Anthony Gitter

A Framework for Benchmarking Pathway Reconstruction Algorithms

This paper benchmarks 14 pathway reconstruction algorithms across 822 datasets using a standardized framework to evaluate performance, similarity, and computational efficiency.

BoltzMol-1: Towards Reliable Virtual Screening for Fast and Cost-Effective Hit Discovery

BoltzMol-1 identifies chemically tractable binders for diverse targets with limited experimental resources using model-driven ranking and physicochemical filtering.

Protein Set Transformer: A protein-based genome language model to power high diversity viromics

The paper introduces PST, a protein-based genome language model that outperforms existing methods in relating viral genomes through shared protein content and demonstrates structural and functional awareness.

Democratizing Protein Language Model Training, Sharing and Collaboration

The paper introduces SaprotHub, a platform that simplifies training and sharing of protein language models, enabling non-experts to build and collaborate on customized models.

MPAC: a computational framework for inferring pathway activities from multi-omic data

MPAC infers pathway activities from multi-omic data to identify patient subgroups and clinically relevant proteins, demonstrating improved results over single-omic analyses in head and neck cancer.

Biophysics-based protein language models for protein engineering

This paper introduces METL, a protein language model that integrates biophysical modeling with machine learning to predict protein properties and design functional variants.

Crowdsourced Protein Design: Lessons From the Adaptyv EGFR Binder Competition

The paper analyzes a crowdsourced protein design competition, showing participants designed EGFR binders with varying affinities and highlighting challenges in benchmarking and experimental design.

Decoding the Molecular Language of Proteins with Evolla

Evolla, a protein-language model, improves functional inference and discovers novel proteins through natural language queries and benchmarking.

Network Inference with Granger Causality Ensembles on Single-Cell Transcriptomic Data

This paper introduces SINGE, a method for gene regulatory network inference from ordered single-cell transcriptomic data, showing improved performance over existing methods in mouse stem cell differentiation studies.

Neural networks to learn protein sequence-function relationships from deep mutational scanning data

This paper develops a deep learning framework to predict protein function from sequence using deep mutational scanning data and demonstrates its ability to design new proteins with improved properties.

Automating parameter selection to avoid implausible biological pathway models

This paper develops a method to tune pathway reconstruction algorithms to avoid biologically implausible predictions by using graphlet decomposition metrics and pathway databases.

Lag Penalized Weighted Correlation for Time Series Clustering

The paper introduces a time series clustering method called Lag Penalized Weighted Correlation (LPWC) that captures temporal patterns and outperforms existing methods in simulated and biological datasets.

Classifying T cell activity in autofluorescence intensity images with convolutional neural networks

The paper uses convolutional neural networks to classify T cell activity from autofluorescence intensity images and shows that pre-trained models outperform traditional methods.

Learning Drug Function from Chemical Structure with Convolutional Neural Networks and Random Forests

The paper predicts drug classification from chemical structure using CNN and random forests, achieving better accuracy than transcriptomic-based methods.

Synthesizing Signaling Pathways from Temporal Phosphoproteomic Data

The paper introduces a computational method to identify missing signaling pathway elements from temporal phosphoproteomic data, demonstrating its effectiveness in both human EGF response and yeast osmotic stress response.

Network inference reveals novel connections in pathways regulating growth and defense in the yeast salt response

The paper infers a signaling network regulating phosphorylation changes in yeast during salt stress, revealing novel interactions between stress and growth pathways.

Opportunities And Obstacles For Deep Learning In Biology And Medicine

Deep learning rivals or beats baselines across imaging, health records, genomics and drug discovery but is not yet transformative; scarce labels, privacy and opacity remain hurdles.