SonicParanoid

{{Multiple issues|

{{Orphan|date=September 2020}}

{{Context|date=April 2020}}

}}

SonicParanoid is an algorithm for the de-novo prediction of orthologous genes among multiple species.{{cite journal

|last1 = Cosentino

|first1 = Salvatore

|last2 = Iwasaki

|first2 = Wataru

|year= 2019

|title= SonicParanoid: fast, accurate and easy orthology inference

|journal= Bioinformatics

|volume= 35

|issue= 1

|pages= 149–151

|doi= 10.1093/bioinformatics/bty631

| pmid = 30032301

|pmc = 6298048

}} It borrows the main idea from InParanoid{{Cite journal

| doi = 10.1006/jmbi.2000.5197

| year = 2001

| volume = 314

| issue = 5

| pages = 1041–1052

| last = Remm

| first = Maido

|author2=Christian E.V. Storm |author3=Erik L.L. Sonnhammer

| title = Automatic clustering of orthologs and in-paralogs from pairwise species comparisons

| journal = Journal of Molecular Biology

| pmid = 11743721

| citeseerx = 10.1.1.328.6724

}} with substantial changes to the algorithm that drastically reduce the time required for the analysis. Additionally, SonicParanoid generates groups of orthologous genes shared among the input proteomes using single-linkage hierarchical clustering or markov clustering. The latest iteration of SonicParanoid uses machine learning to substantially reduce execution times, and language models to infer orthologs at the domain level.{{cite journal |last1=Cosentino |first1=Salvatore |last2=Sriswasdi |first2=Sira |last3=Iwasaki |first3=Wataru |title=SonicParanoid2: fast, accurate, and comprehensive orthology inference with machine learning and language models |journal=Genome Biology |date=25 July 2024 |volume=25 |issue=1 |pages=195 |doi=10.1186/s13059-024-03298-4 |doi-access=free |pmid=39054525|pmc = 11270883}}