perturbation--gene pairs pass the significance threshold despite some of them having minuscule effects. We derive an inflation factor showing that replicated predictions can amplify the standardized Mann--Whitney statistic even after correction for tied ranks, without adding independent information. This artifact…
PDF arXiv
arXiv cs.AIOct 19
REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
Wanli Ma, Tianmeng Hu, Ke Li
RNA molecules often function through multiple experimentally observed conformational states. A central challenge is to capture ensemble diversity without sacrificing structural fidelity: samples may collapse toward averaged representative structures or drift into unsupported conformational regions. We introduce REFLEX (RNA Ensemble generation calibrated by FLEXibility), a sequence-conditioned generator for RNA backbone-frame ensembles based on a heteroscedastic stochastic bridge on SE(3). During training, experimental B-factors calibrate residue-wise bridge widths, exposing each observed conformer through local perturbation neighborhoods with residue-specific scales while keeping constrained regions sharper. A learned flexibility condition guides the bridge-field network to recover target conformer-specific frames from these calibrated noisy states. At inference, REFLEX uses only the input sequence, requiring no MSA-subsampling heuristics. On a multi-conformer RNA benchmark, REFLEX achieves the best precision-recall trade-off for ensemble coverage across evaluation thresholds, while recovery-stress ablations indicate gains in target-frame recovery under stronger perturbations.
PDF arXiv
arXiv cs.LGOct 19
ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model
Minghao Xu, Jiaze Song, Jinyu Wang, Wentao Zhang
Performing accurate protein-glycan docking is critical to understanding protein-glycan interactions which govern many biological processes. However, this important task is hampered by the lack of tailored datasets, benchmarks and models for protein-glycan docking. To fill this blank, we first curate a standard benchmark ProtGlycanDock for training and evaluating protein-glycan docking models under both protein and glycan generalization settings. On this benchmark, we evaluate ten models in three categories, physics-based docking methods, machine-learning-based docking models and molecular structure prediction models. To obtain more precise binding poses, we further propose two finetuning techniques to inject the knowledge of glycan conformations into a general-purpose molecular structure prediction model. These two techniques respectively augment model inputs with glycan topological features and refine glycan binding pose with a glycan energy loss. Benchmark results show the superiority of AlphaFold 3 among existing methods, and the two proposed finetuning techniques can be well combined to achieve a state-of-the-art model for protein-glycan docking. Also, we perform stratified…
PDF arXiv

Activity · 12 weeks

Coming with more sources: repos

Fields · AI · updated 30m ago

Machine learned interatomic

Found by the topic model: machine learned interatomic, protein language models, molecular optimization.

41papers this week−46.1% vs last week

All papers · 296 With code · 4

Newest Most relevant

278 papers this month

Open problems in Machine learned interatomic

Reliable geometric reasoning over protein structures1 paper raises it · 2 address it
Frontier models excel at metadata lookup but struggle with numeric geometry tasks, limiting their use in structural biology.
Integration of foundation model inputs in biological reasoning1 paper raises it · 0 address it
Biological reasoning models often ignore foundation model inputs and rely on text, reducing their effectiveness.
- When Do Biological Reasoning Models Use Their Biological Inputs?raises
Scalable and durable pretraining data filtering for protein models1 paper raises it · 0 address it
Filtering pretraining data degrades performance on filtered domains but is easily undone by fine-tuning, limiting its long-term utility.
- The Effectiveness and Durability of Pretraining Data Filtering in Protein Language Modelsraises
Stable evaluation metrics for gene perturbation models1 paper raises it · 0 address it
Heterogeneous metrics and DE gene subsets lead to unstable rankings, obscuring true model performance.
- A Pitfall in the Evaluation of Gene Perturbation Modelsraises
Autoregressive generation of protein sequences and structures1 paper raises it · 2 address it
Autoregressive transformers underperform in protein sequence and structure generation due to weak target representations.
- Learning Latent Protein Languages for Autoregressive Generationraises · addresses
- recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Modelsaddresses

Named by an AI from these papers' abstracts.