Papers

Field

Top tools here

Open problems in Machine learned interatomic

Reliable geometric reasoning from protein structures1 paper raises it · 2 address it
Frontier models excel at metadata lookup but struggle with numeric geometry tasks, which are critical for structural biology.
Effective integration of biological foundation model inputs1 paper raises it · 1 addresses it
Biological reasoning models often ignore foundation model inputs, relying instead on text, which limits their accuracy and interpretability.
- When Do Biological Reasoning Models Use Their Biological Inputs?raises
- Does Learning Protein Folding Generalize to Broader Reasoning?addresses
Scalable and robust protein sequence and structure generation1 paper raises it · 2 address it
Autoregressive models for protein generation are weak, and current representations lack contextual semantics or efficient discrete encodings.
- Learning Latent Protein Languages for Autoregressive Generationraises · addresses
- recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Modelsaddresses
Durable and selective pretraining data filtering1 paper raises it · 1 addresses it
Filtering pretraining data can degrade performance on specific domains, but fine-tuning can easily undo these effects, limiting its long-term utility.
- The Effectiveness and Durability of Pretraining Data Filtering in Protein Language Modelsraises · addresses
Stable evaluation metrics for gene perturbation models1 paper raises it · 0 address it
Heterogeneous metrics and DE gene subsets lead to unstable rankings, undermining fair comparisons across methods.
- A Pitfall in the Evaluation of Gene Perturbation Modelsraises

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

molecular optimization · molecular design · molecular generation100 papers19 this week
protein language models · protein language · protein structure107 papers16 this week
machine learned interatomic · crystal structure prediction · learned interatomic potentials101 papers10 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

Recent papers

All in Research →

arXiv cs.AIOct 5
From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
Pierre Llompart, Levent Guner, Helen Lai, Alessandro Tibo, Yijie Xu
Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We developed MAGI, an open modular agent that authors objectives, launches and monitors optimization, interprets structure--activity relationships, and revises its strategy accordingly. MAGI generates molecules either directly through the LLM or by delegating to REINVENT 4, with scoring services interchangeable behind a common contract. We tested it across nine retrospective lead-optimization campaigns from three pharmaceutical companies, replayed under fixed temporal cutoffs. Both routes produced valid structures: LLM proposals stayed closer to local chemistry and reached comparable or higher primary activity in fewer operations, whereas REINVENT explored broader chemical space. Whether a campaign met its objective depended on the predictive models, not on the generation route: attainment followed model accuracy on the chemistry proposed, dropping once that chemistry moved outside the model's applicability domain. Separately, a blinded evaluation asked whether the MAGI's output could pass as expert work: chemists were not able to…
PDF arXiv
arXiv cs.LGOct 5
FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials
Viktor Zaverkin, Payman Goodarzi, Sergey V. Sukhomlinov, Davit Hovhannisyan, Roland Aydin +2
Machine-learned interatomic potentials extend atomistic simulations beyond the length- and timescales accessible to electronic-structure methods. However, the computational cost of equivariant architectures limits the local correlations they can represent in practice and therefore their achievable accuracy. Here we introduce FlashCart, which makes higher-order correlations affordable by combining generated GPU kernels with an architecture that recursively builds equivariant features and compresses them to a fixed width at each step. We express tensor products in independent Cartesian components and symbolically simplify them and their derivatives, producing fused kernels that often outperform optimized spherical counterparts. We then show that increasing correlation order improves accuracy more efficiently than increasing width, depth, or tensor rank. On SPICE-MACE-OFF, FlashCart models advance the measured accuracy-efficiency frontier: a model with $5.6$ million parameters achieves lower energy and force errors and $10\times$ faster inference than a transformer with $189$ million parameters.
PDF arXiv
arXiv cs.CLOct 5
Agentic schema-guided extraction of materials process knowledge from scientific literature
Sameer Sadruddin, Jennifer D'Souza
Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported in heterogeneous forms and depend on process-specific context. We present SciKGExtract, a schema-guided framework that combines large-language-model extraction with chemical normalization and agent-based evaluation and refinement before knowledge-graph integration. We evaluate the framework on 176 atomic-layer-deposition papers describing zinc oxide (ZnO) and indium--gallium--zinc oxide (IGZO), together with an expert-annotated full-schema subset. PubChem normalization improves exact-match extraction F1 for every tested model. For ZnO, the best F1 increases from 0.591 for direct normalized extraction to 0.805 with agentic refinement, whereas the best IGZO result is 0.344, revealing the greater difficulty of multicomponent supercycle processes. Evaluation against a deeply nested schema containing 65 experimental properties and 155 quantitative measurement nodes further exposes errors in process segmentation and numerical assignment. These results show that chemical canonicalization and targeted agentic…
PDF arXiv
arXiv cs.LGOct 5
dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra
Alfred Nilsson, Joel Lapin, Samuel H. Payne, Mathias Wilhelm, Lukas Käll
We introduce a novel invariance for peptide tandem mass spectrometry data, unlocking self-supervised representation learning that improves de novo sequencing of peptides. This invariance exploits the physical relationship between precursor properties (mass and charge) and fragment-ion evidence, without requiring peptide sequence labels. We introduce dIon, which adapts the DINO framework with two latent prediction tasks, both recovering a clean teacher representation: one from a spectrum mixture, using the precursor as a selection query, and one from a partial spectrum with the precursor withheld. The first associates precursor information with fragment-ion evidence; the second prevents representational collapse onto that information alone. Mechanistic probes support both effects, and ablations show that the full objective performs best. Under identical end-to-end training, dIon initialization improves de novo peptide precision over training from scratch by 5.5 and 8.4 percentage points on the held-out MassIVE-KB and Kingdoms test sets, and by 2.3 and 4.8 percentage points with a larger supervised training corpus. The resulting models surpass fully supervised state-of-the-art de…
PDF arXiv
arXiv cs.AIOct 5
Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design
Haosen Zhang, Yang Yang
Large language models (LLMs) can reason over scientific literature to devise design strategies, yet fail to reliably implement them for biological sequences. While protein generative models learn sequence patterns, they lack the capacity to incorporate literature evidence for multi-step reflective reasoning, forming an evidence-to-execution gap between scientific reasoning and sequence manipulation. We present EASER (Evidence-Aware Sequence Engineering with Reflection), a reflective agent bridging reasoning and sequence generation via a learned property interface of offline-trained, fixed low-rank matrices. The agent steers a diffusion generator by combining these matrices, proposing intervention hypotheses (anchors, editable positions, control coefficients) grounded in retrieved evidence, sequence context and past results. A Probe-and-Steer mechanism validates interventions and allocates samples according to predicted property responses, with outcome reflection informing subsequent decisions. Evaluated on multi-objective antimicrobial peptide design (optimizing activity, non-hemolysis and non-toxicity), explicit hypothesis formulation delivers better multi-objective performance…
PDF arXiv
arXiv cs.LGOct 5
Few-Shot Bioactivity Prediction with Meta-Learning under Assay Heterogeneity
Michal Kmicikiewicz, Tommy Rochussen, Vincent Fortuin, Ewa Szczurek
Accurate bioactivity prediction is a central challenge in early-stage drug discovery, as individual assays often contain too few measurements to train reliable models independently. Meta-learning offers a principled approach to this few-shot setting, but assay heterogeneity may limit its effectiveness. Here, we test this hypothesis and show that meta-learning performance degrades as meta-training tasks become more heterogeneous. To address this, we introduce MetaHeta, a meta-learning framework that accounts for assay heterogeneity by conditioning predictions on auxiliary data from related assays, with relatedness defined flexibly from available assay information. The architecture of MetaHeta combines linear attention over large auxiliary datasets with exact attention over scarce task-specific context, enabling efficient scaling to the former without compromising exact attention over the latter. We demonstrate the benefits of our approach on assays from ChEMBL and BindingDB, improving few-shot bioactivity prediction and downstream compound prioritization in retrospective Bayesian optimization.
PDF arXiv

Papers

Topics in this field

molecular optimization · molecular design · molecular generation100 papers19 this week
protein language models · protein language · protein structure107 papers16 this week
machine learned interatomic · crystal structure prediction · learned interatomic potentials101 papers10 this week

Active contributors · 90 days

Activity · 12 weeks

Coming with more sources: repos

Recent papers

All in Research →

arXiv cs.AIOct 5
From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
Pierre Llompart, Levent Guner, Helen Lai, Alessandro Tibo, Yijie Xu
Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We developed MAGI, an open modular agent that authors objectives, launches and monitors optimization, interprets structure--activity relationships, and revises its strategy accordingly. MAGI generates molecules either directly through the LLM or by delegating to REINVENT 4, with scoring services interchangeable behind a common contract. We tested it across nine retrospective lead-optimization campaigns from three pharmaceutical companies, replayed under fixed temporal cutoffs. Both routes produced valid structures: LLM proposals stayed closer to local chemistry and reached comparable or higher primary activity in fewer operations, whereas REINVENT explored broader chemical space. Whether a campaign met its objective depended on the predictive models, not on the generation route: attainment followed model accuracy on the chemistry proposed, dropping once that chemistry moved outside the model's applicability domain. Separately, a blinded evaluation asked whether the MAGI's output could pass as expert work: chemists were not able to…
PDF arXiv
arXiv cs.LGOct 5
FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials
Viktor Zaverkin, Payman Goodarzi, Sergey V. Sukhomlinov, Davit Hovhannisyan, Roland Aydin +2
Machine-learned interatomic potentials extend atomistic simulations beyond the length- and timescales accessible to electronic-structure methods. However, the computational cost of equivariant architectures limits the local correlations they can represent in practice and therefore their achievable accuracy. Here we introduce FlashCart, which makes higher-order correlations affordable by combining generated GPU kernels with an architecture that recursively builds equivariant features and compresses them to a fixed width at each step. We express tensor products in independent Cartesian components and symbolically simplify them and their derivatives, producing fused kernels that often outperform optimized spherical counterparts. We then show that increasing correlation order improves accuracy more efficiently than increasing width, depth, or tensor rank. On SPICE-MACE-OFF, FlashCart models advance the measured accuracy-efficiency frontier: a model with $5.6$ million parameters achieves lower energy and force errors and $10\times$ faster inference than a transformer with $189$ million parameters.
PDF arXiv
arXiv cs.CLOct 5
Agentic schema-guided extraction of materials process knowledge from scientific literature
Sameer Sadruddin, Jennifer D'Souza
Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported in heterogeneous forms and depend on process-specific context. We present SciKGExtract, a schema-guided framework that combines large-language-model extraction with chemical normalization and agent-based evaluation and refinement before knowledge-graph integration. We evaluate the framework on 176 atomic-layer-deposition papers describing zinc oxide (ZnO) and indium--gallium--zinc oxide (IGZO), together with an expert-annotated full-schema subset. PubChem normalization improves exact-match extraction F1 for every tested model. For ZnO, the best F1 increases from 0.591 for direct normalized extraction to 0.805 with agentic refinement, whereas the best IGZO result is 0.344, revealing the greater difficulty of multicomponent supercycle processes. Evaluation against a deeply nested schema containing 65 experimental properties and 155 quantitative measurement nodes further exposes errors in process segmentation and numerical assignment. These results show that chemical canonicalization and targeted agentic…
PDF arXiv
arXiv cs.LGOct 5
dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra
Alfred Nilsson, Joel Lapin, Samuel H. Payne, Mathias Wilhelm, Lukas Käll
We introduce a novel invariance for peptide tandem mass spectrometry data, unlocking self-supervised representation learning that improves de novo sequencing of peptides. This invariance exploits the physical relationship between precursor properties (mass and charge) and fragment-ion evidence, without requiring peptide sequence labels. We introduce dIon, which adapts the DINO framework with two latent prediction tasks, both recovering a clean teacher representation: one from a spectrum mixture, using the precursor as a selection query, and one from a partial spectrum with the precursor withheld. The first associates precursor information with fragment-ion evidence; the second prevents representational collapse onto that information alone. Mechanistic probes support both effects, and ablations show that the full objective performs best. Under identical end-to-end training, dIon initialization improves de novo peptide precision over training from scratch by 5.5 and 8.4 percentage points on the held-out MassIVE-KB and Kingdoms test sets, and by 2.3 and 4.8 percentage points with a larger supervised training corpus. The resulting models surpass fully supervised state-of-the-art de…
PDF arXiv
arXiv cs.AIOct 5
Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design
Haosen Zhang, Yang Yang
Large language models (LLMs) can reason over scientific literature to devise design strategies, yet fail to reliably implement them for biological sequences. While protein generative models learn sequence patterns, they lack the capacity to incorporate literature evidence for multi-step reflective reasoning, forming an evidence-to-execution gap between scientific reasoning and sequence manipulation. We present EASER (Evidence-Aware Sequence Engineering with Reflection), a reflective agent bridging reasoning and sequence generation via a learned property interface of offline-trained, fixed low-rank matrices. The agent steers a diffusion generator by combining these matrices, proposing intervention hypotheses (anchors, editable positions, control coefficients) grounded in retrieved evidence, sequence context and past results. A Probe-and-Steer mechanism validates interventions and allocates samples according to predicted property responses, with outcome reflection informing subsequent decisions. Evaluated on multi-objective antimicrobial peptide design (optimizing activity, non-hemolysis and non-toxicity), explicit hypothesis formulation delivers better multi-objective performance…
PDF arXiv
arXiv cs.LGOct 5
Few-Shot Bioactivity Prediction with Meta-Learning under Assay Heterogeneity
Michal Kmicikiewicz, Tommy Rochussen, Vincent Fortuin, Ewa Szczurek
Accurate bioactivity prediction is a central challenge in early-stage drug discovery, as individual assays often contain too few measurements to train reliable models independently. Meta-learning offers a principled approach to this few-shot setting, but assay heterogeneity may limit its effectiveness. Here, we test this hypothesis and show that meta-learning performance degrades as meta-training tasks become more heterogeneous. To address this, we introduce MetaHeta, a meta-learning framework that accounts for assay heterogeneity by conditioning predictions on auxiliary data from related assays, with relatedness defined flexibly from available assay information. The architecture of MetaHeta combines linear attention over large auxiliary datasets with exact attention over scarce task-specific context, enabling efficient scaling to the former without compromising exact attention over the latter. We demonstrate the benefits of our approach on assays from ChEMBL and BindingDB, improving few-shot bioactivity prediction and downstream compound prioritization in retrospective Bayesian optimization.
PDF arXiv

Open problems in Machine learned interatomic

Reliable geometric reasoning from protein structures1 paper raises it · 2 address it
Frontier models excel at metadata lookup but struggle with numeric geometry tasks, which are critical for structural biology.
Effective integration of biological foundation model inputs1 paper raises it · 1 addresses it
Biological reasoning models often ignore foundation model inputs, relying instead on text, which limits their accuracy and interpretability.
- When Do Biological Reasoning Models Use Their Biological Inputs?raises
- Does Learning Protein Folding Generalize to Broader Reasoning?addresses
Scalable and robust protein sequence and structure generation1 paper raises it · 2 address it
Autoregressive models for protein generation are weak, and current representations lack contextual semantics or efficient discrete encodings.
- Learning Latent Protein Languages for Autoregressive Generationraises · addresses
- recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Modelsaddresses
Durable and selective pretraining data filtering1 paper raises it · 1 addresses it
Filtering pretraining data can degrade performance on specific domains, but fine-tuning can easily undo these effects, limiting its long-term utility.
- The Effectiveness and Durability of Pretraining Data Filtering in Protein Language Modelsraises · addresses
Stable evaluation metrics for gene perturbation models1 paper raises it · 0 address it
Heterogeneous metrics and DE gene subsets lead to unstable rankings, undermining fair comparisons across methods.
- A Pitfall in the Evaluation of Gene Perturbation Modelsraises

Named by an AI from these papers' abstracts.

Fields · AI · updated 44m ago

Machine learned interatomic

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

45papers this week−42.3% vs last week

All papers · 308 With code · 4

Newest Most relevant

287 papers this month