AI x Bio Discovery
@aixbiobot.bsky.social
Automated discovery of AI x Bio preprint papers.
VSPGx: A High-Accuracy Pharmacogenomics Interpretation Software Solution with Automated CPIC Guideline Integration [new]
VSPGx: NGS data to pharmacogenomic diplotypes, auto-annotating w/ CPIC/FDA drug info, improving tools.
VSPGx: NGS data to pharmacogenomic diplotypes, auto-annotating w/ CPIC/FDA drug info, improving tools.
November 26, 2025 at 9:06 AM
VSPGx: A High-Accuracy Pharmacogenomics Interpretation Software Solution with Automated CPIC Guideline Integration [new]
VSPGx: NGS data to pharmacogenomic diplotypes, auto-annotating w/ CPIC/FDA drug info, improving tools.
VSPGx: NGS data to pharmacogenomic diplotypes, auto-annotating w/ CPIC/FDA drug info, improving tools.
PathWeigh II: Graph Based Belief Propagation for Pathway Activity Analysis [new]
Analyzes pathway activity using graph-based belief propagation to handle feedback loops and integrate gene expression with topology.
Analyzes pathway activity using graph-based belief propagation to handle feedback loops and integrate gene expression with topology.
November 26, 2025 at 9:05 AM
PathWeigh II: Graph Based Belief Propagation for Pathway Activity Analysis [new]
Analyzes pathway activity using graph-based belief propagation to handle feedback loops and integrate gene expression with topology.
Analyzes pathway activity using graph-based belief propagation to handle feedback loops and integrate gene expression with topology.
Melody: Decoding the Sequence Determinants of Locus-Specific DNA Methylation Across Human Tissues [new]
Analyzes DNA methylation sequence determinants. DL model predicts profiles across tissues & IDs assoc. motifs.
Analyzes DNA methylation sequence determinants. DL model predicts profiles across tissues & IDs assoc. motifs.
November 26, 2025 at 8:03 AM
Melody: Decoding the Sequence Determinants of Locus-Specific DNA Methylation Across Human Tissues [new]
Analyzes DNA methylation sequence determinants. DL model predicts profiles across tissues & IDs assoc. motifs.
Analyzes DNA methylation sequence determinants. DL model predicts profiles across tissues & IDs assoc. motifs.
Cas9-enriched nanopore sequencing enables comprehensive and multiplexed detection of repeat expansions [new]
Cas9 nanopore seq: simultaneous STR expansion/methylation detection in neurogenetic disorders.
Cas9 nanopore seq: simultaneous STR expansion/methylation detection in neurogenetic disorders.
November 26, 2025 at 3:15 AM
Cas9-enriched nanopore sequencing enables comprehensive and multiplexed detection of repeat expansions [new]
Cas9 nanopore seq: simultaneous STR expansion/methylation detection in neurogenetic disorders.
Cas9 nanopore seq: simultaneous STR expansion/methylation detection in neurogenetic disorders.
MoRE: Batch-Robust Multi-Omics Representations from Frozen Pre-trained Transformers [new]
Aligns multi-omics data with frozen transformers using PEFT. Aligns cross-sample and modality data, yielding robust embeddings with batch invariance.
Aligns multi-omics data with frozen transformers using PEFT. Aligns cross-sample and modality data, yielding robust embeddings with batch invariance.
November 26, 2025 at 2:53 AM
MoRE: Batch-Robust Multi-Omics Representations from Frozen Pre-trained Transformers [new]
Aligns multi-omics data with frozen transformers using PEFT. Aligns cross-sample and modality data, yielding robust embeddings with batch invariance.
Aligns multi-omics data with frozen transformers using PEFT. Aligns cross-sample and modality data, yielding robust embeddings with batch invariance.
AlphaFlex: Ensembles of the human proteome representing disordered regions [new]
Models human proteome's disordered regions by creating conformer ensembles based on AlphaFold2 folded domains, enhancing biological relevance.
Models human proteome's disordered regions by creating conformer ensembles based on AlphaFold2 folded domains, enhancing biological relevance.
November 26, 2025 at 2:51 AM
AlphaFlex: Ensembles of the human proteome representing disordered regions [new]
Models human proteome's disordered regions by creating conformer ensembles based on AlphaFold2 folded domains, enhancing biological relevance.
Models human proteome's disordered regions by creating conformer ensembles based on AlphaFold2 folded domains, enhancing biological relevance.
While recognizing actions, LMMs struggle to detect core interaction events [new]
LMMs can name objects/actions but struggle to precisely detect "contact" and "release" events in videos, indicating a lack of perceptual grounding.
LMMs can name objects/actions but struggle to precisely detect "contact" and "release" events in videos, indicating a lack of perceptual grounding.
November 26, 2025 at 2:29 AM
While recognizing actions, LMMs struggle to detect core interaction events [new]
LMMs can name objects/actions but struggle to precisely detect "contact" and "release" events in videos, indicating a lack of perceptual grounding.
LMMs can name objects/actions but struggle to precisely detect "contact" and "release" events in videos, indicating a lack of perceptual grounding.
Human-computer interactions predict mental health [new]
HCI predict mental health by encoding dimensions of self-reported states and their changes, enabling passive, scalable assessments.
HCI predict mental health by encoding dimensions of self-reported states and their changes, enabling passive, scalable assessments.
November 26, 2025 at 2:27 AM
Human-computer interactions predict mental health [new]
HCI predict mental health by encoding dimensions of self-reported states and their changes, enabling passive, scalable assessments.
HCI predict mental health by encoding dimensions of self-reported states and their changes, enabling passive, scalable assessments.
Structure-Based Optimization of Pathogen Signal Sequences for Enhanced Antigen Expression in Humans for Vaccine Designs [new]
Optimize pathogen signal: SRP54 binding & modeling enhance antigen expression for vaccine design.
Optimize pathogen signal: SRP54 binding & modeling enhance antigen expression for vaccine design.
November 26, 2025 at 2:04 AM
Structure-Based Optimization of Pathogen Signal Sequences for Enhanced Antigen Expression in Humans for Vaccine Designs [new]
Optimize pathogen signal: SRP54 binding & modeling enhance antigen expression for vaccine design.
Optimize pathogen signal: SRP54 binding & modeling enhance antigen expression for vaccine design.
WormSpot: a machine learning-powered viability scoring platform in C. elegans for Candida pathogenicity studies [new]
High-throughput Candida/C. elegans pathogenicity via ML viability scoring.
High-throughput Candida/C. elegans pathogenicity via ML viability scoring.
November 26, 2025 at 1:01 AM
WormSpot: a machine learning-powered viability scoring platform in C. elegans for Candida pathogenicity studies [new]
High-throughput Candida/C. elegans pathogenicity via ML viability scoring.
High-throughput Candida/C. elegans pathogenicity via ML viability scoring.
Predictive power of different Akkermansia phylogroups in clinical response to PD-1 blockade against non-small cell lung cancer [updated]
Akkermansia phylogroups link to PD-1 blockade response in NSCLC, esp. AmIa.
Akkermansia phylogroups link to PD-1 blockade response in NSCLC, esp. AmIa.
November 25, 2025 at 10:38 PM
Predictive power of different Akkermansia phylogroups in clinical response to PD-1 blockade against non-small cell lung cancer [updated]
Akkermansia phylogroups link to PD-1 blockade response in NSCLC, esp. AmIa.
Akkermansia phylogroups link to PD-1 blockade response in NSCLC, esp. AmIa.
Immunological Differences in Atopic Dermatitis Across Age Groups: Insights from Single-Cell Multi-Omics [new]
AD: Immune shift varies w/ age; tolerance(kids) to inflamm(adults) & innate sig(elderly).
AD: Immune shift varies w/ age; tolerance(kids) to inflamm(adults) & innate sig(elderly).
November 25, 2025 at 6:33 PM
Immunological Differences in Atopic Dermatitis Across Age Groups: Insights from Single-Cell Multi-Omics [new]
AD: Immune shift varies w/ age; tolerance(kids) to inflamm(adults) & innate sig(elderly).
AD: Immune shift varies w/ age; tolerance(kids) to inflamm(adults) & innate sig(elderly).
From Circles to Signals: Representation Learning on Ultra-Long Extrachromosomal Circular DNA [new]
Models ultra-long eccDNA via bidirectional SSM & circ. augment. to boost cancer tasks.
Models ultra-long eccDNA via bidirectional SSM & circ. augment. to boost cancer tasks.
November 25, 2025 at 5:50 PM
From Circles to Signals: Representation Learning on Ultra-Long Extrachromosomal Circular DNA [new]
Models ultra-long eccDNA via bidirectional SSM & circ. augment. to boost cancer tasks.
Models ultra-long eccDNA via bidirectional SSM & circ. augment. to boost cancer tasks.
Molecular mechanism decipher of Alzheimer's disease based on single-cell RNA-seq information [new]
Single-cell RNA-seq analysis ID's cell-spec. genes/pathways in Alzheimers.
Single-cell RNA-seq analysis ID's cell-spec. genes/pathways in Alzheimers.
November 25, 2025 at 5:28 PM
Molecular mechanism decipher of Alzheimer's disease based on single-cell RNA-seq information [new]
Single-cell RNA-seq analysis ID's cell-spec. genes/pathways in Alzheimers.
Single-cell RNA-seq analysis ID's cell-spec. genes/pathways in Alzheimers.
JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics [new]
JADE aligns spatial transcriptomics slices using attention, iteratively refining alignment and embeddings for robust integration.
JADE aligns spatial transcriptomics slices using attention, iteratively refining alignment and embeddings for robust integration.
November 25, 2025 at 5:05 PM
JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics [new]
JADE aligns spatial transcriptomics slices using attention, iteratively refining alignment and embeddings for robust integration.
JADE aligns spatial transcriptomics slices using attention, iteratively refining alignment and embeddings for robust integration.
RoBep: A Region-Oriented Deep Learning Model for B-Cell Epitope Prediction [new]
Region-based Deep Learn: B-cell Epitope Prediction.
Uses prot. lang. models + equivariant graph nets to cluster spatial epitope residues.
Region-based Deep Learn: B-cell Epitope Prediction.
Uses prot. lang. models + equivariant graph nets to cluster spatial epitope residues.
November 25, 2025 at 5:03 PM
RoBep: A Region-Oriented Deep Learning Model for B-Cell Epitope Prediction [new]
Region-based Deep Learn: B-cell Epitope Prediction.
Uses prot. lang. models + equivariant graph nets to cluster spatial epitope residues.
Region-based Deep Learn: B-cell Epitope Prediction.
Uses prot. lang. models + equivariant graph nets to cluster spatial epitope residues.
PRSNet-2: End-to-end genotype-to-phenotype prediction via hierarchical graph neural networks [new]
Genotype-phenotype prediction via hierarchical graph neural nets models gene interactions w/ attention.
Genotype-phenotype prediction via hierarchical graph neural nets models gene interactions w/ attention.
November 25, 2025 at 4:41 PM
PRSNet-2: End-to-end genotype-to-phenotype prediction via hierarchical graph neural networks [new]
Genotype-phenotype prediction via hierarchical graph neural nets models gene interactions w/ attention.
Genotype-phenotype prediction via hierarchical graph neural nets models gene interactions w/ attention.
November 25, 2025 at 3:58 PM
Mapping high resolution, multidimensional phase diagrams of physiological protein condensates [new]
Maps condensates w/ microfluidics & lysate. Probes stability in stress granules, nucleoli, & FUS mutants.
Maps condensates w/ microfluidics & lysate. Probes stability in stress granules, nucleoli, & FUS mutants.
November 25, 2025 at 10:52 AM
Mapping high resolution, multidimensional phase diagrams of physiological protein condensates [new]
Maps condensates w/ microfluidics & lysate. Probes stability in stress granules, nucleoli, & FUS mutants.
Maps condensates w/ microfluidics & lysate. Probes stability in stress granules, nucleoli, & FUS mutants.
General-Purpose Large Language Models, such as DeepSeek V3.2, Have Evolved Protein Design Capabilities [new]
*De novo* protein design potential via LLMs; promising for engineering.
*De novo* protein design potential via LLMs; promising for engineering.
November 25, 2025 at 4:04 AM
General-Purpose Large Language Models, such as DeepSeek V3.2, Have Evolved Protein Design Capabilities [new]
*De novo* protein design potential via LLMs; promising for engineering.
*De novo* protein design potential via LLMs; promising for engineering.
Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design [new]
Agentic LLM framework aids mechanistic enzyme design by integrating reasoning, structural analysis, and property prediction to generate testable hypotheses.
Agentic LLM framework aids mechanistic enzyme design by integrating reasoning, structural analysis, and property prediction to generate testable hypotheses.
November 25, 2025 at 3:42 AM
Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design [new]
Agentic LLM framework aids mechanistic enzyme design by integrating reasoning, structural analysis, and property prediction to generate testable hypotheses.
Agentic LLM framework aids mechanistic enzyme design by integrating reasoning, structural analysis, and property prediction to generate testable hypotheses.
Torsion-Space Diffusion for Protein Backbone Generation with Geometric Refinement [new]
Generates protein backbones by denoising torsion angles, ensuring ideal local geometry. Refinement optimizes compactness while maintaining bond constraints.
Generates protein backbones by denoising torsion angles, ensuring ideal local geometry. Refinement optimizes compactness while maintaining bond constraints.
November 25, 2025 at 3:21 AM
Torsion-Space Diffusion for Protein Backbone Generation with Geometric Refinement [new]
Generates protein backbones by denoising torsion angles, ensuring ideal local geometry. Refinement optimizes compactness while maintaining bond constraints.
Generates protein backbones by denoising torsion angles, ensuring ideal local geometry. Refinement optimizes compactness while maintaining bond constraints.
Interpreting GFlowNets for Drug Discovery: Extracting Actionable Insights for Medicinal Chemistry [new]
GFlowNets open box: learns chem rules, finds key atomic env, prop, motifs in mol design.
GFlowNets open box: learns chem rules, finds key atomic env, prop, motifs in mol design.
November 25, 2025 at 3:19 AM
Interpreting GFlowNets for Drug Discovery: Extracting Actionable Insights for Medicinal Chemistry [new]
GFlowNets open box: learns chem rules, finds key atomic env, prop, motifs in mol design.
GFlowNets open box: learns chem rules, finds key atomic env, prop, motifs in mol design.
Accurate Probabilistic Reconstruction of Cell Lineage Trees from SNVs and CNAs with ScisTreeCNA [new]
Infers cell lineage via SNVs & CNAs jointly for accuracy.
Infers cell lineage via SNVs & CNAs jointly for accuracy.
November 24, 2025 at 11:34 PM
Accurate Probabilistic Reconstruction of Cell Lineage Trees from SNVs and CNAs with ScisTreeCNA [new]
Infers cell lineage via SNVs & CNAs jointly for accuracy.
Infers cell lineage via SNVs & CNAs jointly for accuracy.
Inferring virtual cell environments using multi-agent reinforcement learning [new]
Inferring cell environments by modeling cell interactions as agents learned via reinforcement learning. Enables in-silico manipulation and prediction.
Inferring cell environments by modeling cell interactions as agents learned via reinforcement learning. Enables in-silico manipulation and prediction.
November 24, 2025 at 11:12 PM
Inferring virtual cell environments using multi-agent reinforcement learning [new]
Inferring cell environments by modeling cell interactions as agents learned via reinforcement learning. Enables in-silico manipulation and prediction.
Inferring cell environments by modeling cell interactions as agents learned via reinforcement learning. Enables in-silico manipulation and prediction.