Biology & Genomics

Manage electronic lab notebook entries, attachments and backups in LabArchive

Track, version and curate biological datasets with LaminDB

Build and deploy Latch bioinformatics workflows with the Latch SDK

Label cell types in multiplexed imaging and cytometry clusters from marker panels

Match mass spectra and identify metabolites with cosine similarity scores

Filter compound libraries with Lipinski, Veber, PAINS and structural alerts

Query NIH Metabolomics Workbench for studies, metabolites and MS or NMR data

Fit bacterial growth curves and model microbial community dynamics

Simulate PCR, restriction digests, Gibson and Golden Gate cloning in silico

Run end-to-end protein-ligand docking with pocket detection and pose ranking

Iterate on lead molecules with analyze, generate and verify optimization loops

Find similar ChEMBL and ZINC compounds to ground molecular property predictions

Draw publication-quality 2D molecule grids, scaffolds and 3D views

Balance several ADMET properties at once in Pareto-aware molecular design

Sort spikes and curate Neuropixels recordings with Kilosort4 and quality metrics

Build, run and debug Nextflow and nf-core pipelines with DSL2

Manage microscopy images, ROIs and annotations on OMERO from Python

Find 1000 Genomes individuals carrying specific variants in a gene or region

Write Opentrons OT-2 and Flex lab protocols with the Protocol API v2

Launch nf-core pacsomatic tumor-normal sequencing pipelines from BAM inputs

Run gene set enrichment on gene lists and see which pathways stand out

Analyze Western blots, xenograft tumor growth and Arrhenius stability data

Detect and score druggable binding pockets with fpocket and P2Rank

Run fast overlap, merge and coverage operations on BED and VCF with Polars

Design and validate de novo protein binders with NVIDIA BioNeMo workflows

Draw protein domain maps, contact maps and Ramachandran plots for papers

Search, create and publish scientific protocols through the protocols.io API

Find differentially expressed genes from RNA-seq counts with PyDESeq2

Program Hamilton, Tecan, plate readers and pumps through one lab automation API

Run proteomics feature detection and peptide identification with pyOpenMS

Read, write and filter SAM, BAM, VCF and FASTA genomic files in Python

Score animal welfare severity and predict humane endpoints with RELSA

Estimate RNA velocity and cell state trajectories in single-cell data

Validate SMILES strings and catch invalid molecules from LLM output

Compute contacts, hydrogen bonds and interfaces from PDB and mmCIF files

Predict protein 3D structures from sequence with ESMFold and pLDDT scores

Codon-optimize genes and simulate gene circuits and SBML models

Run AlphaFold, Boltz and other molecular design models through Tamarind Bio

Store and query population VCF variant data at scale with TileDB

Embed microbiome samples with the Waypoint foundation models from Outpost Bio

Search 230M+ purchasable ZINC compounds for virtual screening and analogs

Predict protein and ligand structures and binding affinity with Boltz2 NIM

Extract CodonFM embeddings from coding sequence CSVs for property modeling

Fine-tune public CodonFM Encodon checkpoints with LoRA or full training

Score coding variants with public CodonFM Encodon masked-codon models

Set up the CodonFM container and download public Encodon model weights

Score protein designs in a PDB folder for interface pAE, RMSD and designability

Run Proteina-Complexa parameter sweeps and rank designs by success rate

Define and validate Proteina-Complexa target sites for protein and ligand binders